[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-minimax-3d-animation-short-generator":3,"mdc--jgveb5-key":36,"related-org-minimax-3d-animation-short-generator":1159,"related-repo-minimax-3d-animation-short-generator":1358},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":32,"sourceUrl":34,"mdContent":35},"3d-animation-short-generator","generate stylized 3D animated shorts","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.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"minimax","MiniMax","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fminimax.jpg","MiniMax-AI",[13,17,20,23],{"name":14,"slug":15,"type":16},"Creative","creative","tag",{"name":18,"slug":19,"type":16},"3D","3d",{"name":21,"slug":22,"type":16},"Animation","animation",{"name":24,"slug":25,"type":16},"Video","video",1132,"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-H3","2026-08-08T04:19:20.46802",null,59,[],{"repoUrl":27,"stars":26,"forks":30,"topics":33,"description":29},[],"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-H3\u002Ftree\u002FHEAD\u002Fskills\u002F3d-animation-short-generator","---\nname: 3d-animation-short-generator\ndescription: |\n  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.\n---\n\n# 3D Animation Short Generator\n\nUse 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.\n\nCore rule: **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\u002Fscene 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**.\n\n## Global Visual Style Lock\n\nUnless 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:\n\n- Rendering style: Pixar-inspired 3D cartoon rendering, C4D + Octane renderer look, high-end animated feature quality.\n- 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.\n- 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.\n- Hair \u002F fur: combine strong sculpted clumps and clean block shapes with fine edge flyaway hairs or fuzzy rim details, so hair\u002Ffur feels designed but tactile under light.\n- Skin \u002F material: warm subsurface scattering skin quality, soft translucent reddish light through ears, cheeks, nose, and fingertips; avoid hard plastic skin.\n- Acting style: exaggerated, lively Disney\u002FPixar-style character animation performance with squash and stretch, strong brows, eye corners, pupils, lips, and cheek shape changes.\n- Motion style: high-energy poses, clear line of action, forward lean, strong anticipation, fast but readable timing, elastic body mechanics, and vivid micro-expressions.\n- Emotional range: balance cuteness and explosive expressiveness; intense emotions may use dramatic facial deformation while preserving character appeal.\n\nNegative 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.\n\n## STEP 0: Intake and Canvas Plan\n\nCapture:\n\n- One-line idea or rough premise\n- 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\n- Approximate length, if the user already stated it\n- Screen size \u002F aspect ratio, if the user already stated it\n- Visual tone: default warm stylized 3D animation\n- Dialogue requirement: whether the film has dialogue, voiceover, or no speech\n- Dialogue language only if the user explicitly states it; do not default to English dialogue\n\nImmediately after capturing the user's input, before Project Brief or any other next step, show choice cards to confirm production format:\n\nScreen size \u002F aspect ratio card:\n\n- 16:9 landscape (recommended for cinematic short)\n- 9:16 vertical short\n- 1:1 square\n- 4:5 social portrait\n- Custom size \u002F aspect ratio\n\nTotal duration card:\n\n- 30–60 seconds (recommended)\n- 15–30 seconds\n- 60–90 seconds\n- 90–180 seconds\n- Custom duration\n\nOnly proceed after the user chooses both screen size\u002Faspect ratio and total duration, or explicitly supplies custom values. Store the approved screen size\u002Faspect 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.\n\nCreate or later update canvas artifacts in this order:\n\n1. Project Brief text node\n2. Story Outline text node\n3. Labeled Character Card image nodes\n4. Environment-only Scene Card image nodes\n5. Standardized Shot Information Table node with six columns; each row must include per-second directives inside `Shot Description`\n6. **Single text storyboards document** — one canvas text node named `\u003Ctitle> text storyboards` 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 `(extracted)` marker is left in the document. Pencil image storyboards, if opted in, are separate image nodes.\n7. Single-Shot Video Clip nodes (rendered by the video model selected in Step 7 — H3 default, Seedance 2.0 fallback)\n8. Assembled Main Video node\n9. Matched BGM audio node and Final BGM-Composited Video node\n\nDo not dump long production content only in chat. Put durable outputs on canvas as text, image, video, or audio nodes.\n\n## STEP 1: Project Brief\n\nProduce a concise project brief and write it to a canvas text node named with the project title or `项目简报`.\n\nInclude:\n\n- Working title\n- One-line What-if\n- Emotional premise\n- Target audience feeling\n- Main deliverables planned\n- Approved screen size \u002F aspect ratio\n- Approved total duration\n- Dialogue mode and language: only use a specific language when the user explicitly requested it; otherwise write `language not specified` and keep dialogue minimal or ask later when needed\n- Initial risks\n- Dialogue intent when present\n\nThen show a user choice card:\n\n- Continue with this direction (recommended)\n- Regenerate premise options\n- Revise emotional premise\n- Refine dialogue direction\n\nOnly proceed after the user chooses or explicitly says to continue.\n\n## STEP 2: Story Outline and Gates\n\nCreate a story outline and write it to a canvas text node named `故事大纲` or `story-outline`.\n\nInclude:\n\n- Protagonist Want \u002F Need \u002F flaw\n- Core world rule\n- 8-beat causal story spine\n- Emotional anchor and payoff\n- Dialogue beats if the user requested dialogue\n- Red-line checks\n\nGate checks:\n\n- Protagonist is active\n- Crisis is intensified by protagonist flaw\n- Coincidence never solves the problem\n- Ending reuses an earlier emotional anchor\n- Antagonistic pressure is not a flat villain\n- Dialogue reveals relationship change instead of explaining the theme\n\nThen show a user choice card:\n\n- Approve story and continue (recommended)\n- Revise beats\n- Revise emotion curve\n- Revise dialogue beats\n- Return to premise\n\n## STEP 3: Character Cards\n\nGenerate character reference cards and place each image on canvas. Recommended order:\n\n1. Protagonist card\n2. Contrast \u002F pressure character card\n3. Optional supporting character card\n\nEach 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:\n\n- Character name label in English and\u002For the project language\n- Role label, such as protagonist, grandma, thief, sidekick, pressure character\n- Main 3\u002F4 view\n- Front \u002F side \u002F back views\n- Expressions\n- Material \u002F costume \u002F prop details\n- Important prop labels, such as handbag, wallet, skateboard, apple basket, scarf, shoes, glasses\n- Identity lock repeated in the prompt\n- A short visual-ID note listing age range, body type, hairstyle, outfit colors, signature props, and do-not-change traits\n\nFor stylized 3D animation, keep the character soft, readable, and consistent across later images and videos.