[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-minimax-paper-collage-explainer-generator":3,"mdc-piw3r0-key":39,"related-org-minimax-paper-collage-explainer-generator":1176,"related-repo-minimax-paper-collage-explainer-generator":1375},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":29,"repoUrl":30,"updatedAt":31,"license":32,"forks":33,"topics":34,"repo":35,"sourceUrl":37,"mdContent":38},"paper-collage-explainer-generator","generate paper-collage explainer videos","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.\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",[13,17,20,23,26],{"name":14,"slug":15,"type":16},"Creative","creative","tag",{"name":18,"slug":19,"type":16},"Generative Art","generative-art",{"name":21,"slug":22,"type":16},"Education","education",{"name":24,"slug":25,"type":16},"Animation","animation",{"name":27,"slug":28,"type":16},"Video","video",1132,"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-H3","2026-08-08T04:19:21.306917",null,59,[],{"repoUrl":30,"stars":29,"forks":33,"topics":36,"description":32},[],"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-H3\u002Ftree\u002FHEAD\u002Fskills\u002Fpaper-collage-explainer-generator","---\nname: paper-collage-explainer-generator\ndescription: |\n  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.\ntrigger-words: [paper collage explainer, paper-collage animation, halftone collage, collage explainer, 纸拼贴, 拼贴科普, 定格拼贴, 拼贴动画]\nexported-by: MiniMax-hub\n---\n\n# Paper Collage Explainer Generator\n\nTurn 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.\n\nThis 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.\n\n## When to Use\n\nUse this Skill when the user wants:\n\n- A short script line turned into a visual-metaphor collage animation\n- A simple story or literary topic explained through collage B-roll\n- Editorial paper-collage animation for narration or social video\n- Halftone collage animation with objects assembling from an empty color field\n- A batch of short abstract sentences or story beats converted into separate visual-metaphor animation clips\n- A tactile knowledge explainer that may include paper clicks, pops, slides, presses, and rustles but not automatic music or voiceover\n\nDo not use this Skill when the user needs:\n\n- A realistic product ad or presenter-led video\n- Precise editable layers, timeline keyframes, or transparent cut-out assets\n- Exact logo placement or readable typography\n- Only a written video prompt without generation\n\n## Default Creative Targets\n\nUnless the user specifies otherwise:\n\n- Output ratio: 16:9 landscape\n- Clip length: about 4 seconds per segment\n- Audio default: keep or generate tactile paper-collage sound effects only, such as paper slide, pop, press, light rustle, and soft tap sounds\n- 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\n- Default: do not add voiceover, spoken narration, or presenter narration. You may ask whether the user wants narration\u002F口播 when the project may benefit, but write, synthesize, or add spoken audio only after explicit user confirmation\n- Default: do not add subtitles. You may ask whether the user wants subtitles, but create or burn in subtitles only after explicit user confirmation\n- Visual style: premium editorial halftone paper collage\n- Motion style: tactile stop-motion assembly, not slow zoom, generic drifting, or smooth digital layer movement\n- Default video generation model: `MiniMax-H3`, unless the user explicitly specifies another model, the model is unavailable, or a hard capability requirement excludes it\n- Text in image\u002Fvideo: avoid readable letters, numerals, UI, subtitles, watermark, and logos\n- 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\n\n## Audio Policy\n\nThis Skill's default delivery is **with collage SFX, and without BGM, voiceover, or subtitles**.\n\n1. During the first production-plan confirmation, state the default media approach explicitly: tactile paper-collage sound effects are kept or generated; BGM, voiceover\u002F口播, and subtitles are not added by default.\n2. It is acceptable to ask the user whether they want **voiceover narration\u002F口播**, **BGM**, or **subtitles**, especially for explainers, but present all three as optional add-ons, not defaults.\n3. 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.\n4. Do not infer that a social video automatically needs BGM or subtitles. If the user does not choose them, keep the clip SFX only.\n5. 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.\n6. During final assembly, preserve the original clip audio tracks when they contain collage SFX. Do not drop audio by default.\n7. Remove or replace audio only when the user asked for silence, when the generated audio contains unwanted speech\u002Fmusic, or when the user requests a separate music\u002Fnarration mix. Create subtitles only when the user explicitly asks for them.