{
  "skillId": "minimax-h3-official",
  "kind": "markdown",
  "title": "MiniMax H3 official skills",
  "language": "en",
  "capturedAt": "2026-09-13T11:12:04.211Z",
  "source": {
    "url": "https://github.com/MiniMax-AI/MiniMax-H3",
    "author": "MiniMax-AI",
    "revision": "d21241f0a4b3acbb34c97dae47fa417b7065e438"
  },
  "sections": [
    {
      "url": "https://github.com/MiniMax-AI/MiniMax-H3/blob/main/skills/h3-prompt-writing/SKILL.md",
      "title": "h3-prompt-writing",
      "anchor": "skill-h3-prompt-writing",
      "blocks": [
        {
          "type": "quote",
          "inlines": [
            {
              "t": "Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal requests into H3 prompt structures, composing integrated_multimodal_description, overall_soundscape, and non_diegetic_music, aligning keyframes, or defining reference labels for images, videos, and audio."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "H3 Prompt Writing"
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Workflow"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Identify the input mode: T2VA, I2VA, FL2VA, L2VA, or full-reference Ref2VA."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "For base text/keyframe modes, read "
                },
                {
                  "c": true,
                  "t": "references/base-en.txt"
                },
                {
                  "t": " and follow its final prompt structure."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "For full-reference mode, read "
                },
                {
                  "c": true,
                  "t": "references/ref-en.txt"
                },
                {
                  "t": " and follow its six-section rewrite format."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Preserve the exact field names, section order, labels, and timing notation from the selected guide."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Base Modes"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "T2VA: build the full audiovisual timeline from text."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "I2VA: start from the first frame and develop forward from it."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "FL2VA: describe the continuous path between the first and last frames."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "L2VA: infer a plausible opening and converge to the supplied last frame."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use "
            },
            {
              "c": true,
              "t": "integrated_multimodal_description"
            },
            {
              "t": ", "
            },
            {
              "c": true,
              "t": "overall_soundscape"
            },
            {
              "t": ", and "
            },
            {
              "c": true,
              "t": "non_diegetic_music"
            },
            {
              "t": " in the order shown in "
            },
            {
              "c": true,
              "t": "references/base-en.txt"
            },
            {
              "t": "."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Full-Reference Mode"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Ref2VA rewrites use "
            },
            {
              "c": true,
              "t": "subject_definitions"
            },
            {
              "t": ", "
            },
            {
              "c": true,
              "t": "summary"
            },
            {
              "t": ", "
            },
            {
              "c": true,
              "t": "retention_analysis"
            },
            {
              "t": ", "
            },
            {
              "c": true,
              "t": "detailed_description"
            },
            {
              "t": ", "
            },
            {
              "c": true,
              "t": "overall_soundscape"
            },
            {
              "t": ", and "
            },
            {
              "c": true,
              "t": "non_diegetic_music"
            },
            {
              "t": " in that order. Reference labels stay consistent across all sections."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Read "
            },
            {
              "c": true,
              "t": "references/ref-en.txt"
            },
            {
              "t": " for label rules, retention analysis, and complete examples."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Output Rules"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Write rewrite sections in English; preserve dialogue, lyrics, and visible scene text in their original language."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Describe each shot by composition, subjects, environment, actions, camera, sound, and the exact point where referenced content appears."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Avoid plot summaries, unresolved reference labels, and timing that does not match the requested duration."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Tips for Better Results"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Always match the total duration of the description to the requested video length (4–15 seconds)."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Keep reference labels consistent (e.g. "
                },
                {
                  "c": true,
                  "t": "<Picture 1>"
                },
                {
                  "t": ", "
                },
                {
                  "c": true,
                  "t": "<Video 1>"
                },
                {
                  "t": ", "
                },
                {
                  "c": true,
                  "t": "<Audio 1>"
                },
                {
                  "t": ") across every section."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Prefer concrete visual and audio details over abstract words like \"cinematic\" or \"beautiful\"."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "When using keyframes (I2VA / FL2VA / L2VA), clearly state how the first and/or last frame connects to the timeline."
                }
              ]
            }
          ]
        }
      ]
    },
    {
      "url": "https://github.com/MiniMax-AI/MiniMax-H3/blob/main/skills/3d-animation-short-generator/SKILL.md",
      "title": "3d-animation-short-generator",
      "anchor": "skill-3d-animation-short-generator",
      "blocks": [
        {
          "type": "quote",
          "inlines": [
            {
              "t": "Create complete stylized 3D animated shorts from a story idea through an ordered production workflow covering project brief, story outline, character and environment cards, standardized shot planning, text or optional pencil storyboards, video-model selection, single-shot generation, assembly, BGM matching, and final review. Use when the user wants an end-to-end narrative animation workflow with strong character consistency, scene continuity, timing, camera, performance, and audio control. Not for single images, simple edits, photorealistic live action, or one standalone clip."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "3D Animation Short Generator"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use this Skill when the user wants a complete story-first animated short workflow, from one-line idea to final edited video. The workflow must place every major artifact on the canvas in production order and pause at creative gates with user choice cards before expensive or high-impact steps."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Core rule: "
            },
            {
              "b": true,
              "t": "story first, ask screen size and total duration with choice cards immediately after user intake, ordered canvas artifacts, every required confirmation via choice card, fixed order after character/scene cards: six-column standardized shot table with per-second directives + audio cues + spatial anchor chain → shot-table self-check gate → one single text storyboards document with one section per shot (multi-panel pencil image only when user explicitly opts into visualization mode; any shot flagged for heavy iteration is extracted to a standalone text storyboard node) → video-model choice card (H3 default, Seedance 2.0 fallback) + resolution choice card → single-shot clips rendered by the chosen video model → full-film assembly with BGM; final video must remove all storyboard artifacts"
            },
            {
              "t": "."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Global Visual Style Lock"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Unless the user explicitly requests another visual style, all character cards, scene cards, shot tables, text storyboards, optional pencil storyboards, single-shot video clips (regardless of which video model is selected), assembled videos, and final composites must use this visual style:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Rendering style: Pixar-inspired 3D cartoon rendering, C4D + Octane renderer look, high-end animated feature quality."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Character design: exaggerated geometric simplification balanced with excellent material detail. Avoid 100% realistic human anatomy; use high-level shape language, large readable silhouettes, and Q-version proportions when appropriate."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Proportion language: friendly stylized proportions, often 2.5–3 head-tall for cute or childlike characters, with big heads, compact bodies, clear silhouettes, and high recognizability."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Hair / fur: combine strong sculpted clumps and clean block shapes with fine edge flyaway hairs or fuzzy rim details, so hair/fur feels designed but tactile under light."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Skin / material: warm subsurface scattering skin quality, soft translucent reddish light through ears, cheeks, nose, and fingertips; avoid hard plastic skin."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Acting style: exaggerated, lively Disney/Pixar-style character animation performance with squash and stretch, strong brows, eye corners, pupils, lips, and cheek shape changes."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Motion style: high-energy poses, clear line of action, forward lean, strong anticipation, fast but readable timing, elastic body mechanics, and vivid micro-expressions."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Emotional range: balance cuteness and explosive expressiveness; intense emotions may use dramatic facial deformation while preserving character appeal."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Negative style constraints: no photorealistic live-action, no flat 2D anime, no plastic toy skin, no stiff mannequin posing, no realistic anatomical stiffness, no lifeless facial expressions."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 0: Intake and Canvas Plan"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Capture:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "One-line idea or rough premise"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Desired output: blueprint only, assets only, standardized shot table with per-second directives, single text storyboards document (default) + extracted single-shot text storyboard nodes for heavy-iteration shots + multi-panel pencil storyboards (opt-in), single-shot video clips (with video model chosen in Step 7), assembled main video, or final BGM-composited film"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Approximate length, if the user already stated it"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Screen size / aspect ratio, if the user already stated it"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Visual tone: default warm stylized 3D animation"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Dialogue requirement: whether the film has dialogue, voiceover, or no speech"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Dialogue language only if the user explicitly states it; do not default to English dialogue"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Immediately after capturing the user's input, before Project Brief or any other next step, show choice cards to confirm production format:"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Screen size / aspect ratio card:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "16:9 landscape (recommended for cinematic short)"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "9:16 vertical short"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "1:1 square"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "4:5 social portrait"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Custom size / aspect ratio"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Total duration card:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "30–60 seconds (recommended)"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "15–30 seconds"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "60–90 seconds"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "90–180 seconds"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Custom duration"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Only proceed after the user chooses both screen size/aspect ratio and total duration, or explicitly supplies custom values. Store the approved screen size/aspect ratio and duration in the Project Brief and reuse them in shot timing, transition continuity, the standardized shot table with per-second directives, single-shot storyboards (text by default, pencil image when user opts in), single-shot video clips, assembly, BGM matching, and final composite settings."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Create or later update canvas artifacts in this order:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Project Brief text node"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Story Outline text node"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Labeled Character Card image nodes"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Environment-only Scene Card image nodes"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Standardized Shot Information Table node with six columns; each row must include per-second directives inside "
                },
                {
                  "c": true,
                  "t": "Shot Description"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Single text storyboards document"
                },
                {
                  "t": " — one canvas text node named "
                },
                {
                  "c": true,
                  "t": "<title> text storyboards"
                },
                {
                  "t": " containing one section per shot (mirrors the half-narrated-drama storyboard structure). When the user flags a shot for heavy iteration, that section is extracted to a standalone text node and a "
                },
                {
                  "c": true,
                  "t": "(extracted)"
                },
                {
                  "t": " marker is left in the document. Pencil image storyboards, if opted in, are separate image nodes."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Single-Shot Video Clip nodes (rendered by the video model selected in Step 7 — H3 default, Seedance 2.0 fallback)"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Assembled Main Video node"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Matched BGM audio node and Final BGM-Composited Video node"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Do not dump long production content only in chat. Put durable outputs on canvas as text, image, video, or audio nodes."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 1: Project Brief"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Produce a concise project brief and write it to a canvas text node named with the project title or "
            },
            {
              "c": true,
              "t": "项目简报"
            },
            {
              "t": "."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Include:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Working title"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "One-line What-if"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Emotional premise"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Target audience feeling"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Main deliverables planned"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Approved screen size / aspect ratio"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Approved total duration"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Dialogue mode and language: only use a specific language when the user explicitly requested it; otherwise write "
                },
                {
                  "c": true,
                  "t": "language not specified"
                },
                {
                  "t": " and keep dialogue minimal or ask later when needed"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Initial risks"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Dialogue intent when present"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Then show a user choice card:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Continue with this direction (recommended)"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Regenerate premise options"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Revise emotional premise"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Refine dialogue direction"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Only proceed after the user chooses or explicitly says to continue."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 2: Story Outline and Gates"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Create a story outline and write it to a canvas text node named "
            },
            {
              "c": true,
              "t": "故事大纲"
            },
            {
              "t": " or "
            },
            {
              "c": true,
              "t": "story-outline"
            },
            {
              "t": "."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Include:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Protagonist Want / Need / flaw"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Core world rule"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "8-beat causal story spine"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Emotional anchor and payoff"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Dialogue beats if the user requested dialogue"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Red-line checks"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Gate checks:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Protagonist is active"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Crisis is intensified by protagonist flaw"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Coincidence never solves the problem"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Ending reuses an earlier emotional anchor"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Antagonistic pressure is not a flat villain"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Dialogue reveals relationship change instead of explaining the theme"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Then show a user choice card:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Approve story and continue (recommended)"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Revise beats"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Revise emotion curve"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Revise dialogue beats"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Return to premise"
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 3: Character Cards"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Generate character reference cards and place each image on canvas. Recommended order:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Protagonist card"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Contrast / pressure character card"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Optional supporting character card"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Each character card should be a 16:9 production reference sheet when possible. Unlike final rendered video, character cards should include clear readable labels so downstream generation can bind the correct person and props:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Character name label in English and/or the project language"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Role label, such as protagonist, grandma, thief, sidekick, pressure character"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Main 3/4 view"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Front / side / back views"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Expressions"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Material / costume / prop details"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Important prop labels, such as handbag, wallet, skateboard, apple basket, scarf, shoes, glasses"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Identity lock repeated in the prompt"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "A short visual-ID note listing age range, body type, hairstyle, outfit colors, signature props, and do-not-change traits"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For stylized 3D animation, keep the character soft, readable, and consistent across later images and videos."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "After the main character cards are generated, show a user choice card:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Lock character designs and continue (recommended)"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Regenerate protagonist card"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Adjust specific visual details"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Add another character card"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Warn the user that changing locked character designs later may require regenerating the shot table, single-shot storyboards, single-shot video clips, assembled main video, and final composite."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 4: Scene Cards"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Generate scene reference cards and place them on canvas after character cards. Scene cards must show environments only: do not include characters, people, crowd figures, silhouettes, hands, faces, or character cameos. Character action belongs in the shot table, single-shot multi-panel pencil storyboards, and single-shot video clips, not scene cards."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Include:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Main environment overview"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Key light states, such as day / night"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Emotional sub-spaces"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Continuity landmarks (fixed objects whose screen position must persist across shots in the same scene, e.g. kitchen island, sofa, door frame, tree, mailbox)"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Important props in the environment"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Then show a user choice card:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Lock scene design and continue (recommended)"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Regenerate scene card"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Add another scene angle"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Adjust lighting or layout"
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 5: Standardized Shot Table Video Prompts (Six Columns)"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "After character cards and scene cards are locked, output standardized video prompts as a shot information table. This step is mandatory and cannot be swapped with storyboard or video generation."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Required reference: read and follow "
            },
            {
              "c": true,
              "t": "references/shot-table-spec.md"
            },
            {
              "t": " for the exact six-column schema, per-second directive requirements, table-wide rules, user approval card, and mandatory Step 5.5 self-check gate."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Minimum runtime contract:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Create a canvas table node named "
                },
                {
                  "c": true,
                  "t": "标准镜头信息表"
                },
                {
                  "t": " or "
                },
                {
                  "c": true,
                  "t": "standard-shot-table"
                },
                {
                  "t": "."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use exactly six columns: "
                },
                {
                  "c": true,
                  "t": "Shot ID & Duration"
                },
                {
                  "t": ", "
                },
                {
                  "c": true,
                  "t": "Continuity Handoff"
                },
                {
                  "t": ", "
                },
                {
                  "c": true,
                  "t": "Reference Anchors (Spatial + Identity)"
                },
                {
                  "t": ", "
                },
                {
                  "c": true,
                  "t": "Hook Type"
                },
                {
                  "t": ", "
                },
                {
                  "c": true,
                  "t": "Shot Description (Per-Second Directives)"
                },
                {
                  "t": ", "
                },
                {
                  "c": true,
                  "t": "Audio & Dialogue Track"
                },
                {
                  "t": "."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Every row must include complete per-second directives, continuity handoff, reference anchors, hook type, and audio/dialogue timing."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Run the Step 5.5 self-check from "
                },
                {
                  "c": true,
                  "t": "references/shot-table-spec.md"
                },
                {
                  "t": " before storyboarding. Do not enter Step 6 until the self-check passes."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Then show the table approval/self-check choice cards defined in "
            },
            {
              "c": true,
              "t": "references/shot-table-spec.md"
            },
            {
              "t": "."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 6: Text Storyboards Document (Default) + Pencil Image Storyboards (Opt-in)"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "After the Step 5.5 self-check passes, show a storyboard-mode choice card before producing any storyboard artifact."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Required reference: read and follow "
            },
            {
              "c": true,
              "t": "references/storyboard-guidelines.md"
            },
            {
              "t": " for the default single text storyboards document, optional multi-panel pencil storyboards, shot-level extraction/re-integration, storyboard approval cards, and visualization fallback rules."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Minimum runtime contract:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Default mode is one authoritative text storyboards document containing one section per shot."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Pencil storyboard images are opt-in visualization artifacts only; they never override the text storyboard."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Extract a shot into a standalone text node only when the user flags that shot for heavy iteration."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Step 7 must read the matching text storyboard section or extracted standalone node, not the pencil image."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "After all storyboards are approved, proceed to the video-model choice card."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 7: Video-Model Choice Card + Single-Shot Video Clips"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Before any clip is rendered, show the video-model choice card and resolution choice card."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Required references:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Read "
                },
                {
                  "c": true,
                  "t": "references/model-selection.md"
                },
                {
                  "t": " for the H3 default, Seedance 2.0 fallback, per-shot mixed mode, resolution choices, and model-specific prompt shaping."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Read "
                },
                {
                  "c": true,
                  "t": "references/fallback-policy.md"
                },
                {
                  "t": " for per-model retry ladders, drift handling, and escalation choices."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Minimum runtime contract:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "H3 is the recommended default model."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Seedance 2.0 is the fallback for high-stakes animation performance or repeated H3 failure."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Per-shot mixed mode is allowed only when the shot table marks the model per row; unmarked rows default to H3."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Strip all storyboard-only labels before video render."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Bind each clip to the approved text storyboard section, exact character cards, and exact scene card."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If a clip drifts from the approved "
                },
                {
                  "c": true,
                  "t": "Reference Anchors"
                },
                {
                  "t": ", follow "
                },
                {
                  "c": true,
                  "t": "references/fallback-policy.md"
                },
                {
                  "t": "; do not silently assemble incorrect clips."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "After all clips render, place them on canvas in shot order, group them as "
            },
            {
              "c": true,
              "t": "<title> shot clips"
            },
            {
              "t": ", and show the clip approval card defined in "
            },
            {
              "c": true,
              "t": "references/model-selection.md"
            },
            {
              "t": "."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 8: Full Film Assembly, BGM Match, and Final Output"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "After all single-shot clips are approved, assemble the complete main video, match or generate one continuous BGM track, and produce the final composited video."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Required reference: read "
            },
            {
              "c": true,
              "t": "references/qc-checklist.md"
            },
            {
              "t": " for assembly rules, BGM rules, final review checks, canvas ordering/grouping discipline, user choice-card discipline, and regeneration/latest-asset discipline."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Minimum runtime contract:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Preserve the exact shot order from the approved table."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use only approved latest assets."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Duck BGM under dialogue, reactions, and important SFX."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Do not add subtitles or text unless explicitly requested."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Final video must contain no storyboard traces, labels, arrows, timing marks, panel borders, or double-binding labels."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Then run the final review checks from "
            },
            {
              "c": true,
              "t": "references/qc-checklist.md"
            },
            {
              "t": " and deliver the final approved asset."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Boundaries"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Do not use this Skill for a single image, a simple edit, a single clip animation, logo design, or pure prompt consultation. If the user only wants a prompt, use a video prompt workflow instead. If the user only wants a character card, use a character breakdown workflow instead."