\n\nAfter the main character cards are generated, show a user choice card:\n\n- Lock character designs and continue (recommended)\n- Regenerate protagonist card\n- Adjust specific visual details\n- Add another character card\n\nWarn 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.\n\n## STEP 4: Scene Cards\n\nGenerate 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.\n\nInclude:\n\n- Main environment overview\n- Key light states, such as day \u002F night\n- Emotional sub-spaces\n- Continuity landmarks (fixed objects whose screen position must persist across shots in the same scene, e.g. kitchen island, sofa, door frame, tree, mailbox)\n- Important props in the environment\n\nThen show a user choice card:\n\n- Lock scene design and continue (recommended)\n- Regenerate scene card\n- Add another scene angle\n- Adjust lighting or layout\n\n## STEP 5: Standardized Shot Table Video Prompts (Six Columns)\n\nAfter 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.\n\nRequired reference: read and follow `references\u002Fshot-table-spec.md` for the exact six-column schema, per-second directive requirements, table-wide rules, user approval card, and mandatory Step 5.5 self-check gate.\n\nMinimum runtime contract:\n\n- Create a canvas table node named `标准镜头信息表` or `standard-shot-table`.\n- Use exactly six columns: `Shot ID & Duration`, `Continuity Handoff`, `Reference Anchors (Spatial + Identity)`, `Hook Type`, `Shot Description (Per-Second Directives)`, `Audio & Dialogue Track`.\n- Every row must include complete per-second directives, continuity handoff, reference anchors, hook type, and audio\u002Fdialogue timing.\n- Run the Step 5.5 self-check from `references\u002Fshot-table-spec.md` before storyboarding. Do not enter Step 6 until the self-check passes.\n\nThen show the table approval\u002Fself-check choice cards defined in `references\u002Fshot-table-spec.md`.\n\n## STEP 6: Text Storyboards Document (Default) + Pencil Image Storyboards (Opt-in)\n\nAfter the Step 5.5 self-check passes, show a storyboard-mode choice card before producing any storyboard artifact.\n\nRequired reference: read and follow `references\u002Fstoryboard-guidelines.md` for the default single text storyboards document, optional multi-panel pencil storyboards, shot-level extraction\u002Fre-integration, storyboard approval cards, and visualization fallback rules.\n\nMinimum runtime contract:\n\n- Default mode is one authoritative text storyboards document containing one section per shot.\n- Pencil storyboard images are opt-in visualization artifacts only; they never override the text storyboard.\n- Extract a shot into a standalone text node only when the user flags that shot for heavy iteration.\n- Step 7 must read the matching text storyboard section or extracted standalone node, not the pencil image.\n\nAfter all storyboards are approved, proceed to the video-model choice card.\n\n## STEP 7: Video-Model Choice Card + Single-Shot Video Clips\n\nBefore any clip is rendered, show the video-model choice card and resolution choice card.\n\nRequired references:\n\n- Read `references\u002Fmodel-selection.md` for the H3 default, Seedance 2.0 fallback, per-shot mixed mode, resolution choices, and model-specific prompt shaping.\n- Read `references\u002Ffallback-policy.md` for per-model retry ladders, drift handling, and escalation choices.\n\nMinimum runtime contract:\n\n- H3 is the recommended default model.\n- Seedance 2.0 is the fallback for high-stakes animation performance or repeated H3 failure.\n- Per-shot mixed mode is allowed only when the shot table marks the model per row; unmarked rows default to H3.\n- Strip all storyboard-only labels before video render.\n- Bind each clip to the approved text storyboard section, exact character cards, and exact scene card.\n- If a clip drifts from the approved `Reference Anchors`, follow `references\u002Ffallback-policy.md`; do not silently assemble incorrect clips.\n\nAfter all clips render, place them on canvas in shot order, group them as `\u003Ctitle> shot clips`, and show the clip approval card defined in `references\u002Fmodel-selection.md`.\n\n## STEP 8: Full Film Assembly, BGM Match, and Final Output\n\nAfter all single-shot clips are approved, assemble the complete main video, match or generate one continuous BGM track, and produce the final composited video.\n\nRequired reference: read `references\u002Fqc-checklist.md` for assembly rules, BGM rules, final review checks, canvas ordering\u002Fgrouping discipline, user choice-card discipline, and regeneration\u002Flatest-asset discipline.\n\nMinimum runtime contract:\n\n- Preserve the exact shot order from the approved table.\n- Use only approved latest assets.\n- Duck BGM under dialogue, reactions, and important SFX.\n- Do not add subtitles or text unless explicitly requested.\n- Final video must contain no storyboard traces, labels, arrows, timing marks, panel borders, or double-binding labels.\n\nThen run the final review checks from `references\u002Fqc-checklist.md` and deliver the final approved asset.\n\n## Boundaries\n\nDo 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.\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,50,56,69,76,81,126,131,137,142,180,185,190,218,223,251,256,261,338,343,349,361,366,427,432,455,460,466,486,490,523,528,561,565,593,599,604,622,627,675,680,685,708,713,719,724,728,756,760,783,789,794,807,812,899,910,916,921,933,937,960,965,971,976,981,1009,1013,1061,1080,1086,1091,1104,1108,1136,1148,1154],{"type":42,"tag":43,"props":44,"children":46},"element","h1",{"id":45},"_3d-animation-short-generator",[47],{"type":48,"value":49},"text","3D Animation Short Generator",{"type":42,"tag":51,"props":52,"children":53},"p",{},[54],{"type":48,"value":55},"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":42,"tag":51,"props":57,"children":58},{},[59,61,67],{"type":48,"value":60},"Core rule: ",{"type":42,"tag":62,"props":63,"children":64},"strong",{},[65],{"type":48,"value":66},"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\u002Fscene 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",{"type":48,"value":68},".",{"type":42,"tag":70,"props":71,"children":73},"h2",{"id":72},"global-visual-style-lock",[74],{"type":48,"value":75},"Global Visual Style Lock",{"type":42,"tag":51,"props":77,"children":78},{},[79],{"type":48,"value":80},"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":42,"tag":82,"props":83,"children":84},"ul",{},[85,91,96,101,106,111,116,121],{"type":42,"tag":86,"props":87,"children":88},"li",{},[89],{"type":48,"value":90},"Rendering style: Pixar-inspired 3D cartoon rendering, C4D + Octane renderer look, high-end animated feature quality.",{"type":42,"tag":86,"props":92,"children":93},{},[94],{"type":48,"value":95},"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.",{"type":42,"tag":86,"props":97,"children":98},{},[99],{"type":48,"value":100},"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.",{"type":42,"tag":86,"props":102,"children":103},{},[104],{"type":48,"value":105},"Hair \u002F fur: combine strong sculpted clumps and clean block shapes with fine edge flyaway hairs or fuzzy rim details, so hair\u002Ffur feels designed but tactile under light.",{"type":42,"tag":86,"props":107,"children":108},{},[109],{"type":48,"value":110},"Skin \u002F material: warm subsurface scattering skin quality, soft translucent reddish light through ears, cheeks, nose, and fingertips; avoid hard plastic skin.",{"type":42,"tag":86,"props":112,"children":113},{},[114],{"type":48,"value":115},"Acting style: exaggerated, lively Disney\u002FPixar-style character animation performance with squash and stretch, strong brows, eye corners, pupils, lips, and cheek shape changes.",{"type":42,"tag":86,"props":117,"children":118},{},[119],{"type":48,"value":120},"Motion style: high-energy poses, clear line of action, forward lean, strong anticipation, fast but readable timing, elastic body mechanics, and vivid micro-expressions.",{"type":42,"tag":86,"props":122,"children":123},{},[124],{"type":48,"value":125},"Emotional range: balance cuteness and explosive expressiveness; intense emotions may use dramatic facial deformation while preserving character appeal.",{"type":42,"tag":51,"props":127,"children":128},{},[129],{"type":48,"value":130},"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":42,"tag":70,"props":132,"children":134},{"id":133},"step-0-intake-and-canvas-plan",[135],{"type":48,"value":136},"STEP 0: Intake and Canvas Plan",{"type":42,"tag":51,"props":138,"children":139},{},[140],{"type":48,"value":141},"Capture:",{"type":42,"tag":82,"props":143,"children":144},{},[145,150,155,160,165,170,175],{"type":42,"tag":86,"props":146,"children":147},{},[148],{"type":48,"value":149},"One-line idea or rough premise",{"type":42,"tag":86,"props":151,"children":152},{},[153],{"type":48,"value":154},"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",{"type":42,"tag":86,"props":156,"children":157},{},[158],{"type":48,"value":159},"Approximate length, if the user already stated it",{"type":42,"tag":86,"props":161,"children":162},{},[163],{"type":48,"value":164},"Screen size \u002F aspect ratio, if the user already stated it",{"type":42,"tag":86,"props":166,"children":167},{},[168],{"type":48,"value":169},"Visual tone: default warm stylized 3D animation",{"type":42,"tag":86,"props":171,"children":172},{},[173],{"type":48,"value":174},"Dialogue requirement: whether the film has dialogue, voiceover, or no speech",{"type":42,"tag":86,"props":176,"children":177},{},[178],{"type":48,"value":179},"Dialogue language only if the user explicitly states it; do not default to English dialogue",{"type":42,"tag":51,"props":181,"children":182},{},[183],{"type":48,"value":184},"Immediately after capturing the user's input, before Project Brief or any other next step, show choice cards to confirm production format:",{"type":42,"tag":51,"props":186,"children":187},{},[188],{"type":48,"value":189},"Screen size \u002F aspect ratio card:",{"type":42,"tag":82,"props":191,"children":192},{},[193,198,203,208,213],{"type":42,"tag":86,"props":194,"children":195},{},[196],{"type":48,"value":197},"16:9 landscape (recommended for cinematic short)",{"type":42,"tag":86,"props":199,"children":200},{},[201],{"type":48,"value":202},"9:16 vertical short",{"type":42,"tag":86,"props":204,"children":205},{},[206],{"type":48,"value":207},"1:1 square",{"type":42,"tag":86,"props":209,"children":210},{},[211],{"type":48,"value":212},"4:5 social portrait",{"type":42,"tag":86,"props":214,"children":215},{},[216],{"type":48,"value":217},"Custom size \u002F aspect ratio",{"type":42,"tag":51,"props":219,"children":220},{},[221],{"type":48,"value":222},"Total duration card:",{"type":42,"tag":82,"props":224,"children":225},{},[226,231,236,241,246],{"type":42,"tag":86,"props":227,"children":228},{},[229],{"type":48,"value":230},"30–60 seconds (recommended)",{"type":42,"tag":86,"props":232,"children":233},{},[234],{"type":48,"value":235},"15–30 seconds",{"type":42,"tag":86,"props":237,"children":238},{},[239],{"type":48,"value":240},"60–90 seconds",{"type":42,"tag":86,"props":242,"children":243},{},[244],{"type":48,"value":245},"90–180 seconds",{"type":42,"tag":86,"props":247,"children":248},{},[249],{"type":48,"value":250},"Custom duration",{"type":42,"tag":51,"props":252,"children":253},{},[254],{"type":48,"value":255},"Only proceed after the user chooses both screen size\u002Faspect ratio and total duration, or explicitly supplies custom values. Store the approved screen size\u002Faspect 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":42,"tag":51,"props":257,"children":258},{},[259],{"type":48,"value":260},"Create or later update canvas artifacts in this order:",{"type":42,"tag":262,"props":263,"children":264},"ol",{},[265,270,275,280,285,297,323,328,333],{"type":42,"tag":86,"props":266,"children":267},{},[268],{"type":48,"value":269},"Project Brief text node",{"type":42,"tag":86,"props":271,"children":272},{},[273],{"type":48,"value":274},"Story Outline text node",{"type":42,"tag":86,"props":276,"children":277},{},[278],{"type":48,"value":279},"Labeled Character Card image nodes",{"type":42,"tag":86,"props":281,"children":282},{},[283],{"type":48,"value":284},"Environment-only Scene Card image nodes",{"type":42,"tag":86,"props":286,"children":287},{},[288,290],{"type":48,"value":289},"Standardized Shot Information Table node with six columns; each row must include per-second directives inside ",{"type":42,"tag":291,"props":292,"children":294},"code",{"className":293},[],[295],{"type":48,"value":296},"Shot Description",{"type":42,"tag":86,"props":298,"children":299},{},[300,305,307,313,315,321],{"type":42,"tag":62,"props":301,"children":302},{},[303],{"type":48,"value":304},"Single text storyboards document",{"type":48,"value":306}," — one canvas text node named ",{"type":42,"tag":291,"props":308,"children":310},{"className":309},[],[311],{"type":48,"value":312},"\u003Ctitle> text storyboards",{"type":48,"value":314}," 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 ",{"type":42,"tag":291,"props":316,"children":318},{"className":317},[],[319],{"type":48,"value":320},"(extracted)",{"type":48,"value":322}," marker is left in the document. Pencil image storyboards, if opted in, are separate image nodes.",{"type":42,"tag":86,"props":324,"children":325},{},[326],{"type":48,"value":327},"Single-Shot Video Clip nodes (rendered by the video model selected in Step 7 — H3 default, Seedance 2.0 fallback)",{"type":42,"tag":86,"props":329,"children":330},{},[331],{"type":48,"value":332},"Assembled Main Video node",{"type":42,"tag":86,"props":334,"children":335},{},[336],{"type":48,"value":337},"Matched BGM audio node and Final BGM-Composited Video node",{"type":42,"tag":51,"props":339,"children":340},{},[341],{"type":48,"value":342},"Do not dump long production content only in chat. Put durable outputs on canvas as text, image, video, or audio nodes.",{"type":42,"tag":70,"props":344,"children":346},{"id":345},"step-1-project-brief",[347],{"type":48,"value":348},"STEP 1: Project Brief",{"type":42,"tag":51,"props":350,"children":351},{},[352,354,360],{"type":48,"value":353},"Produce