\n\n## Global Style Rules\n\nApply these rules to every still and video in the project:\n\n1. **Unify the overall visual style.** 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.\n2. **Control the paper texture intensity.** 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.\n3. **Unify the color tone.** 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.\n4. **Make motion read as stop-motion collage.** 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.\n5. **Keep segments coordinated.** 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.\n6. **Default to polished 16:9 layered scenes.** Unless the user explicitly requests another platform frame, plan and generate in 16:9 landscape. Use the wider canvas to build attractive foreground \u002F midground \u002F background separation, richer environment props, clear subject hierarchy, and cinematic lateral composition without turning the frame into clutter.\n7. **Emphasize paper-collage craft.** 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.\n\n## STEP 1: Parse the Input\n\nFor each line, concept, story, or topic, extract:\n\n- Core meaning: what the viewer should understand\n- Emotion: calm, urgent, ironic, surprising, absurd, clarifying, reflective, mysterious, or playful\n- Action verb: open, connect, leak, archive, compress, split, illuminate, bind, assemble, reveal, fall, chase, transform, collide\n- Visual metaphor: a concrete image that expresses the idea without writing the script on screen\n- Key objects: three to six large readable paper groups\n- Audio implication: whether the beat benefits from paper slide, pop, press, tap, rustle, or snap SFX\n\nFor 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.\n\n## STEP 2: Gate 1 — Production Plan Document Approval\n\nBefore 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.\n\nThe production plan must include:\n\n### Brief\n\n- Topic or source line\n- Intended audience \u002F use context when known\n- Aspect ratio and duration assumptions\n- Tone and pacing\n- Visual style summary\n- Media approach, stated as: default collage SFX are kept or generated; BGM, voiceover\u002F口播, and subtitles are not added unless the user explicitly requests them\n- Optional add-on question when useful: ask whether the user wants voiceover narration\u002F口播, BGM, or subtitles, but keep them optional\n\n### Visual Metaphors\n\nFor each planned segment:\n\n- Core meaning\n- Emotion\n- One-sentence visual proposition\n- Three to six key objects\n- Suggested background color and accent colors\n- Expected assembly order\n- Expected collage SFX moments, such as slide, pop, press, tap, rustle, or snap\n\n### Script \u002F Visual Beat Track\n\nIf the user explicitly requests narration, write a concise voiceover script. If the user has not explicitly requested narration, do **not** write a voiceover script; instead write a silent visual beat track explaining what the audience understands from the sequence.\n\nIf the user only needs B-roll for an existing line, preserve the original line as context instead of inventing narration.\n\n### Storyboard\n\nFor each segment, include:\n\n- Segment title\n- Final-frame description\n- Motion idea\n- Approximate duration\n- Collage SFX idea\n- Notes on style continuity and color harmony\n\nAfter 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.\n\n## STEP 3: Build Still-Frame Specifications\n\nAfter 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.\n\nInclude:\n\n- Script meaning or story beat\n- Visual metaphor\n- Aspect ratio\n- Background color field\n- Accent colors\n- Key object groups and their roles\n- Composition, foreground \u002F midground \u002F background depth, and negative space\n- Final frame relationship\n- Style continuity notes\n- Avoid list for this specific still\n\nUse this style signature:\n\n```text\nflat 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\n```\n\nColor guidance:\n\n- Burnt orange or red: labor, time pressure, urgency\n- Mustard yellow: tools, warning, accumulated errors\n- Ink green: cognition, reset, judgment, surreal calm\n- Deep purple: memory, structure, mystery, dream logic\n- Teal: collaboration, execution, system flow\n- Rose red: absurdity, ceremony, theatrical tension\n\nDo 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.\n\n## STEP 4: Gate 2 — Generate and Approve Still Frames\n\nGenerate one final still frame per approved segment. The still must look like the completed last frame of the future animation.