            }
          ]
        }
      ]
    },
    {
      "url": "https://github.com/MiniMax-AI/MiniMax-H3/blob/main/skills/brand-promo-video-generator/SKILL.md",
      "title": "brand-promo-video-generator",
      "anchor": "skill-brand-promo-video-generator",
      "blocks": [
        {
          "type": "quote",
          "inlines": [
            {
              "t": "For marketers and creators producing promotional content for brands, products, websites, apps, shops, or personal projects. Users provide logos, product images, interface screenshots, official links, or other verifiable assets and confirm duration, aspect ratio, audience, and campaign focus. The Skill organizes brand facts and asset provenance, selects a narrative direction, plans precise beats and shots, generates needed imagery, video, voiceover, or music, and completes assembly and pre-delivery review. It outputs a promotional short that highlights product capabilities, use cases, and a call to action. Best for launches, website showcases, and social promotion; not for imitating real brand marks without authorized assets, inventing product claims, or producing long-form narrative films."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Brand Promo Video Generator"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Create a polished short promo video for a brand, product, website, app, shop, or personal project. Use this Skill when the user has a logo, product images, screenshots, a website link, or just a clear idea and wants the agent to turn those materials into a clean brand reel."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "This Hub adaptation replaces third-party Vibe Motion / Remotion implementation details with Hub-native orchestration: source research, asset verification, story planning, image/video generation, optional speech or music, and editing assembly. Do not initialize external projects or depend on npm validators during normal execution."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Tool Coverage Rule"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "The "
            },
            {
              "c": true,
              "t": "allowed-tools"
            },
            {
              "t": " list must cover the full production promise in this Skill: source lookup, image preparation/generation, video clip generation, optional speech/music/audio generation, final editing/assembly, media inspection, and canvas grouping. If a runtime does not provide one of the listed generation or editing tools, downgrade the deliverable explicitly to a pre-production package instead of claiming that a final promo video can be generated."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 1: Intake assets and resolve the brief"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Before any story planning or generation, run a required user intake. Ask the user to upload or provide links to the elements that must be verified:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Logo files or official logo source pages"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Font files, font names, typography guidance, or official website pages that show brand typography"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Brand colors, color system, style guide, or pages that clearly show official colors"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Product images, UI screenshots, packaging, renders, footage, or other brand imagery"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Product information: official product name, feature list, launch focus, claims, CTA, disclaimers, and target audience"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Company/product official URL or official source package"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Treat user-uploaded assets as usable by default for pre-production and concept planning. Do not repeatedly ask a standalone rights/permission question during the first intake unless there is a concrete risk signal, such as a visible third-party watermark, obviously scraped marketplace imagery, contradictory user wording, legal/medical/financial compliance claims, or the user asks for commercial publication. Record the source as \"user-provided\" and surface rights caveats in the source summary instead of blocking the flow."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "In the same opening intake, ask the user to choose:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Target duration, normally 15-30 seconds; recommend 15 seconds when the user wants a fast launch film"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Aspect ratio; offer common choices such as 16:9, 9:16, 1:1, 4:3, 3:4, or match a supplied reference"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Also identify campaign focus, distribution channel, narration language, on-screen copy language, and visible copy needs when they are not already clear. Do not proceed to creative direction until the user has supplied the usable materials or explicitly confirms which elements are unavailable."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Language rule for promo content: choose narration and on-screen copy language from the brand materials, target audience, and platform context, not mechanically from the chat language. If the brand assets and visible source copy are primarily English or global corporate English, default narration and on-screen copy to English unless the user explicitly asks for Chinese localization. If the user is Chinese but says they are testing as a new user, keep chat replies in Chinese, but plan the actual video copy in the language that best fits the brand campaign."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "If a logo, product UI, person, mascot, packaging, font, color system, or other identity-bearing asset cannot be authenticated, stop and ask for an authorized original instead of generating a plausible substitute."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 2: Build the brand truth sheet"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Research or inspect the strongest available sources and summarize the brand truth sheet before creative production:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "User-provided original exports"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Official company website, static bundle, newsroom, brand portal, media kit, press kit, or official repository"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Company-controlled media library"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Licensed stock or authorized partner kit"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Extract:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Exact logo variants, clear space, and usage constraints"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Official fonts or visible typographic behavior"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Primary, secondary, and dynamic brand colors"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Brand tone, principles, visual motifs, and interaction language"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Current product names, features, scenarios, metrics, slogans, CTA, and disclaimers"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Official photography, renders, UI screenshots, footage, press assets, and media kit material"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Do not use logo aggregation sites, search thumbnails, fan recreations, Pinterest reposts, or AI-generated substitutes as identity-bearing sources. Procedural graphics are allowed only as non-representational motion layers: masks, gradients, color fields, grids, glows, particles, trails, typography, verified-data charts, and transition geometry."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 3: Create a provenance manifest"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Record every identity-bearing asset in a compact manifest that can be delivered to the user. The manifest may be a text node or table and should include:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Stable asset ID and role"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Local path or canvas node reference when available"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Exact source URL or user-provided source note"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Source type, such as official website, media kit, user-provided original, or licensed stock"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Verification target used for comparison"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Rights or publication note"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Authenticity status: verified, user-supplied, licensed, or blocked"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "The manifest does not grant publication rights by itself. If authorization is unclear, label the video as an unofficial concept and tell the user commercial publication requires permission."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 4: Choose the story spine"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Present 2-3 concise creative directions when the user has not already chosen one, recommend one, and continue after confirmation. Use the product category to pick a spine:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "AI / SaaS: user intent -> thinking or planning -> capabilities -> execution -> useful output -> proof -> logo"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Physical product: hero reveal -> interaction -> feature macro -> usage context -> result -> logo"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Service / company: context -> process -> evidence -> outcome -> promise -> logo"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Image-led brand: authentic imagery -> visual motif -> benefit -> emotional payoff -> logo"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Keep the story product-specific. Show actual features, interactions, scenarios, outputs, and proof instead of hiding the story behind abstract effects."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 5: Plan exact beats"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Plan a frame-aware timeline before generation. Use 30fps as the planning convention unless the output pipeline requires otherwise."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For a 15-second film, target 5-8 major beats. For a 30-second film, target 8-12 major beats. Each beat should define:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Start and end time or frame range"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Visual owner and authentic asset IDs"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Primary action"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Product or brand proof shown in the shot"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Copy and readable hold"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Color state"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Incoming and outgoing transition"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Motion intent: setup, anticipation, commitment, impact, brake, settle"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "A useful 15-second pattern is: brand hook, user intent or setup, product mechanism, capabilities or scenarios, output or proof, product payoff, final logo and CTA. Use 6-12 frame overlaps when outgoing motion naturally supplies the next shot."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 6: Direct the motion language"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Build intensity with control:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Let product motion, cursor paths, UI flow, light, scrolling content, object edges, or matched geometry drive transitions"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use 2-5 deliberate color states tied to meaning"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Keep one primary action per beat; delay secondary layers slightly"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Establish 2-3 high-energy peaks and quieter braking moments"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Preserve readable silhouettes, copy, and logo clear space"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Avoid fake HUDs, arbitrary glass cards, decorative text walls, unverified metrics, and identical easing everywhere"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For AI products, include at least one readable chain such as: prompt -> planning -> parallel capabilities -> generated result -> proof. For physical or service products, show cause and effect from user action to concrete outcome."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 7: Hard confirmation before generation"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Before generating any video, image sequence, speech, music, or final edit, stop and show the user the completed pre-production package:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Provenance manifest or source summary"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Brand truth sheet"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Chosen creative direction"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Exact beat / shot plan"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Visible copy, CTA, narration, and audio plan"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Known authenticity, rights, or placeholder caveats"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use a concise confirmation step before generation. If the user clearly expresses approval or intent to proceed after seeing the pre-production package — for example \"confirm\", \"generate\", \"go ahead\", \"continue\", \"next\", \"可以\", \"继续\", \"下一步\", or similar — treat it as permission to generate, unless the message also asks for changes. If the user asks to skip the process, still provide a compact source summary, brand truth sheet, and beat plan first, then proceed when they indicate approval. Offer revision choices only when the user's reply is ambiguous or requests changes."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 8: Produce Hub assets"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use Hub-native generation and editing only after the hard confirmation gate has passed. Keep each dispatch self-contained with the chosen model, aspect ratio, authentic reference paths, and original request."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Typical production flow:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Generate or prepare verified still frames, UI plates, product hero frames, or motion-ready story images."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Generate video clips from those frames or from precise text prompts, preserving the same ratio and brand assets."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Default audio policy for native brand reels: when the user asks for BGM, music, soundtrack, ambient sound, or says nothing beyond needing a finished promo video, prefer video-native audio from the selected video model instead of generating a separate music track. For the default MiniMax H3 route, set native audio on ("
                },
                {
                  "c": true,
                  "t": "generate_audio=true"
                },
                {
                  "t": ") and prompt for brand-safe instrumental music / UI sound design inside the video prompt."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Generate separate speech or music only when the user explicitly needs controllable narration, voiceover, dialogue, replaceable standalone BGM, exact music duration independent of the video, post-production remixing, or when the selected video model cannot generate suitable audio. Do not duplicate a soundtrack between video-native audio and separate audio generation."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Assemble clips, any explicitly separate audio, and final brand lockup in editing. Add subtitles only when the user explicitly asks for subtitles."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Do not redraw or approximate logos, wordmarks, product UI, packaging, mascot, person, or brand scene. Use generated material only for abstract motion, atmosphere, transition geometry, or clearly conceptual scenes that do not impersonate official product evidence."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 9: Verify before delivery"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Before final response, check:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The logo and identity-bearing assets came from verified or user-authorized sources"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Product names, feature wording, claims, metrics, slogans, and CTA match official sources or are clearly marked as concept copy"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The video duration, aspect ratio, and language match the brief"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Copy is readable and not overcrowded"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The final logo is not stretched, cropped, or rebuilt"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Motion has clear visual ownership and does not obscure the product"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The output is on the canvas and multi-asset outputs are grouped"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "If the output fails an authenticity check, replace the questionable asset with an official/user-authorized source or stop and ask for the asset. Never improve an imitation."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 10: Deliver"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Provide:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Final video path or canvas output"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Duration, aspect ratio, and language"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Short creative summary"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Provenance manifest or source summary"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Rights/disclaimer note when needed"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Specific suggestions for the next iteration, such as pacing, claim clarity, CTA, audio, or platform crop"
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Failure recovery"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Wrong or approximate logo: remove it, locate the current official file or ask for the user's original, then regenerate or re-edit."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Fake-looking product/UI: replace with official, user-supplied, or licensed media. Do not polish the imitation."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Beautiful but generic: add a complete product interaction, verified claim, or real output."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Fast but chaotic: reduce simultaneous actions, assign a visual owner, and preserve matched motion across cuts."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Smooth but slow: shorten holds, overlap transitions, and brake only around key messages."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Asset unavailable: ask for an authorized original; never guess."