a concise project brief and write it to a canvas text node named with the project title or ",{"type":42,"tag":291,"props":355,"children":357},{"className":356},[],[358],{"type":48,"value":359},"项目简报",{"type":48,"value":68},{"type":42,"tag":51,"props":362,"children":363},{},[364],{"type":48,"value":365},"Include:",{"type":42,"tag":82,"props":367,"children":368},{},[369,374,379,384,389,394,399,404,417,422],{"type":42,"tag":86,"props":370,"children":371},{},[372],{"type":48,"value":373},"Working title",{"type":42,"tag":86,"props":375,"children":376},{},[377],{"type":48,"value":378},"One-line What-if",{"type":42,"tag":86,"props":380,"children":381},{},[382],{"type":48,"value":383},"Emotional premise",{"type":42,"tag":86,"props":385,"children":386},{},[387],{"type":48,"value":388},"Target audience feeling",{"type":42,"tag":86,"props":390,"children":391},{},[392],{"type":48,"value":393},"Main deliverables planned",{"type":42,"tag":86,"props":395,"children":396},{},[397],{"type":48,"value":398},"Approved screen size \u002F aspect ratio",{"type":42,"tag":86,"props":400,"children":401},{},[402],{"type":48,"value":403},"Approved total duration",{"type":42,"tag":86,"props":405,"children":406},{},[407,409,415],{"type":48,"value":408},"Dialogue mode and language: only use a specific language when the user explicitly requested it; otherwise write ",{"type":42,"tag":291,"props":410,"children":412},{"className":411},[],[413],{"type":48,"value":414},"language not specified",{"type":48,"value":416}," and keep dialogue minimal or ask later when needed",{"type":42,"tag":86,"props":418,"children":419},{},[420],{"type":48,"value":421},"Initial risks",{"type":42,"tag":86,"props":423,"children":424},{},[425],{"type":48,"value":426},"Dialogue intent when present",{"type":42,"tag":51,"props":428,"children":429},{},[430],{"type":48,"value":431},"Then show a user choice card:",{"type":42,"tag":82,"props":433,"children":434},{},[435,440,445,450],{"type":42,"tag":86,"props":436,"children":437},{},[438],{"type":48,"value":439},"Continue with this direction (recommended)",{"type":42,"tag":86,"props":441,"children":442},{},[443],{"type":48,"value":444},"Regenerate premise options",{"type":42,"tag":86,"props":446,"children":447},{},[448],{"type":48,"value":449},"Revise emotional premise",{"type":42,"tag":86,"props":451,"children":452},{},[453],{"type":48,"value":454},"Refine dialogue direction",{"type":42,"tag":51,"props":456,"children":457},{},[458],{"type":48,"value":459},"Only proceed after the user chooses or explicitly says to continue.",{"type":42,"tag":70,"props":461,"children":463},{"id":462},"step-2-story-outline-and-gates",[464],{"type":48,"value":465},"STEP 2: Story Outline and Gates",{"type":42,"tag":51,"props":467,"children":468},{},[469,471,477,479,485],{"type":48,"value":470},"Create a story outline and write it to a canvas text node named ",{"type":42,"tag":291,"props":472,"children":474},{"className":473},[],[475],{"type":48,"value":476},"故事大纲",{"type":48,"value":478}," or ",{"type":42,"tag":291,"props":480,"children":482},{"className":481},[],[483],{"type":48,"value":484},"story-outline",{"type":48,"value":68},{"type":42,"tag":51,"props":487,"children":488},{},[489],{"type":48,"value":365},{"type":42,"tag":82,"props":491,"children":492},{},[493,498,503,508,513,518],{"type":42,"tag":86,"props":494,"children":495},{},[496],{"type":48,"value":497},"Protagonist Want \u002F Need \u002F flaw",{"type":42,"tag":86,"props":499,"children":500},{},[501],{"type":48,"value":502},"Core world rule",{"type":42,"tag":86,"props":504,"children":505},{},[506],{"type":48,"value":507},"8-beat causal story spine",{"type":42,"tag":86,"props":509,"children":510},{},[511],{"type":48,"value":512},"Emotional anchor and payoff",{"type":42,"tag":86,"props":514,"children":515},{},[516],{"type":48,"value":517},"Dialogue beats if the user requested dialogue",{"type":42,"tag":86,"props":519,"children":520},{},[521],{"type":48,"value":522},"Red-line checks",{"type":42,"tag":51,"props":524,"children":525},{},[526],{"type":48,"value":527},"Gate checks:",{"type":42,"tag":82,"props":529,"children":530},{},[531,536,541,546,551,556],{"type":42,"tag":86,"props":532,"children":533},{},[534],{"type":48,"value":535},"Protagonist is active",{"type":42,"tag":86,"props":537,"children":538},{},[539],{"type":48,"value":540},"Crisis is intensified by protagonist flaw",{"type":42,"tag":86,"props":542,"children":543},{},[544],{"type":48,"value":545},"Coincidence never solves the problem",{"type":42,"tag":86,"props":547,"children":548},{},[549],{"type":48,"value":550},"Ending reuses an earlier emotional anchor",{"type":42,"tag":86,"props":552,"children":553},{},[554],{"type":48,"value":555},"Antagonistic pressure is not a flat villain",{"type":42,"tag":86,"props":557,"children":558},{},[559],{"type":48,"value":560},"Dialogue reveals relationship change instead of explaining the theme",{"type":42,"tag":51,"props":562,"children":563},{},[564],{"type":48,"value":431},{"type":42,"tag":82,"props":566,"children":567},{},[568,573,578,583,588],{"type":42,"tag":86,"props":569,"children":570},{},[571],{"type":48,"value":572},"Approve story and continue (recommended)",{"type":42,"tag":86,"props":574,"children":575},{},[576],{"type":48,"value":577},"Revise beats",{"type":42,"tag":86,"props":579,"children":580},{},[581],{"type":48,"value":582},"Revise emotion curve",{"type":42,"tag":86,"props":584,"children":585},{},[586],{"type":48,"value":587},"Revise dialogue beats",{"type":42,"tag":86,"props":589,"children":590},{},[591],{"type":48,"value":592},"Return to premise",{"type":42,"tag":70,"props":594,"children":596},{"id":595},"step-3-character-cards",[597],{"type":48,"value":598},"STEP 3: Character Cards",{"type":42,"tag":51,"props":600,"children":601},{},[602],{"type":48,"value":603},"Generate character reference cards and place each image on canvas. Recommended order:",{"type":42,"tag":262,"props":605,"children":606},{},[607,612,617],{"type":42,"tag":86,"props":608,"children":609},{},[610],{"type":48,"value":611},"Protagonist card",{"type":42,"tag":86,"props":613,"children":614},{},[615],{"type":48,"value":616},"Contrast \u002F pressure character card",{"type":42,"tag":86,"props":618,"children":619},{},[620],{"type":48,"value":621},"Optional supporting character card",{"type":42,"tag":51,"props":623,"children":624},{},[625],{"type":48,"value":626},"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":42,"tag":82,"props":628,"children":629},{},[630,635,640,645,650,655,660,665,670],{"type":42,"tag":86,"props":631,"children":632},{},[633],{"type":48,"value":634},"Character name label in English and\u002For the project language",{"type":42,"tag":86,"props":636,"children":637},{},[638],{"type":48,"value":639},"Role label, such as protagonist, grandma, thief, sidekick, pressure character",{"type":42,"tag":86,"props":641,"children":642},{},[643],{"type":48,"value":644},"Main 3\u002F4 view",{"type":42,"tag":86,"props":646,"children":647},{},[648],{"type":48,"value":649},"Front \u002F side \u002F back views",{"type":42,"tag":86,"props":651,"children":652},{},[653],{"type":48,"value":654},"Expressions",{"type":42,"tag":86,"props":656,"children":657},{},[658],{"type":48,"value":659},"Material \u002F costume \u002F prop details",{"type":42,"tag":86,"props":661,"children":662},{},[663],{"type":48,"value":664},"Important prop labels, such as handbag, wallet, skateboard, apple basket, scarf, shoes, glasses",{"type":42,"tag":86,"props":666,"children":667},{},[668],{"type":48,"value":669},"Identity lock repeated in the prompt",{"type":42,"tag":86,"props":671,"children":672},{},[673],{"type":48,"value":674},"A short visual-ID note listing age range, body type, hairstyle, outfit colors, signature props, and do-not-change traits",{"type":42,"tag":51,"props":676,"children":677},{},[678],{"type":48,"value":679},"For stylized 3D animation, keep the character soft, readable, and consistent across later images and videos.",{"type":42,"tag":51,"props":681,"children":682},{},[683],{"type":48,"value":684},"After the main character cards are generated, show a user choice card:",{"type":42,"tag":82,"props":686,"children":687},{},[688,693,698,703],{"type":42,"tag":86,"props":689,"children":690},{},[691],{"type":48,"value":692},"Lock character designs and continue (recommended)",{"type":42,"tag":86,"props":694,"children":695},{},[696],{"type":48,"value":697},"Regenerate protagonist card",{"type":42,"tag":86,"props":699,"children":700},{},[701],{"type":48,"value":702},"Adjust specific visual details",{"type":42,"tag":86,"props":704,"children":705},{},[706],{"type":48,"value":707},"Add another character card",{"type":42,"tag":51,"props":709,"children":710},{},[711],{"type":48,"value":712},"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":42,"tag":70,"props":714,"children":716},{"id":715},"step-4-scene-cards",[717],{"type":48,"value":718},"STEP 4: Scene Cards",{"type":42,"tag":51,"props":720,"children":721},{},[722],{"type":48,"value":723},"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":42,"tag":51,"props":725,"children":726},{},[727],{"type":48,"value":365},{"type":42,"tag":82,"props":729,"children":730},{},[731,736,741,746,751],{"type":42,"tag":86,"props":732,"children":733},{},[734],{"type":48,"value":735},"Main environment overview",{"type":42,"tag":86,"props":737,"children":738},{},[739],{"type":48,"value":740},"Key light states, such as day \u002F night",{"type":42,"tag":86,"props":742,"children":743},{},[744],{"type":48,"value":745},"Emotional sub-spaces",{"type":42,"tag":86,"props":747,"children":748},{},[749],{"type":48,"value":750},"Continuity landmarks (fixed objects whose screen position must persist across shots in the same scene, e.g. kitchen island, sofa, door frame, tree, mailbox)",{"type":42,"tag":86,"props":752,"children":753},{},[754],{"type":48,"value":755},"Important props in the environment",{"type":42,"tag":51,"props":757,"children":758},{},[759],{"type":48,"value":431},{"type":42,"tag":82,"props":761,"children":762},{},[763,768,773,778],{"type":42,"tag":86,"props":764,"children":765},{},[766],{"type":48,"value":767},"Lock scene design and continue (recommended)",{"type":42,"tag":86,"props":769,"children":770},{},[771],{"type":48,"value":772},"Regenerate scene card",{"type":42,"tag":86,"props":774,"children":775},{},[776],{"type":48,"value":777},"Add another scene angle",{"type":42,"tag":86,"props":779,"children":780},{},[781],{"type":48,"value":782},"Adjust lighting or layout",{"type":42,"tag":70,"props":784,"children":786},{"id":785},"step-5-standardized-shot-table-video-prompts-six-columns",[787],{"type":48,"value":788},"STEP 5: Standardized Shot Table Video Prompts (Six Columns)",{"type":42,"tag":51,"props":790,"children":791},{},[792],{"type":48,"value":793},"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":42,"tag":51,"props":795,"children":796},{},[797,799,805],{"type":48,"value":798},"Required reference: read and follow ",{"type":42,"tag":291,"props":800,"children":802},{"className":801},[],[803],{"type":48,"value":804},"references\u002Fshot-table-spec.md",{"type":48,"value":806}," 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":42,"tag":51,"props":808,"children":809},{},[810],{"type":48,"value":811},"Minimum runtime contract:",{"type":42,"tag":82,"props":813,"children":814},{},[815,834,882,887],{"type":42,"tag":86,"props":816,"children":817},{},[818,820,826,827,833],{"type":48,"value":819},"Create a canvas table node named ",{"type":42,"tag":291,"props":821,"children":823},{"className":822},[],[824],{"type":48,"value":825},"标准镜头信息表",{"type":48,"value":478},{"type":42,"tag":291,"props":828,"children":830},{"className":829},[],[831],{"type":48,"value":832},"standard-shot-table",{"type":48,"value":68},{"type":42,"tag":86,"props":835,"children":836},{},[837,839,845,847,853,854,860,861,867,868,874,875,881],{"type":48,"value":838},"Use exactly six columns: ",{"type":42,"tag":291,"props":840,"children":842},{"className":841},[],[843],{"type":48,"value":844},"Shot ID & Duration",{"type":48,"value":846},", ",{"type":42,"tag":291,"props":848,"children":850},{"className":849},[],[851],{"type":48,"value":852},"Continuity Handoff",{"type":48,"value":846},{"type":42,"tag":291,"props":855,"children":857},{"className":856},[],[858],{"type":48,"value":859},"Reference Anchors (Spatial + Identity)",{"type":48,"value":846},{"type":42,"tag":291,"props":862,"children":864},{"className":863},[],[865],{"type":48,"value":866},"Hook Type",{"type":48,"value":846},{"type":42,"tag":291,"props":869,"children":871},{"className":870},[],[872],{"type":48,"value":873},"Shot Description (Per-Second Directives)",{"type":48,"value":846},{"type":42,"tag":291,"props":876,"children":878},{"className":877},[],[879],{"type":48,"value":880},"Audio & Dialogue Track",{"type":48,"value":68},{"type":42,"tag":86,"props":883,"children":884},{},[885],{"type":48,"value":886},"Every row must include complete per-second directives, continuity handoff, reference anchors, hook type, and audio\u002Fdialogue timing.",{"type":42,"tag":86,"props":888,"children":889},{},[890,892,897],{"type":48,"value":891},"Run the Step 5.5 self-check from ",{"type":42,"tag":291,"props":893,"children":895},{"className":894},[],[896],{"type":48,"value":804},{"type":48,"value":898}," before storyboarding. Do not enter Step 6 until the self-check passes.",{"type":42,"tag":51,"props":900,"children":901},{},[902,904,909],{"type":48,"value":903},"Then show the table approval\u002Fself-check choice cards defined in ",{"type":42,"tag":291,"props":905,"children":907},{"className":906},[],[908],{"type":48,"value":804},{"type":48,"value":68},{"type":42,"tag":70,"props":911,"children":913},{"id":912},"step-6-text-storyboards-document-default-pencil-image-storyboards-opt-in",[914],{"type":48,"value":915},"STEP 6: Text Storyboards Document (Default) + Pencil Image Storyboards (Opt-in)",{"type":42,"tag":51,"props":917,"children":918},{},[919],{"type":48,"value":920},"After the Step 5.5 self-check passes, show a storyboard-mode choice card before producing any storyboard artifact.",{"type":42,"tag":51,"props":922,"children":923},{},[924,925,931],{"type":48,"value":798},{"type":42,"tag":291,"props":926,"children":928},{"className":927},[],[929],{"type":48,"value":930},"references\u002Fstoryboard-guidelines.md",{"type":48,"value":932}," for