                }
              ]
            }
          ]
        }
      ]
    },
    {
      "url": "https://github.com/MiniMax-AI/MiniMax-H3/blob/main/skills/co-op-game-intro-generator/SKILL.md",
      "title": "co-op-game-intro-generator",
      "anchor": "skill-co-op-game-intro-generator",
      "blocks": [
        {
          "type": "quote",
          "inlines": [
            {
              "t": "For users creating a two-player co-op game menu or opening animation. Users provide two player names, a game title, a target visual style, and optional character reference images. The Skill locks identity cues, generates an approval image from a fixed menu framework with coordinated color, buttons, icons, and typography, then uses the approved result to rebuild the character, UI-copy, and event timing instructions for the final video. It outputs a co-op game intro featuring two characters, player cards, and menu interaction motion. Best for game concepts, character-led menus, and social content; not for playable game development, complex multi-page UI, exact brand-logo replication, or generic character-free title sequences."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Co-op Game Intro Generator"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use this Skill when the user wants a co-op game intro video and wants to confirm the visual direction with one image before generating the final H3 video. The workflow collects style, player names, game title, and optional character refs, then creates a framework-preserving confirmation image before generating the H3 video."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Required References"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "These two templates are mandatory runtime inputs, not optional background notes:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use "
                },
                {
                  "c": true,
                  "t": "references/h3-confirmation-image-template.md"
                },
                {
                  "t": " when building the confirmation-image prompt in STEP 3 and generating the first confirmation image in STEP 4. Fill the template fields in order and do not skip framework, palette, UI, character, typography, layout, or negative-constraint fields."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use "
                },
                {
                  "c": true,
                  "t": "references/h3-video-prompt-template.md"
                },
                {
                  "t": " when refilling the final Minimax H3 video prompt in STEP 6. Fill the template from the approved confirmation image, player/game data, final UI copy, event timing, motion directions, and negative constraints."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "If either template is unavailable, stop and report that the Skill package is incomplete instead of improvising a different prompt structure."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 1: Ask for visual style"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Ask the user to choose a preset style or enter a custom style. This style has top priority and controls supplemental style language, palette language, background texture, character rendering, expression, outfit direction, UI colors, button/icon style, and typography texture."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 2: Collect player and game info"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Collect PLAYER 1 name, PLAYER 2 name, and game title. If the user provides character images, use PLAYER 1 and PLAYER 2 refs only for identity mapping: recognizable face silhouette, hairstyle, glasses, relative facial proportions, and distinctive traits. Do not inherit photographic realism, skin texture, real-world lighting, camera quality, or the original image style; redesign the face into the selected visual style while preserving identity anchors."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 3: Build the GPT confirmation-image prompt"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Load and follow "
            },
            {
              "c": true,
              "t": "references/h3-confirmation-image-template.md"
            },
            {
              "t": " as the required prompt skeleton. Use a fixed framework + dynamic style fill + palette-linked prompt structure:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Overall Style"
                },
                {
                  "t": ": always preserve game main menu UI, high-quality game promo poster, deep UI-character integration, modern commercial game UI design, strong visual impact, clean composition, and avoid over-decoration. Add other style terms from the selected style."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Color Palette"
                },
                {
                  "t": ": always follow: xx as main color, xx as UI body color, xx as text color, xx as functional accent color, red as danger accent, palette within five colors, high-contrast color blocking, fresh modern look, and xx-style color language. All later UI/button/icon/type colors must match this palette."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Composition"
                },
                {
                  "t": ": preserve 16:9 landscape, full-frame background, x centered characters, UI around rather than blocking them, upper-left player card, right-side vertical menu, bottom caution tape, a few corner graffiti accents, Z reading path, enough negative space, clear hierarchy, and Continue as the visual focus."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Background"
                },
                {
                  "t": ": follow pure xx background, slight xx texture, large solid-color blank space, texture only as detail, avoid heavy dirt/dense scratches/too much ink splash/large paint splatter, a little black spray-paint edge detail, clean modern premium UI-first background. Derive xx and additions from the selected style."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Character Style"
                },
                {
                  "t": ": strictly expand according to the selected style. Use source text only as dimension guidance, not fixed style."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Character A"
                },
                {
                  "t": ": facial features from character image 1; expression, rendering, and outfit follow selected style; optional compatible outfit dimensions include khaki short jacket, black inner layer, black cargo pants, brown boots, adventurer outfit. Fixed action: cross-legged, hands on floor, slight backward lean, looking up."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Character B"
                },
                {
                  "t": ": facial features from character image 2; expression, rendering, and outfit follow selected style; optional compatible outfit dimensions include green thick jacket, burgundy padded lining, white inner shirt, black pants, thick boots. Fixed action: cross-legged, hands in front of legs, slight forward lean, looking at camera."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Lighting"
                },
                {
                  "t": ": preserve top main light, upper-left warm/cool fill, soft bottom ambient reflection, soft shadows, contact shadows, rim light, high-quality GI, and natural character-background integration. Choose warm/cool from style."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Game UI"
                },
                {
                  "t": ": preserve console game menu, unified button size, rounded rectangles, slight tilt, minimal spray/drip elements, modern clean sticker design, readability, and no over-decoration. Button body, outline, and glow colors must match the palette."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Layout Rules"
                },
                {
                  "t": ": preserve horizontal long buttons, unified width/height/radius, width adapted to text, single-line titles only, no wrapping, no two-line titles, centered text, consistent margins and spacing."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Buttons"
                },
                {
                  "t": ": adapt colors from palette and icons from selected style. Continue is the large visual-center highlighted button with hover/click state. Start New Game is above Continue. Settings remains visually consistent. Exit Game uses danger/exit cue with red accents allowed."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Player Cards"
                },
                {
                  "t": ": preserve upper-left x-player info cards, irregular rectangular card, outline, slight edge damage, left logo/icon, right three-level info (PLAYER label, nickname, READY), bold sans-serif, industrial sticker design. Card colors, outline, READY color, and logo style follow palette and selected style."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Icon System"
                },
                {
                  "t": ": derive icon style from selected style, colors from palette, and keep one-row-only, no wrapping, no stacking, at most one row per UI block, minimal quantity, unified size, never stealing focus."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Typography"
                },
                {
                  "t": ": preserve bold sans-serif, all caps, Anton/Impact/Burbank/Tungsten-like weight, tight tracking, heavy strokes, clear hierarchy, single-line typography, no wrapping, button width adapts to text, never two-line menu titles. Colors and texture follow palette and selected style."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 4: Generate the first confirmation image"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Generate only one confirmation image from the filled "
            },
            {
              "c": true,
              "t": "references/h3-confirmation-image-template.md"
            },
            {
              "t": ". Preserve the framework structure, while making the selected style visibly dominant."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 5: Wait for approval"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Do not generate video until the user approves the image. If the user changes style, names, game title, identity, or image direction, return to the image prompt step."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 6: Refill video prompt and generate with Minimax H3"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "After approval, load "
            },
            {
              "c": true,
              "t": "references/h3-video-prompt-template.md"
            },
            {
              "t": " and refill the final video prompt with confirmed style, character refs, player names, game title, UI text, event timing, motion directions, and negative constraints. Generate the final video with Minimax H3."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 7: Repair common failures"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "If text is unreadable, reduce on-screen text. If identities swap, strengthen names, positions, and colors. If faces drift, reuse uploaded refs and explicitly preserve identity anchors, hairstyle, and outfit anchors while keeping the face rendered in the selected visual style. If the selected style is weak, rewrite Overall Style, Color Palette, Character Style, Background, Game UI, Buttons, Icons, and Typography instead of changing layout framework."
            }
          ]
        }
      ]
    },
    {
      "url": "https://github.com/MiniMax-AI/MiniMax-H3/blob/main/skills/handdrawn-live-video-generator/SKILL.md",
      "title": "handdrawn-live-video-generator",
      "anchor": "skill-handdrawn-live-video-generator",
      "blocks": [
        {
          "type": "quote",
          "inlines": [
            {
              "t": "For creators making surreal short videos that blend rough glowing hand-drawn animation with live-action spaces. Users provide a scene idea, contact object or hand, desired mood, and optional language or style constraints. The Skill clarifies the physical contact, designs continuous morphing, escape route, and delayed handheld chase movement, then writes a reusable 15-second 16:9 video prompt in the user's language. After user confirmation it recommends MiniMax H3 generation and checks contact realism, camera delay, rough glowing stroke texture, and non-horror tone. Best for single-scene creative clips, not polished CG, horror jump scares, plush characters, or multi-scene cuts."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Handdrawn Live-Action Fusion Video Generator"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use this Skill when the user wants a "
            },
            {
              "b": true,
              "t": "finished 15-second, 16:9 live-action-and-hand-drawn fusion video"
            },
            {
              "t": ". The output must preserve the structure: a flat hand-drawn luminous animation appears in a real space, clearly contacts live-action hands or objects in the first 0-3 seconds, continuously morphs as one single entity, escapes, and a handheld phone camera follows slightly late."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "This Skill "
            },
            {
              "b": true,
              "t": "organizes the prompt in the user input language and recommends MiniMax H3 as the confirmed generation step"
            },
            {
              "t": ". Do not generate video until the user explicitly confirms H3 generation. Do not route to planner or executor for prompt-writing. The final prompt language must follow the dominant language of the user input: Chinese input produces Chinese, English input produces English, Japanese input produces Japanese; for mixed input, use the dominant language; when unclear, use the current conversation language. Only user-required proper nouns, model names, or literal parameters may remain unchanged."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Step 1: Understand the user intent as same-language constraints"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "When the user provides any language, understand it as the following workflow requirements and express the final prompt in the dominant language of the user input:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "基于参考 prompt 创作一个全新的 15 秒视频生成 prompt，不要表面模仿原句。"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "必须保留影像结构：实拍空间中出现平面的手绘发光动画；动画与真实手或真实物体接触；同一个存在连续变形并逃跑；相机总是慢半拍追赶。"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "手绘动画质感必须像蜡笔、粉笔、彩色铅笔、粉彩、粗糙笔刷；线条轻微抖动，有涂抹不均、毛边和逐帧重画感。"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "禁止 3DCG、毛绒玩具感、均匀矢量线、平滑霓虹、恐怖怪物、巨大眼睛、裂口、牙齿、威吓、扑咬、突然黑屏、跳吓。"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "0-3 秒必须出现实拍手与手绘动画的清晰接触，例如缠住手指、落在掌心、被抓时逃跑、从指尖诞生。"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "动画必须作为同一个实体连续变形，可在“线条、生物、记号、植物、交通工具、生活小物”等形态之间变化，并保留前一形态的痕迹。"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "不允许突然出现另一个全新角色。"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "全片在同一空间或相邻范围内连续展开，不用剪辑跳到另一个地点，像拍摄者真的边走边追。"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "每个区间 0-3、3-6、6-10、10-13、13-15 秒都要有新的变形、移动、接触、发现、恶作剧或惊喜。"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "拍摄者也必须参与：伸手、抓、追、打开门或盒子、接住、后退、被恶作剧等。"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "调性是可爱、生活感、怀旧、温柔、略带切感，不是恐怖喜剧。"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "13-15 秒必须有空间级变形：之前的线扩散到墙、地板、天花板、窗户、水槽或通道，变成巨大花、星空、夕阳、云、丝带、涂鸦小镇等；结尾要有感动余韵和一点可爱笑点。"
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Step 2: Invent all creative content fresh"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For every run, create a new combination. Do not reuse the reference prompt's dark room, PC, fridge, stars, hearts, blue vortex, butterfly, snake, octopus, hamburger, giant eye, teeth, or dark ending."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Choose new values for all of these:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "实拍空间，但仍是生活化且可连续追踪的相邻范围；"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "手绘实体或初始形态；"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "中心色彩；"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "连续变形链路；"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "与真实手或实物的接触方式；"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "在空间中的追逐路线；"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "拍摄者反应；"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "最后的空间级变形与可爱笑点。"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Good example directions include: 雨天厨房水槽、旧阳台晾衣角、清晨玄关、小书店走廊、火车窗边小桌、浴室镜柜、手作桌、温室通道、自助洗衣店长椅、旧餐桌. Use only one or adjacent connected areas."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Step 3: Required output format"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "The final prompt must begin with a sentence pattern matching the dominant language of the user input. For Chinese input, use this pattern:"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "c": true,
              "t": "15秒，16:9横版视频。将实拍的〇〇与手绘发光动画融合的影像。"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Replace “〇〇” with the newly invented live-action space or everyday scene. For non-Chinese input, use an equivalent opening in the same language and include duration, 16:9 landscape format, live-action space, and hand-drawn glowing animation fusion."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Do not add titles, auxiliary headings such as 舞台设置 or 色味, or explanatory notes. Keep this paragraph order:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "开头句；"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "实拍空间与手机拍摄质感；"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "0-3 秒；"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "3-6 秒；"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "6-10 秒；"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "10-13 秒；"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "13-15 秒；"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "手绘质感；"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "相机追随方式；"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "禁止事项；"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "环境音。"
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Step 4: Prompt writing rules"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Keep the prompt executable as a video-generation prompt, not an essay."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Unless the user asks for explanation, the final answer should contain the prompt text in the dominant language of the user input first, followed by one short next-step recommendation in the same language."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The recommendation must invite the user, in the same language, to use MiniMax H3 to generate a 15-second 16:9 video from this prompt. Chinese example: "
                },
                {
                  "c": true,
                  "t": "下一步建议：如果你确认这个 prompt，我可以继续用 H3 模型生成 15 秒 16:9 视频。"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Do not generate a video, image, audio, storyboard, or intermediate asset until the user explicitly confirms the H3 generation step."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Mention Seedance only as a target usage context when the user asks; do not add model parameters inside the creative prompt unless requested."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The first 0-3 seconds must make real/hand-drawn fusion obvious through contact."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The camera must not neatly center the animation. It should lag behind, pan/tilt/advance after the entity already leaves the frame edge."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The entity should remain traceable: each new form preserves a line, tail, color smear, body curve, or motif from the previous form."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use soft, emotional, comic, cute beats: tiny stumbles, shy gestures, a dot falling behind, a petal sticking to lens, a star dropping into a palm, confetti sneeze, one small creature lagging behind."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Avoid any horror-coded anatomy or threatening motion."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The final prompt must not randomly mix in vocabulary, transition sentences, or writing systems from outside the user input language; when the user input language is Japanese, natural Japanese is allowed."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Step 5: Delivery"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Output the final prompt in the dominant language of the user input first. After the prompt, add exactly one short same-language recommendation line inviting the user to continue with MiniMax H3 video generation. Do not include a title, checklist, model call summary, filename, or canvas delivery note. If the user later confirms H3 generation, generate the 15-second 16:9 video with MiniMax H3 and check that the result preserves contact, continuous morphing, delayed camera chase, and non-horror hand-drawn texture."
            }
          ]
        }
      ]
    },
    {
      "url": "https://github.com/MiniMax-AI/MiniMax-H3/blob/main/skills/minimalist-product-ad-generator/SKILL.md",
      "title": "minimalist-product-ad-generator",
      "anchor": "skill-minimalist-product-ad-generator",
      "blocks": [
        {
          "type": "quote",
          "inlines": [
            {
              "t": "Turn product images and ad requirements into minimalist product ad shorts for e-commerce promotion and product launches. The Skill confirms format and product variants, extracts selling points, writes concise English ad copy, builds product anchors, plans beat-synced typography/storyboards, and generates a clean product film with premium camera language. Not for KOC talking-head ads, general editing, or complex screen demos."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Minimalist Product Ad Generator"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use this Skill to guide non-professional users through a flow-style workflow that creates a minimalist product advertising video for e-commerce promotion and product launches. The target users are e-commerce sellers, small brand owners, indie creators, and individual sellers; the user should provide at least one product image or related asset."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "The core principle is: "
            },
            {
              "b": true,
              "t": "confirm assets and brief first, build product facts and a product narrative spine, lock product visuals with independent anchor photos, control video with a precise beat storyboard, then finish the film with native audio or music-based editing."
            },
            {
              "t": " This Skill no longer defaults to a 4-panel anchor sheet, because video models may reproduce the panel layout. By default, it uses three separate anchor photos plus one precise beat text storyboard as the video control system."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Start Gate"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Every time this Skill is triggered, run a complete but lightweight start gate before any analysis, copywriting, anchor generation, or video generation. Confirm only the information required for production. Do not ask about music here; music is handled later in the music step."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "The start gate must confirm all of the following in one pass:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Product images and related materials"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Ask the user to upload product images and related materials, such as product photos, packaging images, renders, detail shots, existing video assets, or visual references."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "If the current message or current canvas / session already contains materials, state that materials have been detected. Do not ask the user to upload again; only confirm whether to use the current materials."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "If there are multiple candidate materials and their roles are unclear, ask which one should be the main product image."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Product variant status"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Confirm whether this is a single variant or multiple variants / colors / models."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "If there are multiple variants, confirm which one is the main variant."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "If the user does not specify, the agent may recommend one based on the product image, but the later storyboard must still write the concrete color or variant name."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Target duration"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "5s / 10s / 15s, with 10s as the recommended default."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Aspect ratio"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "16:9 / 9:16 / 1:1 / 4:3 / 3:4 / match reference image."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Once selected, the anchor sheet, video, and final delivery must strictly keep this ratio."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Apple-style template"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "White-tech / dark rim light / brand color field / light lifestyle scene."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "In-frame copy"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "User-provided copy, or agent-generated Apple-style English copy."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Video model strategy"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Default model is MiniMax-H3, because it often produces cleaner Apple-like product close-ups, negative space, and premium product-film camera language."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Do not ask the user to choose a video model during the start gate. Show “default model: MiniMax-H3” as part of the adopted start-gate result."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "If the user explicitly asks for another model, follow the user's model choice after capability checking."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Seedance is only a backup when the user explicitly wants stronger multi-shot execution, asks for Seedance, or accepts a fallback after H3 fails or cannot satisfy the requested structure."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Start gate is mandatory. If the user has already uploaded product material, only skip the upload request; do "
            },
            {
              "b": true,
              "t": "not"
            },
            {
              "t": " skip the rest of the start gate. The agent must still confirm product variant status, target duration, aspect ratio, Apple-style template, and in-frame copy mode in one pass before analysis, anchor generation, storyboard, or video generation. The video model is not a start-gate question: use MiniMax-H3 by default and display it in the completed start-gate result. If the user says “you decide / just do it,” the agent may choose recommended defaults for the remaining fields, but must still display the adopted choices as the completed start-gate result before continuing."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Operating Principles"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Independent anchor photos are the default visual control system"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Generate three separate anchor photos by default, not one 4-panel sheet, because video models may copy panel layouts into the final film."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "The three anchor photos usually cover: hero / striking main view, material or functional detail, and final copy composition."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Do not create a separate structure-action anchor when it overlaps with the hero view. Merge structure / action cues into the material-detail anchor unless the product truly needs a distinct mechanism reference."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Each anchor photo must be a complete standalone product photo. Do not create grid layouts, split screens, collage boards, framed panels, product walls, or storyboard sheets."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "The precise beat storyboard determines the actual shot order, action, and text behavior. Do not use anchor photos as direct shot replacements."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "In-frame copy must appear as integrated video motion, not a subtitle fallback"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Text in the copy anchor photo is only a reference for font, position, single-line layout, and two-part color treatment. It does not mean the whole video can use only that one copy line."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "The precise beat storyboard may define multiple short English copy lines across shots. Each line must be 3-5 English words, single-line, readable, and follow the two-part color rule: in white-tech style the first half uses black or dark gray, in dark rim-light style the first half may use white, and the second half always uses the specific product color. Do not use isolated 1-2 word feature labels."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Video generation must include the storyboard copy inside the frame."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "The copy does not need to appear in every shot. If the video model tends to make typography mistakes, reduce copy frequency proactively. For a 10-second film, usually keep only one mid-film copy moment plus one final copy moment; do not put text in every shot. The final shot must include one stable single-line copy."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "By default, ask the video model to generate in-frame typography and its timing directly. Do not silently degrade text into post-production subtitles or reserve empty space for later overlay. Use post-production fallback only when the user explicitly asks for it or when integrated video typography fails and the user accepts a fallback."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Product body color is a hard fidelity constraint"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Apple-style means clean composition, premium light, restrained motion, and negative space; it does "
                },
                {
                  "b": true,
                  "t": "not"
                },
                {
                  "t": " mean turning the product itself white, silver, or AirPods-like."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "The product's original body color, accent color, material tint, and visible finish from the user's image must be preserved in all anchor photos and videos."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Only the background, lighting environment, and composition may shift toward the selected Apple-style template. Never recolor the product body unless the user explicitly asks."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "The final copy emphasis color must come from the real product main color, not from a generic silver / white Apple palette."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Every product needs a product-specific narrative"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Do not reuse a fixed earbud template or write vague phrases like “product state changes.”"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "The storyboard must be based on product category, form, material, structure, and visible actions."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Product motion must be visual and concrete, such as “the lid opens 30 degrees and inner reflection appears,” or “the crown rotates while a highlight slides along the edge.”"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Progress must be visible"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "After each step, show what was produced and what decision is needed next."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Do not auto-run the entire pipeline without user confirmation."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Typography Rules"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "In-frame advertising copy must be English."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the user provides Chinese copy, translate it into concise English or ask for approval of the English version."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Visible in-frame copy must be 3-5 English words, preferably no more than 32 English characters including spaces. Do not write isolated 1-2 word feature labels."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Copy should feel like an Apple product film: sensory, benefit-led, material-led, or a light value proposition; avoid promotional slogans and ecommerce feature-tag wording."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Font reference: SF Pro Display / SF Pro Text. Prefer "
                },
                {
                  "c": true,
                  "t": "SF Pro Display Semibold"
                },
                {
                  "t": " in prompts."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use no more than two text colors in a shot."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "In white-tech style, the first half of the text must use black or dark gray; white text is forbidden on white backgrounds. In dark rim-light style, the first half may use white. The second half always uses the specific product color."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Text must stay on one line. Do not wrap, stack, or split into multiple lines."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "At any moment, only one single-line English copy line may appear in the frame. Do not show two rows of text, two-line titles, title + subtitle pairs, or multiple text blocks at the same time. Two-part typography must continue or replace within the same line, never split into upper and lower rows."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Do not place text in a lower subtitle position. Prefer the vertically centered visual zone, left-aligned or right-aligned as part of the composition. Text should be slightly larger and feel like a product-film visual element, not an explanatory subtitle."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Approved mid-film pattern: clean negative space, product motion or product close-up leads the frame, the frame stays uncrowded, and only one single-line English copy appears. Text may sit near the product edge, product surface, or close-up highlight area so it feels integrated into the product image rather than floating like a subtitle. Do not damage negative space or add a second text block just to add copy."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Default two-part text motion must remain visible: the first half fades in or slides in subtly first, then the second half fades in or slides in subtly later. When the second half appears, the first half shifts gently within the same line to make room."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The shift should be subtle, around 10-15px or 8-12% of text width. Motion should be smooth and restrained; avoid bouncy, neon, or flashy UI effects."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Do not make typography completely static just to avoid two-row text. The correct solution is same-line two-part entrance, subtle shift, fade-in, or gentle slide-in; the wrong solution is upper/lower line splitting, two-line titles, or removing text motion."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 1: Asset Check and Product Fact Summary"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "If no product material is available, ask the user to upload it. If material is already available, use it and analyze:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Product category."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Subject position and frame occupancy."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Image quality: sharpness, lighting, composition, and visible details."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Product main color and possible main variant."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Showable structure: opening, rotating, lifting, snapping, folding, popping, glowing, screen, texture, etc."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Real appearance features usable for the storyboard: material, edge, button, port, packaging, transparent part, screen, or distinctive silhouette."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "If the image quality is not usable, stop and give concrete reshoot advice."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Output a short product fact summary:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Material used."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Product category."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Main color candidates and main variant suggestion."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Quality pass / fail."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Showable structure / feature."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 2: Confirm the Production Brief"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Turn the start gate answers into an executable production brief. Do not ask again for parameters that have already been confirmed. The brief drives the narrative spine, copy, anchor sheet, and storyboard."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "The production brief must include:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Product material used."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Main variant / product main color."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Aspect ratio."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Target duration."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Selected Apple-style template."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Single-variant / multi-variant strategy."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "In-frame copy mode: user-provided copy, or agent-generated Apple-style English copy."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Multi-variant product rules:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The user selects a style; do not automatically remove all other variants."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Every multi-variant project must decide one main variant first."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Other variants should not all appear at the very beginning; they appear only in process beats, transitions, or the final full set."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the user does not specify a main variant, the agent may choose the most visually stable one and use the others for rhythm and layering."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Avoid ecommerce matrices, nine-grid displays, stacking, scattered layouts, all colors laid flat, or full-screen product walls."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 3: Choose a Product Narrative Spine"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Before copywriting and anchor generation, choose a lightweight product narrative spine. Do not use a broad corporate brand-film structure; this Skill focuses on short Apple-style films for physical products."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "If the user has not selected a direction, offer 2-3 concise directions, recommend one, and continue after confirmation. If the user says “you decide,” use the recommended one."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Recommended spines:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Product Launch"
                },
                {
                  "t": " (default recommendation)"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Negative-space opening → main variant establishes hero view → material / structure detail → natural product action → variants or color relation → full-copy closing."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Good for earbuds, watches, digital accessories, small appliances, fragrance devices, etc."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Feature Touch"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Product stillness → interaction trigger → feature action → detail magnification → result / feeling → closing frame."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Good for products with clear opening, rotation, magnetic snap, light change, screen, folding, mist, or similar actions."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Color Family"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Main variant appears alone → supporting variants slide in lightly → color order forms → material and structure stay unified → full set closes → copy lands."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Good for multi-color, multi-variant, or multi-model products."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Output one sentence describing the selected narrative spine, for example:"
            }
          ]
        },
        {
          "type": "quote",
          "inlines": [
            {
              "t": "This film uses the Color Family spine: the purple main variant establishes the hero view, other colors enter as supporting layers, and the full product set closes with the English copy."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 4: Direct the Motion Language"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Before copywriting and anchor generation, define the motion language of the film. This step does not generate assets; it defines motion intensity, transition logic, and rhythm peaks for the later storyboard."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Rules:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Transitions are driven by real product or visual elements"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Prefer product edges, material highlights, opening / rotation / snapping / sliding actions, geometric changes in variant arrangement, color entry and exit, matched camera direction, or matched product silhouette."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Do not use meaningless white flashes, abstract particles, random light effects, or random cuts to fake premium motion."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "One main action per beat"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Secondary elements should appear with slight delay and should not compete for attention at the same time."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Examples: product enters first, then text appears; main variant stabilizes first, then supporting variants slide in; material highlight sweeps first, then text motion begins."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Set strong and quiet moments"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "5s film: 1 small peak + 1 stable closing."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "10s film: 1-2 peaks + 1-2 braking moments."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "15s film: 2-3 peaks + 2 quiet braking moments."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Peaks may be product action completion, variant entrance, second-half copy reveal, or full-product closing."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Braking moments may be material-detail pause, readable copy hold, or final frame hold."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Keep safe space clear"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Product silhouette remains clear, single-line copy stays readable, and the main variant is not blocked."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Add a logo only when the user provides one. Do not generate a fake logo."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Avoid fake tech decoration, mirrored white stages, and empty openings"
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Avoid fake technology interfaces, meaningless glass cards, decorative text walls, unconfirmed metrics, random particles and stacked light effects, one identical easing style across the whole film, and full-screen product walls."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "White-tech style is not a mirrored white stage and not dead flat white lighting. Do not place the product on reflective floors, glass tables, or cheap studio mirror surfaces."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "Apple-style white space should be a simple white background; impact comes from striking product angles, real product actions, camera rhythm, and negative-space composition, not from mirror reflections or waiting on empty frames."
                }
              ]
            },
            {
              "depth": 1,
              "inlines": [
                {
                  "t": "The opening must not be empty dead time. It should quickly reveal an attractive product action or angle, such as the product rotating smoothly out of its own structure, emerging from an opening mechanism, sliding along its silhouette, or being revealed by an edge highlight. The exact action must be inferred from the current product form, not hardcoded to earbuds."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Output one short “motion language” statement, for example:"
            }
          ]
        },
        {
          "type": "quote",
          "inlines": [
            {
              "t": "This film uses product-edge highlights and the purple main variant sliding motion to drive transitions. The main peaks are variant entrance and full-copy landing, with a stable final hold for the product and copy."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 5: Generate or Confirm Apple-style English Copy"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Before generating the text anchor and storyboard, obtain a final English copy line for the frame."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Rules:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Analyze product category, usage feeling, and narrative spine."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Generate 2-3 Apple-style English options, each 3-5 words."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Do not use fixed templates or fixed slogans; infer new copy for every product."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Avoid promotional language."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the user already has copy, prioritize it. Chinese copy must be localized into concise English."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "After the user confirms the copy, proceed to anchor generation. If the user says “you decide,” choose the recommended copy and continue."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 6: Generate Three Independent Product Anchor Photos"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Generate "
            },
            {
              "b": true,
              "t": "three independent anchor photos"
            },
            {
              "t": " in the same aspect ratio and resolution as the user-selected video setting. They must be three separate image outputs, not one combined 3-panel or 4-panel sheet. Background follows the selected style, and all three photos must share unified light, shadow, grade, and background language while remaining standalone product photos."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Anchor photo roles:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Photo 1: Hero / striking main-view anchor, locking the most attractive product view, silhouette, and opening visual direction. Avoid ugly extreme material close-ups as the opening reference."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Photo 2: Material / functional detail anchor, locking surface material, grain, reflection, tactile quality, and the most important visible mechanism or structure. If the product needs opening, docking, folding, clasping, button, port, lid, screen, or touch cues, merge those cues into this photo."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Photo 3: Final copy anchor, locking final product composition, font feeling, text position, single-line layout, and two-part color treatment. The copy is a format reference and does not limit the later video to only this one line."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Multi-variant handling:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The anchor photos must inherit the selected narrative spine and style strategy."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Photos 1/2 prioritize building the visual system around the main variant."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Other variants only support rhythm; do not lay everything flat or fill the frame."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Photo 3 may show the main variant plus a few supporting variants, or a full-set closing composition, but must preserve negative space and order."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Final copy anchor typography rules:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Must include the Step 5 confirmed copy; do not use placeholder copy."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Text must stay on one line."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Font: SF Pro Display Semibold."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Text color must be split explicitly into two parts: the first half of the copy uses black or white, and the second half uses the specific product main color. If the main color is purple, write “first half black / white, second half purple.” Do not write only “product color + black or white.”"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Photo 3 may contain only this format-reference copy line and no other text; however, later video copy is controlled by the precise beat storyboard and may include multiple short English copy lines."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Show the three independent anchor photos and ask the user to approve, edit, or regenerate a specific photo before proceeding to the precise beat storyboard."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 7: Precise Beat and Text Storyboard Table"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Before generating any video clip, create and read back a precise beat text storyboard table. It is not artwork; it is the execution table for the video model."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "The storyboard table must be organized as “User Choice Statement → Beat Content → Principles.”"
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "User Choice Statement"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Write the confirmed style, aspect ratio, duration, narrative spine, main variant, product main color, variant strategy, and copy. Example:"
            }
          ]
        },
        {
          "type": "quote",
          "inlines": [
            {
              "t": "White-tech style, 16:9, 10 seconds, Color Family spine, purple as the main variant, other colors as supporting layers, copy: Color Meets Sound."