the default single text storyboards document, optional multi-panel pencil storyboards, shot-level extraction\u002Fre-integration, storyboard approval cards, and visualization fallback rules.",{"type":42,"tag":51,"props":934,"children":935},{},[936],{"type":48,"value":811},{"type":42,"tag":82,"props":938,"children":939},{},[940,945,950,955],{"type":42,"tag":86,"props":941,"children":942},{},[943],{"type":48,"value":944},"Default mode is one authoritative text storyboards document containing one section per shot.",{"type":42,"tag":86,"props":946,"children":947},{},[948],{"type":48,"value":949},"Pencil storyboard images are opt-in visualization artifacts only; they never override the text storyboard.",{"type":42,"tag":86,"props":951,"children":952},{},[953],{"type":48,"value":954},"Extract a shot into a standalone text node only when the user flags that shot for heavy iteration.",{"type":42,"tag":86,"props":956,"children":957},{},[958],{"type":48,"value":959},"Step 7 must read the matching text storyboard section or extracted standalone node, not the pencil image.",{"type":42,"tag":51,"props":961,"children":962},{},[963],{"type":48,"value":964},"After all storyboards are approved, proceed to the video-model choice card.",{"type":42,"tag":70,"props":966,"children":968},{"id":967},"step-7-video-model-choice-card-single-shot-video-clips",[969],{"type":48,"value":970},"STEP 7: Video-Model Choice Card + Single-Shot Video Clips",{"type":42,"tag":51,"props":972,"children":973},{},[974],{"type":48,"value":975},"Before any clip is rendered, show the video-model choice card and resolution choice card.",{"type":42,"tag":51,"props":977,"children":978},{},[979],{"type":48,"value":980},"Required references:",{"type":42,"tag":82,"props":982,"children":983},{},[984,997],{"type":42,"tag":86,"props":985,"children":986},{},[987,989,995],{"type":48,"value":988},"Read ",{"type":42,"tag":291,"props":990,"children":992},{"className":991},[],[993],{"type":48,"value":994},"references\u002Fmodel-selection.md",{"type":48,"value":996}," for the H3 default, Seedance 2.0 fallback, per-shot mixed mode, resolution choices, and model-specific prompt shaping.",{"type":42,"tag":86,"props":998,"children":999},{},[1000,1001,1007],{"type":48,"value":988},{"type":42,"tag":291,"props":1002,"children":1004},{"className":1003},[],[1005],{"type":48,"value":1006},"references\u002Ffallback-policy.md",{"type":48,"value":1008}," for per-model retry ladders, drift handling, and escalation choices.",{"type":42,"tag":51,"props":1010,"children":1011},{},[1012],{"type":48,"value":811},{"type":42,"tag":82,"props":1014,"children":1015},{},[1016,1021,1026,1031,1036,1041],{"type":42,"tag":86,"props":1017,"children":1018},{},[1019],{"type":48,"value":1020},"H3 is the recommended default model.",{"type":42,"tag":86,"props":1022,"children":1023},{},[1024],{"type":48,"value":1025},"Seedance 2.0 is the fallback for high-stakes animation performance or repeated H3 failure.",{"type":42,"tag":86,"props":1027,"children":1028},{},[1029],{"type":48,"value":1030},"Per-shot mixed mode is allowed only when the shot table marks the model per row; unmarked rows default to H3.",{"type":42,"tag":86,"props":1032,"children":1033},{},[1034],{"type":48,"value":1035},"Strip all storyboard-only labels before video render.",{"type":42,"tag":86,"props":1037,"children":1038},{},[1039],{"type":48,"value":1040},"Bind each clip to the approved text storyboard section, exact character cards, and exact scene card.",{"type":42,"tag":86,"props":1042,"children":1043},{},[1044,1046,1052,1054,1059],{"type":48,"value":1045},"If a clip drifts from the approved ",{"type":42,"tag":291,"props":1047,"children":1049},{"className":1048},[],[1050],{"type":48,"value":1051},"Reference Anchors",{"type":48,"value":1053},", follow ",{"type":42,"tag":291,"props":1055,"children":1057},{"className":1056},[],[1058],{"type":48,"value":1006},{"type":48,"value":1060},"; do not silently assemble incorrect clips.",{"type":42,"tag":51,"props":1062,"children":1063},{},[1064,1066,1072,1074,1079],{"type":48,"value":1065},"After all clips render, place them on canvas in shot order, group them as ",{"type":42,"tag":291,"props":1067,"children":1069},{"className":1068},[],[1070],{"type":48,"value":1071},"\u003Ctitle> shot clips",{"type":48,"value":1073},", and show the clip approval card defined in ",{"type":42,"tag":291,"props":1075,"children":1077},{"className":1076},[],[1078],{"type":48,"value":994},{"type":48,"value":68},{"type":42,"tag":70,"props":1081,"children":1083},{"id":1082},"step-8-full-film-assembly-bgm-match-and-final-output",[1084],{"type":48,"value":1085},"STEP 8: Full Film Assembly, BGM Match, and Final Output",{"type":42,"tag":51,"props":1087,"children":1088},{},[1089],{"type":48,"value":1090},"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":42,"tag":51,"props":1092,"children":1093},{},[1094,1096,1102],{"type":48,"value":1095},"Required reference: read ",{"type":42,"tag":291,"props":1097,"children":1099},{"className":1098},[],[1100],{"type":48,"value":1101},"references\u002Fqc-checklist.md",{"type":48,"value":1103}," for assembly rules, BGM rules, final review checks, canvas ordering\u002Fgrouping discipline, user choice-card discipline, and regeneration\u002Flatest-asset discipline.",{"type":42,"tag":51,"props":1105,"children":1106},{},[1107],{"type":48,"value":811},{"type":42,"tag":82,"props":1109,"children":1110},{},[1111,1116,1121,1126,1131],{"type":42,"tag":86,"props":1112,"children":1113},{},[1114],{"type":48,"value":1115},"Preserve the exact shot order from the approved table.",{"type":42,"tag":86,"props":1117,"children":1118},{},[1119],{"type":48,"value":1120},"Use only approved latest assets.",{"type":42,"tag":86,"props":1122,"children":1123},{},[1124],{"type":48,"value":1125},"Duck BGM under dialogue, reactions, and important SFX.",{"type":42,"tag":86,"props":1127,"children":1128},{},[1129],{"type":48,"value":1130},"Do not add subtitles or text unless explicitly requested.",{"type":42,"tag":86,"props":1132,"children":1133},{},[1134],{"type":48,"value":1135},"Final video must contain no storyboard traces, labels, arrows, timing marks, panel borders, or double-binding labels.",{"type":42,"tag":51,"props":1137,"children":1138},{},[1139,1141,1146],{"type":48,"value":1140},"Then run the final review checks from ",{"type":42,"tag":291,"props":1142,"children":1144},{"className":1143},[],[1145],{"type":48,"value":1101},{"type":48,"value":1147}," and deliver the final approved asset.",{"type":42,"tag":70,"props":1149,"children":1151},{"id":1150},"boundaries",[1152],{"type":48,"value":1153},"Boundaries",{"type":42,"tag":51,"props":1155,"children":1156},{},[1157],{"type":48,"value":1158},"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.",{"items":1160,"total":1357},[1161,1185,1199,1218,1233,1253,1269,1287,1302,1318,1337,1347],{"slug":1162,"name":1162,"fn":1163,"description":1164,"org":1165,"tags":1166,"stars":1182,"repoUrl":1183,"updatedAt":1184},"android-native-dev","develop Android native applications","Android native application development and UI design guide. Covers Material Design 3, Kotlin\u002FCompose development, project configuration, accessibility, and build troubleshooting. Read this before Android native application development.