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "Beat Content Table"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Recommended columns:"
            }
          ]
        },
        {
          "type": "table",
          "header": [
            [
              {
                "t": "Time range"
              }
            ],
            [
              {
                "t": "Shot"
              }
            ],
            [
              {
                "t": "Shot purpose"
              }
            ],
            [
              {
                "t": "Visual lead"
              }
            ],
            [
              {
                "t": "Visual / camera move"
              }
            ],
            [
              {
                "t": "Variant state"
              }
            ],
            [
              {
                "t": "Copy"
              }
            ],
            [
              {
                "t": "Text color"
              }
            ],
            [
              {
                "t": "Text effect"
              }
            ],
            [
              {
                "t": "Transition / continuity"
              }
            ],
            [
              {
                "t": "Rhythm intent"
              }
            ]
          ],
          "rows": []
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Table rules:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "5s suggests 3-4 beats."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "10s suggests 5-7 beats."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "15s suggests 6-9 beats."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use seconds as time ranges; do not require frame numbers."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Keep one main action per beat; secondary layers appear with slight delay."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Clearly define when the main variant appears alone, when supporting variants enter, and when the full set closes."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Copy splitting may only be described in plain language as first half / second half. Do not write arrows, slashes, plus signs, or separators, because the model may render them as in-frame copy."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Text color must use the specific product color name and must be split by style: in white-tech style write “first half black or dark gray, second half the specific product color”; only in dark rim-light style may the first half be white. For example, in white-tech style with purple as the main color, write “first half black or dark gray, second half purple.” Do not write “product color + black or white.”"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If typography is error-prone, reduce text beats first: for a 10-second film, usually use only one mid-film copy moment and one final copy moment, with all other beats marked as no text. Do not put text in every shot."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The final beat must be a stable single full-frame product closing + full single-line copy. Never end on four panels, split screens, storyboard boards, anchor-sheet layout, product windows, or framed grids. Text still belongs in the vertically centered composition zone, left-aligned or right-aligned as part of the frame, not in a lower subtitle position. Add a logo only when the user provides one."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Rhythm intent vocabulary: setup, establish, prepare, impact, brake, settle."
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "Principles"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Keep core text on a single line."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "At any moment, only one single-line English copy line may appear; forbid two text rows, upper/lower line splits, title + subtitle pairs, or multiple text blocks at the same time."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use exactly two text colors: black or white + confirmed specific product color."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The text must appear inside the video; do not rely only on post-production fallback."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Shot continuity = element continuity + motion continuity + form continuity."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Smoothness = easing + no awkward timing + seamless entrances and exits."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Total pacing follows the user-selected duration."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Text motion must be visible: the first half fades in or slides in subtly first, then the second half fades in or slides in subtly later. When the second half appears, the first half shifts subtly within the same line to make room. Do not make the text completely static, and do not split it into upper and lower rows."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the style is confirmed, the table must strictly follow that style."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "After the user confirms the storyboard table, proceed to video generation."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 8: Video Generation"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Generate video directly from the confirmed three independent anchor photos + precise beat text storyboard table. Video style, background, lighting, mood, and pacing follow the selected style. Aspect ratio and size must strictly follow the user-selected setting; if the user chose 16:9, generate 16:9 and do not auto-change to another ratio."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Video reference rules:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "During video generation, do not pass the original product image to the video model."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The original product image is used only for product analysis and anchor generation."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use the three independent anchor photos to preserve product consistency, hero view, material / functional detail, final composition, and typography layout."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Creative control comes from the precise beat storyboard: shot order, product action, copy, text motion, continuity, and transitions."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Anchor photos are only product anchors used to protect identity, body color, material, and layout. Never treat them as the storyboard itself, and never turn the three photos into three sequential video segments."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The video output must be one continuous full-frame ad film. Do not show four panels, split screens, collage layouts, frames, storyboard boards, grid layouts, or any shot that reproduces an anchor-sheet layout inside the video. This is especially critical for the ending: never return to a grid, storyboard board, small-window montage, or product wall."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Default to one H3 full-frame product film, not multiple first-frame clips, unless the user explicitly asks for a different construction."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Video generation defaults to MiniMax-H3 native audio unless the user explicitly asks for another model or silence. Use the later Apple-style tech BGM direction as the audio prompt so picture rhythm and sound are generated together."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "The video prompt must include:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The three independent anchor photos and the role of each photo."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The full precise beat storyboard table; read every beat and rewrite every beat into the video prompt. Do not summarize only early beats or omit later typography, variants, or closing requirements."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The exact copy lines. The video prompt must spell out every in-frame copy line verbatim, its time window, first-half / second-half entry timing, colors, and single-line behavior. Do not rely on the storyboard table alone, and do not summarize this as “text beat sync” or “leave space for copy.”"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Prompt completeness check: if the final video-generation prompt does not literally contain every intended English copy line, the task is not ready to dispatch. Rewrite the prompt before video generation."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Single-line typography hard constraint: at any moment, only one single-line English copy line may appear in the frame; forbid two rows, two-line titles, title + subtitle pairs, or multiple text blocks at the same time. If typography is error-prone, reduce copy frequency instead of putting text in every shot."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Two-part text motion rules: the first half and second half must continue or replace within the same line, never split into upper and lower rows; motion must be visible, with the first half fading in or sliding in subtly first, then the second half fading in or sliding in subtly later, while the first half shifts gently within the same line. Do not make the typography completely static."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Shot continuity hard constraints."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "MiniMax-H3 native audio setting and music prompt; native audio is on by default unless the user explicitly asks for silence or another model."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Do not pass the original product image."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 9: music-2.6 Tech BGM"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Video generation defaults to MiniMax-H3 native audio first, and the Apple-style tech BGM direction below should be written into the video prompt. If H3's native music is unpleasant, too loud, too weak, out of sync, or the user asks for new music, use "
            },
            {
              "c": true,
              "t": "music-2.6"
            },
            {
              "t": " to generate a longer standalone instrumental BGM and replace the video audio track. Do not default to ElevenLabs; use ElevenLabs only when the user explicitly requires a strict target duration, and follow the fee-confirmation rule."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Default music direction:"
            }
          ]
        },
        {
          "type": "code",
          "text": "Around 100 BPM, fast tech feeling, block chords, pluck and airy noise bed, kick + sub-bass + sine sweep, wooden percussion, sudden cut-off, within 0.5s everything stops, leaving only the pluck tail to decay."
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Extended interpretation:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Techy, Apple-style, product launch feeling."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Rhythmic drive is allowed, but it must not become cheap EDM."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Pluck should be crisp, pleasant, and forward; airy noise should feel premium."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Kick and sub-bass serve edit points; avoid boomy bass."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Wooden percussion adds tactile texture, not a complex drum loop."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "No vocals, no synthwave, no retro, no gaming, no cheap corporate stock music."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 10: Music Analysis, Beat-synced Editing, and Delivery Verification"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Before final delivery, edit or assemble based on music analysis. Do not simply lay music under the video."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Music analysis:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Detect rhythm, strong beats, energy sections, and clear single-note hits."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Find an 8-12 second segment with continuous sound and suitable energy for product display."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Do not blindly use the first 10 seconds."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Prefer a segment with a clear entry point, no silence or collapse in the second half, and enough stable time for the closing frame."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Audio assembly rules:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Keep the video image, cut a continuous music segment, and replace the video audio track."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Mute the original video track; keep only the new music."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Keep music loudness restrained: do not maximize loudness, do not use aggressive limiting, and do not raise music too much; but also do not push it so low that the pluck, rhythm points, and product display lose clarity."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Do not use long fade-outs. Only apply a 0.1-0.3s tail fade when needed."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "After assembly, check for long silence or audible dropouts."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Pre-delivery verification:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Video aspect ratio, duration, and language match the brief."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Product appearance, main variant, and variant timing match the anchor sheet and storyboard."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Copy is readable, single-line, not crowded, and contains no extra arrows or symbols; no two text rows, upper/lower line splits, title + subtitle pairs, or multiple text blocks appear at the same time."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The final frame has a stable product + copy closing."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Music is not too loud and not too low."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Output is on canvas, and multi-asset outputs are grouped."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Delivery includes:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Final video path or canvas output."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Duration, aspect ratio, and language."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Short creative summary."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Copy used and music segment used."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Whether beat-synced editing was applied."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Specific next improvements, such as pacing, copy, main variant, audio, or platform crop."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Failure Handling"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Product image too weak: stop, give reshoot guidance, and wait for a better image."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Copy too long: compress to 3-5 English words and ask for approval."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Text anchor is wrong: regenerate the text anchor before video generation."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Anchor sheet fails product fidelity: regenerate with stronger product-preservation instructions."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Storyboard is templated: return to the precise beat table and rewrite based on product form and narrative spine."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Copy does not appear in video: rerun the video prompt, explicitly requiring copy in at least the middle and final beats."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Video typography deforms: regenerate the text anchor or degrade the text shot to subtle anchor-based motion."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Aspect ratio is wrong: immediately rerun with the user-selected ratio."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Music quality is poor: retry with "
                },
                {
                  "c": true,
                  "t": "music-2.6"
                },
                {
                  "t": ", do not force duration, and cut the best segment from the longer track."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Final assembly has no sound in the second half: re-analyze music, select a continuous audible segment, and use direct audio replacement."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Trigger Examples"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use this Skill for requests like:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "“帮我的产品做一个苹果味儿广告片”"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "“用这张产品图做 Apple 风电商广告”"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "“做一个极简高级的产品发布视频”"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "“Make an Apple-style product ad from this product photo”"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "“Create a premium minimalist ecommerce product film”"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Do not use this Skill for general video editing, documentary explainers, KOC talking-head ads, or complex UI/screen-text demos unless the user explicitly wants the Apple-style product ad workflow."
            }
          ]
        }
      ]
    },
    {
      "url": "https://github.com/MiniMax-AI/MiniMax-H3/blob/main/skills/music-video-subtitle-generator/SKILL.md",
      "title": "music-video-subtitle-generator",
      "anchor": "skill-music-video-subtitle-generator",
      "blocks": [
        {
          "type": "quote",
          "inlines": [
            {
              "t": "For musicians, video creators, and social-media editors producing AI music videos or emotional short films with lyric typography. Users provide music, lyrics, references, characters, typography direction, mood, or target platform. The Skill analyzes beat and vocal timing, separates character, scene, and text references, designs beat-reactive spatial typography, decomposes long works into connected shots, audits prompts, and routes generation for H3 or other video tools. It outputs MV concepts, shot prompts, lyric text plans, and stitching guidance. Best for stylized MVs and subtitle-driven music visuals, not ordinary caption cleanup, licensed IP copying, or fully manual post-production editing."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Music Aesthetics MV"
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Purpose"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use this Skill when the user wants to create, revise, audit, or generate music-video prompts or emotional short-film prompts where music, lyrics, typography, references, rhythm, performance, and camera language must be designed together. The workflow adapts MV prompt rules into Hub execution: key creative decisions are confirmed, locked prompts are written to canvas text nodes, and media creation is delegated to Hub agents."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Do not use it for ordinary subtitle burn-in, generic video editing, non-music product ads, or simple single-image / single-clip requests without MV structure."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Hub compatibility rules"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Do not assume third-party tools, shell scripts, browser plugins, or external generation APIs."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Write locked prompts and revisions to Hub canvas text nodes."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Delegate character cards, scene cards, typography cards, video clips, BGM, and final assembly to Hub image, video, music, and editing agents."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Do not hardcode output paths; always use Hub-returned paths."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the user says “skip confirmation / just do it”, apply it only to the current run unless the outer orchestrator has active session authorization."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the user only wants a prompt, stop after delivery. If the user wants a finished MV, continue to generation and assembly after confirmation."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Core principles"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Understand the work before choosing a structure. Templates organize, but are not mandatory forms."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use the latest confirmed creative intent."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Omit irrelevant fields instead of filling placeholders."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Do not mechanically add performance, typography, transitions, camera moves, or character actions just because a preset includes them."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "On-screen text is a designed visual layer, not ordinary subtitles, unless the user explicitly requests subtitles."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the user uploads a real song or beat, it is the master music bed unless they request replacement."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Natural multi-shot stitching for >15s videos"
                },
                {
                  "t": ": when duration exceeds the model single-generation limit, use “multi-shot storyboard breakdown + tail/head frame continuation + beat hard cuts + global master-audio alignment”. Every segment must preserve the same groove, tempo feel, aspect ratio, character logic, visual preset, lighting language, and typography motion rules."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the user wants a finished music-aesthetic MV without lyrics, generate and lock original lyrics first. The final MV must reference character, typography packaging, and scene cards together. The typography packaging card controls only text packaging style, font texture, graphic design, layout ratio, and motion language."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 1: Pre-flight lock"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Before writing the final production prompt, confirm the minimum foundation with concise recommended choices."
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "1.1 Video format"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Offer fixed options:"
            }
          ]
        },
        {
          "type": "table",
          "header": [
            [
              {
                "t": "Use case"
              }
            ],
            [
              {
                "t": "Aspect ratio"
              }
            ],
            [
              {
                "t": "Resolution"
              }
            ]
          ],
          "rows": [
            [
              [
                {
                  "t": "TikTok / Reels / Shorts vertical"
                }
              ],
              [
                {
                  "t": "9:16"
                }
              ],
              [
                {
                  "t": "1080×1920"
                }
              ]
            ],
            [
              [
                {
                  "t": "YouTube / Bilibili horizontal"
                }
              ],
              [
                {
                  "t": "16:9"
                }
              ],
              [
                {
                  "t": "1920×1080"
                }
              ]
            ],
            [
              [
                {
                  "t": "Feed square"
                }
              ],
              [
                {
                  "t": "1:1"
                }
              ],
              [
                {
                  "t": "1080×1080"
                }
              ]
            ],
            [
              [
                {
                  "t": "Dense vertical ad test"
                }
              ],
              [
                {
                  "t": "9:16"
                }
              ],
              [
                {
                  "t": "720×1280"
                }
              ]
            ],
            [
              [
                {
                  "t": "Cinematic widescreen MV"
                }
              ],
              [
                {
                  "t": "21:9"
                }
              ],
              [
                {
                  "t": "2560×1080"
                }
              ]
            ]
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "The selected ratio must be reused across character cards, scene cards, typography references, shot prompts, video clips, and final assembly."
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "1.2 Target duration and multi-shot structure"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Before prompt writing or video generation, confirm target MV duration. Never silently use the model default as user intent."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Offer a compact duration card:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "10-second test"
                },
                {
                  "t": ": one or two shots to verify character, scene, typography, and audio style."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "15-second hook"
                },
                {
                  "t": ": 2–4 short shots for a more complete chorus / hook / performance phrase."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "30-second or longer complete MV (multi-shot stitching)"
                },
                {
                  "t": ": because many models have a 15-second single-generation ceiling, automatically use a Multi-Shot stitching workflow. First generate or lock one continuous song / BGM, split 30 seconds into 4–8 dynamic 2–5 second shots, then stitch via beat sync and head/tail frame continuity."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Custom duration"
                },
                {
                  "t": ": user provides duration; plan shot count and stitching based on the selected model’s single-clip limit."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "If uploaded music exists, the confirmed duration is the music window length."
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "1.3 Music window"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "If uploaded or specified music is longer than the confirmed duration, lock a segment before writing prompts:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Recommended window: assistant identifies the strongest chorus / hook / emotional turn and requests confirmation."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "User timestamps: user provides start and end seconds; verify both are inside the audio."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Multi-variant: only for ad-hook testing or multiple creative directions."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "If music is shorter than the target duration, use the full audio unless the user explicitly asks to stretch or extend it."
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "1.3.0 Lyrics lock and lyrics-first fallback"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Before final video prompts or generation, determine lyric ownership:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the user provides lyrics, those are locked lyrics. Do not generate, add, rewrite, expand, translate, paraphrase, or replace them unless explicitly requested."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the user wants a finished music-aesthetic MV without lyrics, generate short original lyrics matching the music style, vocal mode, duration, emotion, and visual preset, then lock them."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Locked lyrics are the only source text for rap/singing performance and visible typography."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Split locked lyrics into each shot’s "
                },
                {
                  "c": true,
                  "t": "Rap line:"
                },
                {
                  "t": ", "
                },
                {
                  "c": true,
                  "t": "Vocal line:"
                },
                {
                  "t": ", "
                },
                {
                  "c": true,
                  "t": "Soft vocal line:"
                },
                {
                  "t": ", or "
                },
                {
                  "c": true,
                  "t": "Spoken line:"
                },
                {
                  "t": "."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Every "
                },
                {
                  "c": true,
                  "t": "Typography:"
                },
                {
                  "t": " field must come from the same locked lyrics. During vocal performance, visible text must word-for-word match the performed phrase."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "In the final typography MV, the performer must rap or sing the locked lyrics with visible lip shapes, jaw motion, breath, facial accents, nods, and hand accents following phrasing and rhythm."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "1.3.1 Default multi-shot stitching for >15s videos"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For >15s MVs such as 30 seconds, the global multi-shot prompt script is the authoritative source:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Lock complete Master Audio"
                },
                {
                  "t": ": lock one continuous song / BGM track with the full vocal and groove as the only audio baseline."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Build a Shotlist Timeline"
                },
                {
                  "t": ": split 30 seconds into 4–8 short shots of 2–5 seconds, mapped precisely to lyric timestamps and beats such as snare, 808, and drop."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Head/tail frame and scene continuity"
                },
                {
                  "t": ": if Shot B continues the same scene, use Shot A’s tail frame as Shot B’s head frame. If it is a hard cut, preserve the same character card, wardrobe, lighting prompt, and use same-direction camera motion or match-cut visual elements."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Generation and edit assembly"
                },
                {
                  "t": ": the video agent generates each shot from the Shotlist. The editing agent aligns all clips to the global Master Audio beat grid, trimming, speed-ramping, and stitching for natural lip-sync, beat sync, and transitions."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 2: Creative Contract"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Before final prompts, create a concise creative contract:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Music genre, instrumentation, tempo/BPM feel, vocal mode, and emotional temperature."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Lyric source and locked lyrics."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Target duration and multi-shot breakdown, e.g. 30s split into 6 short shots."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Reference image roles: character card, scene card, typography packaging card."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Camera language, shot sizes, focus, beat-cut density, and transition logic."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Exclusions such as no fades, no glossy AI beauty face, no single-shot overstretching that causes deformation."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 3: Reference roles and scene sampling"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Assign each reference image one narrow job:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Typography reference card"
                },
                {
                  "t": ": controls only text packaging style, font texture, graphic design, layout ratio, and motion language. It must not contribute people or scenes."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Character reference card"
                },
                {
                  "t": ": controls character identity, facial aura, hairstyle, clothing silhouette, proportions, posture, and presence."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Scene reference card"
                },
                {
                  "t": ": controls scene style, spatial atmosphere, image texture, background depth, and lighting mood."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "3.1 Close-up scene switching and multi-shot sampling"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For Trap, Dark-pop, Cyber-grunge, and other fast-paced MVs, switch quickly among multiple close-up spaces:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Keep scene mood unified, but each shot’s space must differ clearly, such as local background, tunnel, wall, light strip, or reflective floor."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Scene switches must be triggered by musical impacts: bass hit, 808 drop, snare, vocal accent, or typography smash."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Shot switches are “visual samples” on the trap beat: hard cuts, jump cuts, scan-glitch cuts, flash cuts, or action match cuts."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 4: Preset grammar, Dark-pop / Cyber-grunge and Trap example"
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "Visual and editing language"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Realistic high-fashion texture and film-magazine texture, referencing late-90s / early-00s indie magazines, photocopy paper, film scans, and zine collage."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Heavy grain, slight film jitter, halftone dots, rough print edges, scan offsets."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Editing must use hard cuts only"
                },
                {
                  "t": ". No fades, dissolves, or soft transitions."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Image and typography strongly respond to beat cues: hi-hat roll creates micro-shake / frame skips, snare triggers scale-up / hard cut / shoulder drop, 808 bass hit creates low-frequency compression / stretch / offset."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "Typography packaging rules"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Typography is a dynamic graphic subject in space, not a subtitle bar. It may sit in foreground, midground, background, or be occluded by shoulders / hands."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Text must never cover eyes or main facial expression; avoid the mouth during critical lip-sync."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "With vocals, visible words must exactly match the performed lyrics. Each shot has only one main typography event."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 5: Prompt structure template"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "A multi-shot script must be modular by shot, with accurate duration and audio mapping:"
            }
          ]
        },
        {
          "type": "code",
          "text": "[Global Aesthetic & Character Lock]: (global character and aesthetic anchor prompt)\n\nShot 1 (0.0s - 3.5s)\nVocal Line: \"...\"\nTypography: \"...\"\nVisual & Action: ...\nCamera & Motion: ...\nTransition Out: hard cut to Shot 2 on bass hit / same-direction whip pan\n\nShot 2 (3.5s - 7.0s)\nVocal Line: \"...\"\nTypography: \"...\"\nVisual & Action: ...\nCamera & Motion: ...\nTransition Out: ..."
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 6: BGM continuity and natural multi-shot stitching system"
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "6.1 Global audio continuity"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "The entire MV must bind to one Master Audio track. During segmented video generation, do not use independent disconnected clip audio. All video clips are aligned to their corresponding timestamps on the Master Audio timeline during edit assembly."
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "6.2 Natural Stitching Protocol"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For >15s stitching, enforce five continuity locks:"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "b": true,
              "t": "Vocal & Lip Continuity"
            },
            {
              "t": ": Cut points must land on lyric pauses, breaths, snare, or drop. Do not hard cut inside an active vowel or lyric unless the next shot is an extreme close-up with continuous mouth shape."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "b": true,
              "t": "Rhythm & Beat Matching"
            },
            {
              "t": ": Cut points must hit the 1/4 or 1/8 beat grid. Use speed ramping to align head nods, hand gestures, and blinks to beats."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "b": true,
              "t": "Aesthetic & Color Grading"
            },
            {
              "t": ": Every cross-shot generation carries the same aesthetic header prompt: grain level, LUT direction, and light direction. Final assembly uses unified 35mm film grain and LUT to hide batch color differences."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "b": true,
              "t": "Transition & Motion Continuity"
            },
            {
              "t": ": For long-shot continuation, use the previous tail frame as the next head frame and prompt continuation of action. For hard scene switches, use kinetic continuity such as same-direction pan or hand-occlusion match cut."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "b": true,
              "t": "Typography Motion Stitching"
            },
            {
              "t": ": Text in the previous shot should shatter, sweep out, or smash-screen on a bass hit; next-shot text smashes in or unfolds on the accent, transferring visual momentum."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 7: Checklist"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Silently verify before delivery:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If target duration exceeds 15s, has Multi-Shot breakdown been used automatically?"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Is one global Master Audio locked, and are cut points beat-aligned?"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Do cuts avoid mid-lyric vocal breaks, with natural lip and breath continuity?"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Do adjacent shots have clear stitching logic such as tail/head continuation, same-direction motion, match cut, or beat hard cut?"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Is the edit style strictly hard-cut, with no fades or soft transitions?"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Are character / scene / typography cards isolated without cross-contamination?"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Is typography a spatial layer that never blocks eyes or main facial expression?"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Are image quality, grain, color, and lighting consistent globally?"
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 8: Canvas delivery"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "After the complete MV prompt script is locked, write it to a dedicated canvas text node named "
            },
            {
              "c": true,
              "t": "Complete MV Prompt"
            },
            {
              "t": " or "
            },
            {
              "c": true,
              "t": "完整MV Prompt"
            },
            {
              "t": ". The node must contain the full multi-shot prompt script and stitching notes. Later revisions update the same node."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 9: Final MV generation and assembly workflow"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Prompt lock and canvas write"
                },
                {
                  "t": ": confirm the full multi-shot prompt script with timestamps, lyric mapping, and transition logic is written to canvas."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Parallel shot generation"
                },
                {
                  "t": ": the video agent generates each 2–5s shot from the Shotlist. For continuation shots, extract the prior shot’s tail frame as the next I2V head frame."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Multi-track editing and stitching"
                },
                {
                  "t": ": the editing agent imports the global Master Audio, aligns all shot videos by timestamp, trims and speed-ramps on the beat grid, and checks seams with same-direction motion or flash-cut masking."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Finishing"
                },
                {
                  "t": ": apply unified Movie LUT and 35mm film grain overlay to reduce AI plasticity and lock visual consistency."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Delivery"
                },
                {
                  "t": ": output the seamless complete MV video file."
                }
              ]
            }
          ]
        }
      ]
    },
    {
      "url": "https://github.com/MiniMax-AI/MiniMax-H3/blob/main/skills/paper-collage-explainer-generator/SKILL.md",
      "title": "paper-collage-explainer-generator",
      "anchor": "skill-paper-collage-explainer-generator",
      "blocks": [
        {
          "type": "quote",
          "inlines": [
            {
              "t": "For creators, educators, and social-video editors who need a tactile paper-collage language for narration, knowledge points, opinions, or abstract topics. Users provide source copy, story beats, or a core concept and may specify aspect ratio, duration, palette, and audio needs. The Skill extracts meaning, proposes visual metaphors, prepares a production plan and storyboard, generates approved halftone collage stills, then creates stop-motion clips with paper movement and tactile sound effects, with optional final assembly. By default it keeps collage SFX and does not add BGM, voiceover, or subtitles unless requested. Best for explainers, viewpoints, story visuals, and social B-roll; not for presenter ads, editable layers, complex typography, or prompt-only tasks."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Paper Collage Explainer Generator"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Turn a short narration line, story topic, viewpoint sentence, or abstract idea into a cohesive editorial paper-collage animation sequence. The visual language is premium halftone paper collage: flat bold color fields, black-and-white photographic cut-outs, selective colored cardstock accents, warm cream keylines, soft paper shadows, tactile stop-motion assembly, and crisp collage sound effects."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "This Hub-adapted Skill uses Hub-native image, video, audio, and optional postprocess capabilities. It prioritizes style continuity, color harmony, controlled paper texture, stop-motion collage rhythm, and an audio policy that keeps tactile collage SFX by default while explicitly not adding BGM, voiceover, or subtitles unless the user requests them."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "When to Use"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use this Skill when the user wants:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "A short script line turned into a visual-metaphor collage animation"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "A simple story or literary topic explained through collage B-roll"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Editorial paper-collage animation for narration or social video"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Halftone collage animation with objects assembling from an empty color field"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "A batch of short abstract sentences or story beats converted into separate visual-metaphor animation clips"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "A tactile knowledge explainer that may include paper clicks, pops, slides, presses, and rustles but not automatic music or voiceover"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Do not use this Skill when the user needs:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "A realistic product ad or presenter-led video"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Precise editable layers, timeline keyframes, or transparent cut-out assets"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Exact logo placement or readable typography"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Only a written video prompt without generation"
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Default Creative Targets"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Unless the user specifies otherwise:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Output ratio: 16:9 landscape"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Clip length: about 4 seconds per segment"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Audio default: keep or generate tactile paper-collage sound effects only, such as paper slide, pop, press, light rustle, and soft tap sounds"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Default: do not add BGM. You may ask whether the user wants BGM when it may help, but add music only after explicit user confirmation"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Default: do not add voiceover, spoken narration, or presenter narration. You may ask whether the user wants narration/口播 when the project may benefit, but write, synthesize, or add spoken audio only after explicit user confirmation"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Default: do not add subtitles. You may ask whether the user wants subtitles, but create or burn in subtitles only after explicit user confirmation"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Visual style: premium editorial halftone paper collage"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Motion style: tactile stop-motion assembly, not slow zoom, generic drifting, or smooth digital layer movement"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Default video generation model: "
                },
                {
                  "c": true,
                  "t": "MiniMax-H3"
                },
                {
                  "t": ", unless the user explicitly specifies another model, the model is unavailable, or a hard capability requirement excludes it"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Text in image/video: avoid readable letters, numerals, UI, subtitles, watermark, and logos"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Image quality and depth: prioritize visually attractive, layered 16:9 compositions with clear foreground, midground, and background depth, strong subject hierarchy, rich but readable scene design, and controlled negative space"
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Audio Policy"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "This Skill's default delivery is "
            },
            {
              "b": true,
              "t": "with collage SFX, and without BGM, voiceover, or subtitles"
            },
            {
              "t": "."
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "During the first production-plan confirmation, state the default media approach explicitly: tactile paper-collage sound effects are kept or generated; BGM, voiceover/口播, and subtitles are not added by default."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "It is acceptable to ask the user whether they want "
                },
                {
                  "b": true,
                  "t": "voiceover narration/口播"
                },
                {
                  "t": ", "
                },
                {
                  "b": true,
                  "t": "BGM"
                },
                {
                  "t": ", or "
                },
                {
                  "b": true,
                  "t": "subtitles"
                },
                {
                  "t": ", especially for explainers, but present all three as optional add-ons, not defaults."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Do not infer that an explainer automatically needs spoken narration. If the user does not choose narration, create visual story beats rather than a voiceover script."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Do not infer that a social video automatically needs BGM or subtitles. If the user does not choose them, keep the clip SFX only."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "When generating video clips, request synchronized tactile collage SFX if the selected video model supports audio: paper pieces sliding, popping, pressing flat, soft taps, and light paper rustles."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "During final assembly, preserve the original clip audio tracks when they contain collage SFX. Do not drop audio by default."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Remove or replace audio only when the user asked for silence, when the generated audio contains unwanted speech/music, or when the user requests a separate music/narration mix. Create subtitles only when the user explicitly asks for them."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Global Style Rules"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Apply these rules to every still and video in the project:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Unify the overall visual style."
                },
                {
                  "t": " Every segment should feel like part of the same editorial paper-collage series: halftone cut-outs, flat color fields, warm cream keylines, soft physical shadows, clean composition, tactile paper material, and coordinated collage SFX."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Control the paper texture intensity."
                },
                {
                  "t": " Paper must not look perfectly flat, but it also must not become over-aged, dirty, wrinkled, or brown unless the user explicitly asks. Prefer clean, refined hand-made texture: subtle fiber, slightly irregular torn edges, light deckled fibers, layered seams, and soft shadows."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Unify the color tone."
                },
                {
                  "t": " Do not introduce kraft-paper, brown, yellowed, or distressed base papers when they clash with the approved still or the batch palette. Start each clip from a paper field that matches the approved final still's main color direction."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Make motion read as stop-motion collage."
                },
                {
                  "t": " Use clear paper-piece actions: appear piece by piece, slide or pop into position, lightly bounce, press flat, pause, then lock into the final composition. Avoid fast spinning, excessive flipping, chaotic object flight, global fades, smooth digital panning, zooming, or generic drifting."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Keep segments coordinated."
                },
                {
                  "t": " Once one or two clips establish the approved batch style and SFX cadence, later clips and revisions should reference that cadence and tone so the whole sequence feels coherent."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Default to polished 16:9 layered scenes."
                },
                {
                  "t": " Unless the user explicitly requests another platform frame, plan and generate in 16:9 landscape. Use the wider canvas to build attractive foreground / midground / background separation, richer environment props, clear subject hierarchy, and cinematic lateral composition without turning the frame into clutter."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "b": true,
                  "t": "Emphasize paper-collage craft."