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1167,1170,1173,1176,1179],{"name":1168,"slug":1169,"type":16},"Accessibility","accessibility",{"name":1171,"slug":1172,"type":16},"Android","android",{"name":1174,"slug":1175,"type":16},"Kotlin","kotlin",{"name":1177,"slug":1178,"type":16},"Mobile","mobile",{"name":1180,"slug":1181,"type":16},"UI Components","ui-components",13030,"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002Fskills","2026-07-13T06:16:54.247834",{"slug":1186,"name":1186,"fn":1187,"description":1188,"org":1189,"tags":1190,"stars":1182,"repoUrl":1183,"updatedAt":1198},"buddy-sings","generate singing performances for AI companions","Use when user wants their Claude Code pet (\u002Fbuddy) to sing a song. Triggers on any request that combines the concept of their Claude Code buddy, pet, or companion with singing or music. Supports multilingual triggers — match equivalent phrases in any language.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1191,1194,1197],{"name":1192,"slug":1193,"type":16},"Agents","agents",{"name":1195,"slug":1196,"type":16},"Audio","audio",{"name":14,"slug":15,"type":16},"2026-07-13T06:16:35.130644",{"slug":1200,"name":1200,"fn":1201,"description":1202,"org":1203,"tags":1204,"stars":1182,"repoUrl":1183,"updatedAt":1217},"color-font-skill","select color palettes and font pairings","Choose presentation-ready color palettes and font pairings for PPT\u002Fdesign tasks. Use when users ask for visual theme choices, brand-safe palettes, or font recommendations. Triggers include: 配色, 色板, 字体, color palette, font, PPT配色, 字体搭配.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1205,1208,1211,1214],{"name":1206,"slug":1207,"type":16},"Design","design",{"name":1209,"slug":1210,"type":16},"Presentations","presentations",{"name":1212,"slug":1213,"type":16},"Themes","themes",{"name":1215,"slug":1216,"type":16},"Typography","typography","2026-07-13T06:17:02.785587",{"slug":1219,"name":1219,"fn":1220,"description":1221,"org":1222,"tags":1223,"stars":1182,"repoUrl":1183,"updatedAt":1232},"design-style-skill","select visual design systems for presentations","Select a consistent visual design system for PPT slides using radius\u002Fspacing style recipes. Use when users ask for overall style direction or component styling consistency. Includes Sharp\u002FSoft\u002FRounded\u002FPill recipes, component mappings, typography\u002Fspacing rules, and mixing guidance. Triggers: 风格, style, radius, spacing, 圆角, 间距, PPT风格, 视觉风格, design style, component style.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1224,1225,1228,1231],{"name":1206,"slug":1207,"type":16},{"name":1226,"slug":1227,"type":16},"Design System","design-system",{"name":1229,"slug":1230,"type":16},"PowerPoint","powerpoint",{"name":1209,"slug":1210,"type":16},"2026-07-13T06:17:10.398389",{"slug":1234,"name":1234,"fn":1235,"description":1236,"org":1237,"tags":1238,"stars":1182,"repoUrl":1183,"updatedAt":1252},"flutter-dev","build cross-platform apps with Flutter","Flutter cross-platform development guide covering widget patterns, Riverpod\u002FBloc state management, GoRouter navigation, performance optimization, and platform-specific implementations. Includes const optimization, responsive layouts, testing strategies, and DevTools profiling.\nUse when: building Flutter apps, implementing state management (Riverpod\u002FBloc), setting up GoRouter navigation, creating custom widgets, optimizing performance, writing widget tests, cross-platform development.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1239,1242,1245,1246,1249],{"name":1240,"slug":1241,"type":16},"Dart","dart",{"name":1243,"slug":1244,"type":16},"Flutter","flutter",{"name":1177,"slug":1178,"type":16},{"name":1247,"slug":1248,"type":16},"Performance","performance",{"name":1250,"slug":1251,"type":16},"State Management","state-management","2026-07-13T06:16:36.626679",{"slug":1254,"name":1254,"fn":1255,"description":1256,"org":1257,"tags":1258,"stars":1182,"repoUrl":1183,"updatedAt":1268},"frontend-dev","build visually striking frontend web pages","Full-stack frontend development combining premium UI design, cinematic animations,\nAI-generated media assets, persuasive copywriting, and visual art. Builds complete,\nvisually striking web pages with real media, advanced motion, and compelling copy.\nUse when: building landing pages, marketing sites, product pages, dashboards,\ngenerating media assets (image\u002Fvideo\u002Faudio\u002Fmusic), writing conversion copy,\ncreating generative art, or implementing cinematic scroll animations.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1259,1260,1261,1262,1265],{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},{"name":1206,"slug":1207,"type":16},{"name":1263,"slug":1264,"type":16},"Frontend","frontend",{"name":1266,"slug":1267,"type":16},"Web Development","web-development","2026-07-13T06:16:39.108827",{"slug":1270,"name":1270,"fn":1271,"description":1272,"org":1273,"tags":1274,"stars":1182,"repoUrl":1183,"updatedAt":1286},"fullstack-dev","build full-stack web applications","Full-stack backend architecture and frontend-backend integration guide.\nTRIGGER when: building a full-stack app, creating REST API with frontend, scaffolding backend service,\nbuilding todo app, building CRUD app, building real-time app, building chat app,\nExpress + React, Next.js API, Node.js backend, Python backend, Go backend,\ndesigning service layers, implementing error handling, managing config\u002Fauth,\nsetting up API clients, implementing auth flows, handling file uploads,\nadding real-time features (SSE\u002FWebSocket), hardening for production.\nDO NOT TRIGGER when: pure frontend UI work, pure CSS\u002Fstyling, database schema only.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1275,1278,1279,1282,1285],{"name":1276,"slug":1277,"type":16},"Backend","backend",{"name":1263,"slug":1264,"type":16},{"name":1280,"slug":1281,"type":16},"Full-stack","full-stack",{"name":1283,"slug":1284,"type":16},"REST API","rest-api",{"name":1266,"slug":1267,"type":16},"2026-07-13T06:16:43.219005",{"slug":1288,"name":1288,"fn":1289,"description":1290,"org":1291,"tags":1292,"stars":1182,"repoUrl":1183,"updatedAt":1301},"gif-sticker-maker","create animated GIF stickers from photos","Convert photos (people, pets, objects, logos) into 4 animated GIF stickers with captions.\nUse when: user wants to create cartoon stickers, GIF expressions, emoji packs, animated avatars,\nor convert photos to Funko Pop \u002F Pop Mart blind box style animations.\nTriggers: sticker, GIF, cartoon, emoji, expression pack, avatar animation.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1293,1294,1295,1298],{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},{"name":1296,"slug":1297,"type":16},"Images","images",{"name":1299,"slug":1300,"type":16},"Media","media","2026-07-13T06:16:51.74461",{"slug":1303,"name":1303,"fn":1304,"description":1305,"org":1306,"tags":1307,"stars":1182,"repoUrl":1183,"updatedAt":1317},"ios-application-dev","develop iOS applications with SwiftUI and UIKit","iOS application development guide covering UIKit, SnapKit, and SwiftUI. Includes touch targets, safe areas, navigation patterns, Dynamic Type, Dark Mode, accessibility, collection views, common UI components, and SwiftUI design guidelines. For detailed references on specific topics, see the reference files.