                },
                {
                  "t": " Every still and clip should make the paper-collage method visible: separable paper groups, halftone photographic cut-outs, colored cardstock accents, tactile shadows, torn edges, layered seams, and stop-motion actions such as pop-in, slide-in, light bounce, press-flat, pause, and lock."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 1: Parse the Input"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For each line, concept, story, or topic, extract:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Core meaning: what the viewer should understand"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Emotion: calm, urgent, ironic, surprising, absurd, clarifying, reflective, mysterious, or playful"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Action verb: open, connect, leak, archive, compress, split, illuminate, bind, assemble, reveal, fall, chase, transform, collide"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Visual metaphor: a concrete image that expresses the idea without writing the script on screen"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Key objects: three to six large readable paper groups"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Audio implication: whether the beat benefits from paper slide, pop, press, tap, rustle, or snap SFX"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For a story topic, split the story into three to six concise beats unless the user specifies a count. Similar beats may share the same design language, but each should have a distinct metaphor, object set, color field, and SFX rhythm."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 2: Gate 1 — Production Plan Document Approval"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Before generating any media, create a concise production plan document and stop for user approval. Do not generate stills or videos before the user confirms this document."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "The production plan must include:"
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "Brief"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Topic or source line"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Intended audience / use context when known"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Aspect ratio and duration assumptions"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Tone and pacing"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Visual style summary"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Media approach, stated as: default collage SFX are kept or generated; BGM, voiceover/口播, and subtitles are not added unless the user explicitly requests them"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Optional add-on question when useful: ask whether the user wants voiceover narration/口播, BGM, or subtitles, but keep them optional"
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "Visual Metaphors"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For each planned segment:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Core meaning"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Emotion"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "One-sentence visual proposition"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Three to six key objects"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Suggested background color and accent colors"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Expected assembly order"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Expected collage SFX moments, such as slide, pop, press, tap, rustle, or snap"
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "Script / Visual Beat Track"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "If the user explicitly requests narration, write a concise voiceover script. If the user has not explicitly requested narration, do "
            },
            {
              "b": true,
              "t": "not"
            },
            {
              "t": " write a voiceover script; instead write a silent visual beat track explaining what the audience understands from the sequence."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "If the user only needs B-roll for an existing line, preserve the original line as context instead of inventing narration."
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "Storyboard"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For each segment, include:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Segment title"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Final-frame description"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Motion idea"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Approximate duration"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Collage SFX idea"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Notes on style continuity and color harmony"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "After presenting the production plan document, wait for the user to approve, reject, or revise. If the user approves only some numbered items, move only those items forward and revise the rest."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 3: Build Still-Frame Specifications"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "After the production plan is approved, write a compact visual specification for each approved segment. The specification should be self-contained and suitable for image generation."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Include:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Script meaning or story beat"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Visual metaphor"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Aspect ratio"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Background color field"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Accent colors"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Key object groups and their roles"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Composition, foreground / midground / background depth, and negative space"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Final frame relationship"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Style continuity notes"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Avoid list for this specific still"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use this style signature:"
            }
          ]
        },
        {
          "type": "code",
          "text": "flat bold color field, black-and-white halftone photographic cut-outs, selective colored cardstock accents, warm cream keylines, soft paper shadows, fine uncoated-paper grain, premium editorial paper collage, clean refined hand-torn paper edges, subtle fibrous edges, layered paper seams"
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Color guidance:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Burnt orange or red: labor, time pressure, urgency"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Mustard yellow: tools, warning, accumulated errors"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Ink green: cognition, reset, judgment, surreal calm"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Deep purple: memory, structure, mystery, dream logic"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Teal: collaboration, execution, system flow"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Rose red: absurdity, ceremony, theatrical tension"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Do not make cobalt blue the automatic default. Keep the batch visually unified through paper texture, halftone treatment, keylines, shadows, framing, and a controlled palette. Vary the color field only when the story beat benefits from contrast."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 4: Gate 2 — Generate and Approve Still Frames"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Generate one final still frame per approved segment. The still must look like the completed last frame of the future animation."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Still-frame requirements:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use the user-specified aspect ratio; otherwise default to 16:9 landscape"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Flat bold paper background with subtle fiber texture"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Three to six large separable object groups, unless the approved storyboard requires slightly more"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Clear central subject, strong visual hierarchy, generous clean negative space, and visible foreground / midground / background layering"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Black-and-white halftone photographic cut-outs as the main structure, combined with rich but readable scene props that support the story beat"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Selective colored cardstock accents only where they clarify hierarchy"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Warm cream keylines, soft physical paper shadows, refined torn edges, and subtle layered paper seams"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "No readable text, fake letters, numerals, subtitles, UI, watermark, or logos unless explicitly requested"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Show the generated still frames to the user and stop for approval before video generation. If a still looks too busy, has mismatched color, too many paper layers, too-flat digital edges, or too much aged/brown paper texture, revise the still before video generation."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 5: Plan the Stop-Motion Assembly"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For each approved still frame, prepare a motion plan that treats the approved still as the completed final frame."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Default motion order:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Start from a clean paper color field matching the approved still's main background, not a mismatched kraft-paper or brown base."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Base structure appears as paper pieces that slide, pop, or press into place."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Character, card, object, or main metaphor element enters."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Secondary objects assemble one by one with small bounce, press-flat, and pause beats."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Final relationship locks into the approved composition."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Hold the completed still-like frame briefly at the end."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Motion prompt guidance:"
            }
          ]
        },
        {
          "type": "code",
          "text": "Paper-collage stop-motion assembly. Start on a clean paper field matching the approved still's background color and tone. Assemble the scene piece by piece with tactile stop-motion timing: foreground, midground, and background paper groups appear in a readable order; each paper object appears, slides or pops in, lightly bounces, presses flat, pauses, and locks into place. Preserve the halftone dots, cream keylines, subtle fibrous torn edges, layered paper seams, soft shadows, paper grain, color field, and approved aspect ratio. End by holding the completed composition matching the approved still frame. Sound design: tactile collage SFX only, synchronized to paper-piece motion: soft paper slide, pop-in, press-flat tap, light rustle, and tiny paper snap where appropriate. Default: do not add BGM, voiceover, dialogue, or subtitles unless the user explicitly requested them. No mismatched kraft-paper opening, no brown/yellowed base unless approved, no fast spinning, no chaotic object flight, no smooth digital layer movement, no scene cuts, no camera move, no zoom, no morphing, no new objects, no text, no logos, no watermark, no UI."
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 6: Generate Collage-SFX B-roll Clips"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "After Gate 2 approval, generate one video clip per approved still frame."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Generation requirements:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use the approved still as the visual reference / final-frame anchor whenever the selected Hub video model supports it"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use the same ratio as the still frame"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Target about four seconds unless the user requested a different length"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Generate or preserve tactile collage SFX by default when supported: paper slide, pop, press-flat tap, light rustle, tiny snap"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Default: do not generate or add BGM unless the user explicitly requested music"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Default: do not generate or add voiceover, spoken narration, or presenter audio unless the user explicitly requested narration/口播"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If a generated clip contains useful collage SFX, preserve it during post-production and final assembly"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If a generated clip contains unwanted speech, music, fake UI sound, or noisy ambience, remove or regenerate the audio according to the user goal"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Keep the shot visually stable; do not add camera movement unless the user asks"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Preserve the collage material language, final composition, and established batch style"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "When revising later clips, use the best approved previous clips as style/cadence references if helpful"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use "
            },
            {
              "c": true,
              "t": "MiniMax-H3"
            },
            {
              "t": " as the default video generation model for this Skill. Do not ask the user to choose a model unless "
            },
            {
              "c": true,
              "t": "MiniMax-H3"
            },
            {
              "t": " fails, is unavailable, or cannot satisfy a hard capability requirement. If the user explicitly specified another model, keep that model as primary and adapt parameters only when needed."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 7: Quality Review"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Review stills and clips against these standards:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The metaphor or story beat is understandable without writing it on screen"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The still has a strong clean color field, attractive 16:9 composition by default, clear object hierarchy, and visible foreground / midground / background depth"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The number of object groups stays readable, not a screen full of fragments"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The clip begins from a color field matching the approved still or batch palette"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The assembly is visible piece by piece, not a global fade-in"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Motion reads as stop-motion collage: separate paper groups pop in or slide in, lightly bounce, press flat, pause, and lock"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Defaults: tactile collage SFX are desirable; BGM, voiceover/口播, and subtitles are absent unless explicitly requested"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Paper texture is controlled: not too flat, not over-aged, not brown/kraft unless approved"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Color tone is consistent across the batch"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The final frame remains close to the approved still"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "There are no unwanted readable letters, fake UI, subtitles, watermark, or logos"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Minor drift in tiny details is acceptable if the metaphor remains clear and the final composition still resembles the approved still. Major drift, added text, fake UI, mismatched opening color, unwanted kraft-paper base, over-wrinkled/dirty paper texture, lost stop-motion assembly, unwanted BGM, or unwanted voiceover should be regenerated or post-processed depending on where the issue appears."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 8: Optional Assembly, Music, Narration, and Delivery"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "If the user asks for a multi-clip story video, assemble the approved clips in the confirmed storyboard order and preserve each clip's original collage SFX by default."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Add BGM, narration/口播, or subtitles only when explicitly requested. When the user requests BGM or narration after clips already exist, mix it with the collage SFX instead of replacing SFX, unless the user asks to mute the original SFX."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For each completed item, deliver:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Final B-roll video path or final assembled video path"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Approved still frame path when relevant"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "A one-sentence explanation of how the script or visual beat became a visual metaphor"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Media note: collage SFX by default, and list any explicitly requested BGM, narration/口播, or subtitle additions"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Any QA caveat if a clip passed with minor acceptable drift"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For batch work, group the outputs by item number and keep the user's original line or story beat attached to its result."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Failure Handling"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the production plan defaults to silent video, correct it to collage SFX only unless the user explicitly asked for silence."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the production plan includes BGM, voiceover/口播, or subtitles without explicit user request, remove them and present BGM, voiceover/口播, and subtitles as optional choices."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the production plan feels too literal, return to Gate 1 and make the visual proposition more object-driven."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the still contains fake text or UI, regenerate the still before video generation; do not try to fix it only in the video prompt."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the still or clip is too visually busy, reduce paper layers, simplify the object count, and restore negative space."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the video lacks assembly motion, reduce the number of objects and make the step-by-step arrival order more explicit."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If motion feels like smooth digital layers, rewrite the prompt around stop-motion beats: appear → light bounce → press flat → pause → lock."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the paper looks too flat, add subtle torn edges, fiber texture, layered seams, and soft shadows."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the paper looks over-aged or dirty, remove kraft-paper, brown/yellowed base, heavy wrinkles, stains, and distressed treatment."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the opening color clashes with the approved still, start from the same main background color as the still."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If the final frame drifts too far from the still, strengthen the instruction that the approved still is the completed final composition."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If generated audio lacks collage SFX but the visual is otherwise strong, ask the user whether to keep it, regenerate with stronger SFX direction, or add/post-sync SFX."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If generated audio contains unwanted BGM or voiceover, remove or regenerate it before final delivery."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If precise layer control is required, recommend a layered animation or editing workflow instead of continuing this Skill."
                }
              ]
            }
          ]
        }
      ]
    },
    {
      "url": "https://github.com/MiniMax-AI/MiniMax-H3/blob/main/skills/papercraft-stop-motion-explainer/SKILL.md",
      "title": "papercraft-stop-motion-explainer",
      "anchor": "skill-papercraft-stop-motion-explainer",
      "blocks": [
        {
          "type": "quote",
          "inlines": [
            {
              "t": "For creators explaining science, education, or general knowledge through tactile handmade papercraft visuals. Users provide a topic, core knowledge points, or source material and may specify audience, duration, aspect ratio, and deliverable type. The Skill extracts the learning goal and visual metaphor, proposes creative directions, designs paper characters, layered diorama sets, and props, creates preview concepts plus image and video prompts, and plans storyboards, camera movement, transitions, and sound with staged approvals and review checklists. It outputs a production-ready papercraft stop-motion explainer package, or selected assets such as still prompts, image-series prompts, short-video prompts, or storyboards. Best for cut-paper, pop-up-book, layered diorama, and miniature stop-motion explainers; not for standard 2D cartoons, line doodles, live action, or explainers without a paper-art look."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Papercraft Stop-Motion Explainer"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Create a complete papercraft stop-motion explainer package from a science, education, or knowledge topic. The output is a production-ready creative plan: style rules, character and set design, asset planning, prompts, storyboard structures, motion language, sound direction, negative prompts, and review criteria."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use this Skill when the user wants a tactile handmade explainer style: layered paper, cardboard cutouts, miniature diorama, stop-motion puppet movement, pop-up-book staging, paper props, and physical shadows. The default assumption is that the user wants a complete explainer video package. Prompts, storyboards, asset plans, and motion notes are reviewable production assets inside that complete process, not isolated deliverables unless the user says so."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "When this Skill proceeds from planning/prompting into actual video generation, use MiniMax-H3 as the default video generation model. Treat MiniMax-H3 as the default unless the user explicitly selects another available model or MiniMax-H3 is unavailable."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Canvas Document Delivery Rule"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For complete video packages, production plans, storyboards, or any long multi-section planning output, write the full production document to the canvas as a text document. In the chat reply, give only a brief summary, the document filename, and the next recommended action. Do not paste long production plans, large storyboard tables, full prompt libraries, or full checklists into the conversation unless the user explicitly asks to see them in chat."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use chat for concise guidance and decision points; use the canvas document as the source of the detailed plan. When the user asks to revise the plan, update the existing canvas document rather than creating a duplicate unless a new version is intentionally needed."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Visual Depth and Papercraft Motion Priority"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Every visual plan, preview prompt, video prompt, and review pass must prioritize both layered image depth and unmistakable papercraft stop-motion qualities."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Required visual-depth emphasis:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Build scenes with clear foreground, midground, background, and far-background planes."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use foreground occluders such as paper leaves, clouds, frames, curtains, props, or cutout silhouettes to create depth."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Keep the main knowledge object or focal action in a readable middle plane."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Add background parallax, small environmental motions, and layer separation instead of flat static backdrops."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use circular, diagonal, tunnel, pop-up, or cross-section compositions when they help the viewer read depth."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Required papercraft stop-motion emphasis:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Make all visible objects feel physically made from paper: layered cardboard, cut edges, paper fibers, folds, seams, tabs, brads, joints, pull-tabs, sliders, rotating discs, and visible thickness."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Motion should feel frame-by-frame and hand-manipulated: small stepped movements, tiny pauses, slight rebounds, hinged gestures, sliding paper mechanisms, page flips, pull-tab reveals, and paper pieces settling."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Background elements should also be paper mechanisms when possible: paper clouds sliding on rails, paper moons/discs moving on tracks, layered scenery shifting in parallax, paper leaves falling, paper lamps swaying, and cardboard doors opening."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Avoid smooth CG motion, plastic 3D surfaces, flat vector backdrops, overly static backgrounds, and large character motion that breaks the miniature stop-motion feel."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Lightweight Request Bypass"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "If the user explicitly asks for only one production asset, do not force the full 18-step package workflow. Route directly to the relevant step while preserving the papercraft style rules."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use these shortcuts:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Single-image prompt only: run STEP 1, STEP 2, STEP 9, and STEP 17."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Image-series prompts only: run STEP 1, STEP 2, STEP 10, and STEP 17."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "5-second image-to-video prompt only: run STEP 1, STEP 2, STEP 11, and STEP 17."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Storyboard only: run STEP 1, STEP 2, STEP 12, STEP 13, STEP 14, STEP 15, and STEP 16."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Creative directions only: run STEP 1, STEP 2, and STEP 3."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use the full phased confirmation workflow only when the user asks for a complete video package, a full production plan, or does not specify a narrower deliverable."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "Interaction Rule: Confirmation Cards Between Phases"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "After each major phase, pause and ask the user with a selection card before moving forward. All polling, multi-choice decisions, confirmations, continue/revise/stop gates, and user decision points must use cards rather than plain text asking the user to reply with a number. The card must give practical next-step choices, not an open-ended question. After the creative directions phase, the next confirmation card must ask the user to choose the target video duration before detailed character, scene, preview, prompt, or storyboard work continues."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use choices like:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Continue to the next phase with the current direction."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Revise the current phase before continuing."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Switch to one of the other creative directions."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Jump to a specific production asset: visual preview images, single-image prompt, image-series prompts, 5-second image-to-video prompt, or storyboard."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Stop here and export the current package."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Keep each card short. Include the recommended option first when the current result is strong. This staged confirmation protects the full-video workflow: the user can adjust each asset before it becomes the basis for the next step."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 1: Understand the Input"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Analyze the user's topic and production goal. Preserve the user's domain words and do not simplify the science into a different topic."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Output a concise understanding block:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Topic or knowledge point"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Target audience: children, general audience, classroom, social media, brand education, or specialist audience"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Intended duration: 15s, 30s, 60s, or unspecified"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Platform or format when stated"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Required output type: single image, image series, 5-second image-to-video prompt, storyboard, or full package"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Core learning outcome: the one sentence the viewer should remember"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Visual metaphor: how the concept becomes a paper object, model, puppet, layer, path, or mechanism"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "If crucial information is missing, choose reasonable defaults instead of stopping: general audience, 30-second short, horizontal 16:9 video by default unless the user specifies another ratio, and one paper narrator plus one core paper model."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 2: Summarize the Style DNA"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Before designing the video, state the style rules that must stay consistent."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Include these traits:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Handmade papercraft stop-motion look"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Miniature paper diorama or shadow-box stage"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Layered cardboard cutouts with visible thickness"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Matte tactile paper textures, fibers, folds, seams, torn or cut edges"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Paper puppet characters built from separate overlapping parts"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Real physical drop shadows between layers"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Multi-plane foreground, midground, background, and far background"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Macro miniature photography, slight depth of field, and 2.5D parallax"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Educational labels, arrows, cards, and simple symbols made from paper"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Clear foreground / midground / background / far-background depth, with foreground occlusion and readable parallax"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Background layers with paper-mechanism motion, not static painted scenery"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Stop-motion motion language: stepped movement, tiny pauses, slight rebounds, hinged joints, pull-tabs, sliders, rotating discs, paper pieces settling"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Explain the reason: the paper medium turns abstract science into touchable objects and makes layered explanation easy to understand. The scene must feel physically built and animated frame by frame, not merely illustrated in a paper-like texture."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 3: Propose 3-5 Creative Directions"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Generate 3 to 5 distinct concepts. Each direction must explain the same topic through a different visual metaphor or narrative structure."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For each direction, provide:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Title"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Core idea"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Explainer angle"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Paper visual metaphor"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Best duration"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Best audience or platform"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Signature visual moment"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Risk or limitation"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "After presenting directions, ask the user to choose both the creative direction and the target duration. Duration options should be concise: 15s quick version, 30s standard version, 60s full version, or custom duration. Do not proceed into detailed assets until a duration is chosen."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Recommended direction archetypes:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Pop-up-book journey: each page reveals one layer of the concept."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Paper scientist laboratory: a paper host demonstrates the mechanism on a table."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Layered cross-section model: a paper object opens like a sectional diagram."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Miniature nature theater: ecological, geographic, or astronomical topics unfold in a paper landscape."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Paper mechanism board: gears, arrows, sliders, labels, and moving parts explain cause and effect."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 4: Design Paper Characters"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Design characters only when they help communication. A character may be a host, assistant, animal guide, personified molecule, immune cell, planet, machine part, or natural force."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For each character, output:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Name and role in the explanation"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Shape language and proportions"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Paper construction: cutout face, layered hair or body, cardboard limbs, joint nodes, tabs, brads, or folded parts"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Expression system: simple paper eyes, eyebrows, mouth shapes, replaceable emotion cards"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Movement style: stop-motion nudges, hinged arm gestures, pointing, bouncing, sliding, or flip-card expressions"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Reusable identity details for image series consistency"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Keep characters simple enough to remain readable in short videos."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 5: Design Paper Scenes"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Treat every scene as a physical paper stage, not a flat background."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For each scene, output:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Scene name"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Scientific purpose"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Foreground elements"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Midground subject and action"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Background environment"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Far-background board or sky"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Movable paper mechanisms"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Educational information carriers: labels, arrows, charts, measurement tags, captions, or cards"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use at least four depth planes whenever possible. Keep the main knowledge model separated from the background through spacing and shadow."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 6: Plan Layered Diorama Staging"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Create a multi-plane staging table."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Required columns:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Layer number"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Plane role"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Paper elements"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Material and edge treatment"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Motion or parallax behavior"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Shadow interaction"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Knowledge function"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Rules:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use 4-7 layers for most shots."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Place reading-heavy labels on stable layers."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Let foreground elements partially occlude the stage for miniature realism."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Keep the core concept in the midground, where attention is strongest."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use layer separation to explain hierarchy, sequence, anatomy, causality, or scale."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 7: Plan Prop and Asset Library"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Create an asset list grouped by function."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Asset groups:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Host and character assets"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Core scientific object assets"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Explanation props: arrows, labels, cards, charts, magnifiers, rulers, meters"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Scene props: lab bench, hills, books, shelves, clouds, stars, trees, water, tubes, gears"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Motion props: paper strips, sliders, rotating discs, pop-up tabs, pull-out layers, paper confetti"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Sound cue props when useful: page flip, scissors, paper rustle, click, pop, tape peel"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For each asset, define:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Name"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Purpose"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Paper material"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Layer placement"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Static or movable"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Appearance timing"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Consistency notes"
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 8: Plan or Generate 1-3 Visual Preview Images"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Before writing final prompts or storyboards, plan 1 to 3 visual preview images based on the approved creative direction, character design, scene design, and layered staging. If image generation is available and the user wants actual previews, generate them; otherwise provide preview briefs and prompts. These previews are for style and concept confirmation, not final production frames."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Default preview ratio follows the project video ratio: horizontal 16:9 unless the user specifies another ratio. If the user requested vertical, square, or another format, use that ratio consistently for previews and later video planning."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For each preview, define:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Preview number and purpose"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Which approved direction, character, or scene it visualizes"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Key visual focus: overall world, character look, mechanism clarity, cultural atmosphere, or ending memory image"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "What the user should judge before continuing"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Recommended preview set:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": true,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Overall world preview: shows the full papercraft diorama, main character, core object, and atmosphere."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Mechanism preview: shows the science model, paper arrows, labels, and movable explanatory props."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Emotional or ending preview: shows the cultural connection, summary card, or final memory image."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "After presenting previews, pause with a confirmation card. Offer choices such as: continue to prompt writing, revise preview 1, revise preview 2, revise preview 3, reduce to one visual direction, or switch creative direction. Do not write final single-image, image-series, or 5-second image-to-video prompts until the user confirms the visual preview direction."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 9: Write Single-Image Prompt"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Create a prompt for one concept image or key visual."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "The prompt must include:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "User's topic and core object"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Papercraft stop-motion style"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Miniature diorama stage"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Layered cardboard cutouts"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Visible paper fibers, folds, seams, cut edges, and thickness"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Real physical shadows between layers"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Macro miniature photography and slight depth of field"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Educational paper labels, arrows, or cards when needed"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Avoid overloading the image with every knowledge detail. One image should communicate one main idea."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 10: Write Image-Series Prompts"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Create a sequence of prompts when the user needs multiple keyframes or a storyboard image set."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "For each image, provide:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Image number and purpose"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "What changes from the previous image"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Shared style anchors"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Character and scene consistency anchors"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Prompt"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Series rules:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Keep the same paper material language, light direction, depth planes, and character identity."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Each image should explain one step of the knowledge point."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Preserve domain-specific words from the user's topic in every prompt."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use the same aspect ratio across the series unless the user requests variations."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 11: Write 5-Second Image-to-Video Prompt"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Create a short prompt that animates a single reference image while preserving the paper style."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Include:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Preserve paper texture, cut edges, layered set, and physical shadows"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Slow push-in, gentle pan, or parallax move"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Small stop-motion-like puppet gestures"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Paper arrows, labels, sliders, or mechanisms moving slightly"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Foreground and background parallax"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Avoid smooth CG transformation, melting, plastic surfaces, or high-speed camera moves"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Keep motion limited and physically plausible for paper objects."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 12: Create Storyboard for the Chosen Duration"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use the duration chosen after the creative directions phase. Do not present three full storyboard versions by default. First give a brief content overview, then provide a concise storyboard table for the chosen duration only."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "The content overview should be short and clear:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "One-sentence video premise"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Target duration and ratio"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Main visual structure"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Knowledge path: hook → explanation → example or cultural connection → memory sentence"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Storyboard table rules:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Keep text compact. Avoid long paragraphs inside table cells."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use only the shots needed for the chosen duration."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "15s: usually 4 shots."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "30s: usually 5-6 shots."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "60s: usually 7-9 shots."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Each shot explains one knowledge beat."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Required columns:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Time"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Knowledge beat"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Visual action"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Paper movement"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Camera / transition"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Sound cue"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "After the table, ask the user with a confirmation card: continue to editing rhythm and camera rules, revise storyboard, change duration, or return to visual previews."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 13: Define Editing Rhythm"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Set the rhythm according to duration and educational clarity."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Guidelines:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "15s: 4-6 shots, fast but readable, 2-4 seconds per shot."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "30s: 6-8 shots, 3-5 seconds per shot."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "60s: 8-12 shots, 4-7 seconds per shot."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Pause briefly when a label card appears."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Do not cut before the viewer understands the paper mechanism."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use rhythmic paper movements instead of aggressive digital edits."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 14: Define Camera Rules"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use camera movement that feels like filming a miniature paper stage."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Recommended moves:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Slow push-in to enter the paper world"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Lateral pan with multi-plane parallax"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Static medium shot for host explanation"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Macro close-up for paper texture and key props"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Slight top-down angle for cross-section diagrams"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Layer pass-through when moving into internal structures"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Avoid:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "High-speed flying camera"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Full 360-degree orbit unless the set is explicitly built for it"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Digital glitch motion"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Liquid morphing"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Hyper-real CG camera behavior"
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 15: Define Transitions"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Use transitions that obey paper physics."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Recommended transitions:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Page flip"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Pop-up-book unfold"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Pull-tab slide"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Paper label wipe"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Paper cloud pass"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Circular paper mask"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Cut-paper door opening"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Cross-section layer split"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Paper confetti burst"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Tape or sticker reveal"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Avoid electronic scanlines, neon glitches, glass shatter, metallic wipes, and sci-fi particle transitions unless the user explicitly requests a contrast effect."
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 16: Define Sound Design"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Build a tactile handmade sound palette."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Recommended sound cues:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Paper flip"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Scissor snip"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Cardboard slide"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Paper rustle"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Small wooden click"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Soft pop"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Tape peel"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Puppet joint tap"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Box opening"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Paper confetti scatter"
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Music direction:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Match the BGM to the user's topic, culture, and emotional tone, not only to the generic papercraft style."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "For culturally specific topics, design BGM around the topic's relevant musical language. For example, a Mid-Autumn Festival explainer should lean toward restrained Chinese traditional color: guzheng, pipa, bamboo flute or xiao, light percussion, soft strings, and enough silence for narration."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "For science or classroom topics without a strong cultural identity, use light marimba, xylophone, pizzicato strings, soft percussion, and a warm educational tone."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Keep music light under narration and apply ducking in the final mix."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Avoid heavy cinematic bass, aggressive EDM, futuristic textures, or overdramatic scoring unless requested."
                }
              ]
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Paper-motion SFX direction:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Design SFX from the actual video motion beats: page flip, paper door opening, paper rail slide, card flip, cardboard drawer pull, paper box opening, paper layer stack, soft pop, puppet joint tap, and paper rustle."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Use SFX sparingly as tactile accents. They should make paper motion feel physical, not become exaggerated cartoon sounds."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Map SFX to the storyboard timeline before final mixing so action, narration, and sound reinforce each other."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 17: Generate and Clean Voiceover Audio"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "When the workflow includes narration, generate the voiceover after the script is confirmed. Then check the generated audio before final assembly."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Voiceover rules:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Match voice tone to the topic and audience: warm, clear, and gentle for family or education topics; more neutral for classroom or technical explainers."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Compare generated voiceover duration with the chosen video duration. If the deviation is over 20%, ask the user with a card whether to shorten the script, extend the video, or accept the mismatch."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Listen for tail noise, clicks, breath artifacts, abrupt cutoffs, or model residue at the end."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If tail noise exists, repair the existing audio first: trim the noisy tail and add a short fade-out. Prefer repair over regenerating when the voice performance is otherwise good."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "If regenerating, explicitly request a clean ending with no tail noise, but still verify after generation."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 18: Provide Negative Prompts"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Always include a concise negative prompt block to protect the style."
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "Recommended negatives:"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "smooth plastic 3D"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "glossy CG render"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "live-action realism"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "flat vector illustration"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "generic cartoon with no paper texture"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "metallic sci-fi surfaces"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "glass material"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "cyberpunk neon"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "digital glitch effects"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "oil painting strokes"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "realistic hair or skin pores"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "no paper fibers"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "no cut edges"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "no layer shadows"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "overly smooth edges"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "high-speed camera orbit"
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "melting or liquid morphing"
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 3,
          "inlines": [
            {
              "t": "STEP 19: Run Review Checklist"
            }
          ]
        },
        {
          "type": "paragraph",
          "inlines": [
            {
              "t": "End with a checklist. Mark problems only when they matter to the user's requested output."
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "Style checklist"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Paper fibers, folds, seams, and cut edges are visible."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Cardboard thickness is visible."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Layers cast physical shadows."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The image feels like miniature photography, not flat illustration."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The style avoids plastic CG and live-action realism."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "Character checklist"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Characters read as paper puppets."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Faces and expressions are cut-paper simple."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Joints and limbs feel assembled from separate parts."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Motion remains stop-motion-like and physically plausible."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "Scene checklist"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Foreground, midground, background, and far background are clear."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Props are paper-made and support the explanation."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Labels, arrows, and cards do not block the core model."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Each shot explains only one knowledge beat."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "Video checklist"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Camera moves match miniature filming."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Transitions follow paper physics."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Sound cues match paper, cardboard, and puppet movement."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The storyboard duration fits the target length."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "The final memory sentence is clear."
                }
              ]
            }
          ]
        },
        {
          "type": "heading",
          "level": 4,
          "inlines": [
            {
              "t": "Audio checklist"
            }
          ]
        },
        {
          "type": "list",
          "ordered": false,
          "items": [
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Voiceover duration fits the chosen video duration or the mismatch has been resolved with user confirmation."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Voiceover ending is clean, with no tail noise, click, breath residue, or abrupt cutoff."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "BGM matches the topic's culture and emotional tone, not only the generic papercraft style."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "BGM stays under narration and does not compete with spoken information."
                }
              ]
            },
            {
              "depth": 0,
              "inlines": [
                {
                  "t": "Paper-motion SFX align with actual visual motion beats and remain subtle."
                }
              ]
            }
          ]
        }
      ]
    }
  ]
}