\nUse when: developing iOS apps, implementing UI, reviewing iOS code, working with UIKit\u002FSnapKit\u002FSwiftUI layouts, building iPhone interfaces, Swift mobile development, Apple HIG compliance, iOS accessibility implementation.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1308,1309,1312,1313,1316],{"name":1168,"slug":1169,"type":16},{"name":1310,"slug":1311,"type":16},"iOS","ios",{"name":1177,"slug":1178,"type":16},{"name":1314,"slug":1315,"type":16},"SwiftUI","swiftui",{"name":1180,"slug":1181,"type":16},"2026-07-13T06:16:55.686092",{"slug":1319,"name":1319,"fn":1320,"description":1321,"org":1322,"tags":1323,"stars":1182,"repoUrl":1183,"updatedAt":1336},"minimax-docx","create and edit DOCX documents","Professional DOCX document creation, editing, and formatting using OpenXML SDK (.NET). Three pipelines: (A) create new documents from scratch, (B) fill\u002Fedit content in existing documents, (C) apply template formatting with XSD validation gate-check. MUST use this skill whenever the user wants to produce, modify, or format a Word document — including when they say \"write a report\", \"draft a proposal\", \"make a contract\", \"fill in this form\", \"reformat to match this template\", or any task whose final output is a .docx file. Even if the user doesn't mention \"docx\" explicitly, if the task implies a printable\u002Fformal document, use this skill.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1324,1327,1330,1333],{"name":1325,"slug":1326,"type":16},"Documents","documents",{"name":1328,"slug":1329,"type":16},"DOCX","docx",{"name":1331,"slug":1332,"type":16},"Office","office",{"name":1334,"slug":1335,"type":16},"Templates","templates","2026-07-13T06:16:40.461868",{"slug":1338,"name":1338,"fn":1339,"description":1340,"org":1341,"tags":1342,"stars":1182,"repoUrl":1183,"updatedAt":1346},"minimax-music-gen","generate music and audio tracks","Use when user wants to generate music, songs, or audio tracks. Triggers on any request involving music creation, song writing, lyrics generation, audio production, or covers. Also triggers when user provides lyrics and wants them turned into a song, or describes a mood\u002Fscene and wants background music. Supports multilingual triggers — match equivalent phrases in any language. Do NOT use for music playback of existing files, music theory questions, or music recommendation without generation.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1343,1344,1345],{"name":1195,"slug":1196,"type":16},{"name":14,"slug":15,"type":16},{"name":1299,"slug":1300,"type":16},"2026-07-13T06:16:50.381758",{"slug":1348,"name":1348,"fn":1349,"description":1350,"org":1351,"tags":1352,"stars":1182,"repoUrl":1183,"updatedAt":1356},"minimax-music-playlist","generate personalized music playlists","Generate personalized music playlists by analyzing the user's music taste and generation feedback history. Triggers on any request involving playlist generation, music taste profiling, or personalized music recommendations. Supports multilingual triggers — match equivalent phrases in any language.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1353,1354,1355],{"name":1195,"slug":1196,"type":16},{"name":14,"slug":15,"type":16},{"name":1299,"slug":1300,"type":16},"2026-07-13T06:16:57.002997",47,{"items":1359,"total":1447},[1360,1367,1382,1395,1410,1423,1436],{"slug":4,"name":4,"fn":5,"description":6,"org":1361,"tags":1362,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1363,1364,1365,1366],{"name":18,"slug":19,"type":16},{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},{"name":24,"slug":25,"type":16},{"slug":1368,"name":1368,"fn":1369,"description":1370,"org":1371,"tags":1372,"stars":26,"repoUrl":27,"updatedAt":1381},"brand-promo-video-generator","generate promotional brand videos","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.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1373,1376,1377,1380],{"name":1374,"slug":1375,"type":16},"Content Creation","content-creation",{"name":14,"slug":15,"type":16},{"name":1378,"slug":1379,"type":16},"Marketing","marketing",{"name":24,"slug":25,"type":16},"2026-08-08T04:19:08.155902",{"slug":1383,"name":1383,"fn":1384,"description":1385,"org":1386,"tags":1387,"stars":26,"repoUrl":27,"updatedAt":1394},"co-op-game-intro-generator","generate co-op game menu animations","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.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1388,1389,1390,1391],{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},{"name":1206,"slug":1207,"type":16},{"name":1392,"slug":1393,"type":16},"Game Development","game-development","2026-08-08T04:19:07.313539",{"slug":1396,"name":1396,"fn":1397,"description":1398,"org":1399,"tags":1400,"stars":26,"repoUrl":27,"updatedAt":1409},"h3-prompt-writing","write video generation prompts for H3","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.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1401,1402,1405,1408],{"name":14,"slug":15,"type":16},{"name":1403,"slug":1404,"type":16},"Multimodal","multimodal",{"name":1406,"slug":1407,"type":16},"Prompt Engineering","prompt-engineering",{"name":24,"slug":25,"type":16},"2026-08-08T04:19:19.631186",{"slug":1411,"name":1411,"fn":1412,"description":1413,"org":1414,"tags":1415,"stars":26,"repoUrl":27,"updatedAt":1422},"handdrawn-live-video-generator","generate hand-drawn live-action videos","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.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1416,1417,1418,1421],{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},{"name":1419,"slug":1420,"type":16},"Generative Art","generative-art",{"name":24,"slug":25,"type":16},"2026-08-08T04:19:09.002948",{"slug":1424,"name":1424,"fn":1425,"description":1426,"org":1427,"tags":1428,"stars":26,"repoUrl":27,"updatedAt":1435},"minimalist-product-ad-generator","generate minimalist product advertisements","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\u002Fstoryboards, and generates a clean product film with premium camera language. Not for KOC talking-head ads, general editing, or complex screen demos.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1429,1430,1433,1434],{"name":14,"slug":15,"type":16},{"name":1431,"slug":1432,"type":16},"E-commerce","e-commerce",{"name":1378,"slug":1379,"type":16},{"name":24,"slug":25,"type":16},"2026-08-08T04:19:12.135191",{"slug":1437,"name":1437,"fn":1438,"description":1439,"org":1440,"tags":1441,"stars":26,"repoUrl":27,"updatedAt":1446},"music-video-subtitle-generator","generate music video subtitles and typography","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.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1442,1443,1444,1445],{"name":1374,"slug":1375,"type":16},{"name":14,"slug":15,"type":16},{"name":1215,"slug":1216,"type":16},{"name":24,"slug":25,"type":16},"2026-08-08T04:19:18.794688",9]