\n\nStill-frame requirements:\n\n- Use the user-specified aspect ratio; otherwise default to 16:9 landscape\n- Flat bold paper background with subtle fiber texture\n- Three to six large separable object groups, unless the approved storyboard requires slightly more\n- Clear central subject, strong visual hierarchy, generous clean negative space, and visible foreground \u002F midground \u002F background layering\n- Black-and-white halftone photographic cut-outs as the main structure, combined with rich but readable scene props that support the story beat\n- Selective colored cardstock accents only where they clarify hierarchy\n- Warm cream keylines, soft physical paper shadows, refined torn edges, and subtle layered paper seams\n- No readable text, fake letters, numerals, subtitles, UI, watermark, or logos unless explicitly requested\n\nShow 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\u002Fbrown paper texture, revise the still before video generation.\n\n## STEP 5: Plan the Stop-Motion Assembly\n\nFor each approved still frame, prepare a motion plan that treats the approved still as the completed final frame.\n\nDefault motion order:\n\n1. Start from a clean paper color field matching the approved still's main background, not a mismatched kraft-paper or brown base.\n2. Base structure appears as paper pieces that slide, pop, or press into place.\n3. Character, card, object, or main metaphor element enters.\n4. Secondary objects assemble one by one with small bounce, press-flat, and pause beats.\n5. Final relationship locks into the approved composition.\n6. Hold the completed still-like frame briefly at the end.\n\nMotion prompt guidance:\n\n```text\nPaper-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\u002Fyellowed 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.\n```\n\n## STEP 6: Generate Collage-SFX B-roll Clips\n\nAfter Gate 2 approval, generate one video clip per approved still frame.\n\nGeneration requirements:\n\n- Use the approved still as the visual reference \u002F final-frame anchor whenever the selected Hub video model supports it\n- Use the same ratio as the still frame\n- Target about four seconds unless the user requested a different length\n- Generate or preserve tactile collage SFX by default when supported: paper slide, pop, press-flat tap, light rustle, tiny snap\n- Default: do not generate or add BGM unless the user explicitly requested music\n- Default: do not generate or add voiceover, spoken narration, or presenter audio unless the user explicitly requested narration\u002F口播\n- If a generated clip contains useful collage SFX, preserve it during post-production and final assembly\n- If a generated clip contains unwanted speech, music, fake UI sound, or noisy ambience, remove or regenerate the audio according to the user goal\n- Keep the shot visually stable; do not add camera movement unless the user asks\n- Preserve the collage material language, final composition, and established batch style\n- When revising later clips, use the best approved previous clips as style\u002Fcadence references if helpful\n\nUse `MiniMax-H3` as the default video generation model for this Skill. Do not ask the user to choose a model unless `MiniMax-H3` 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.\n\n## STEP 7: Quality Review\n\nReview stills and clips against these standards:\n\n- The metaphor or story beat is understandable without writing it on screen\n- The still has a strong clean color field, attractive 16:9 composition by default, clear object hierarchy, and visible foreground \u002F midground \u002F background depth\n- The number of object groups stays readable, not a screen full of fragments\n- The clip begins from a color field matching the approved still or batch palette\n- The assembly is visible piece by piece, not a global fade-in\n- Motion reads as stop-motion collage: separate paper groups pop in or slide in, lightly bounce, press flat, pause, and lock\n- Defaults: tactile collage SFX are desirable; BGM, voiceover\u002F口播, and subtitles are absent unless explicitly requested\n- Paper texture is controlled: not too flat, not over-aged, not brown\u002Fkraft unless approved\n- Color tone is consistent across the batch\n- The final frame remains close to the approved still\n- There are no unwanted readable letters, fake UI, subtitles, watermark, or logos\n\nMinor 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\u002Fdirty paper texture, lost stop-motion assembly, unwanted BGM, or unwanted voiceover should be regenerated or post-processed depending on where the issue appears.\n\n## STEP 8: Optional Assembly, Music, Narration, and Delivery\n\nIf 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.\n\nAdd BGM, narration\u002F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.\n\nFor each completed item, deliver:\n\n- Final B-roll video path or final assembled video path\n- Approved still frame path when relevant\n- A one-sentence explanation of how the script or visual beat became a visual metaphor\n- Media note: collage SFX by default, and list any explicitly requested BGM, narration\u002F口播, or subtitle additions\n- Any QA caveat if a clip passed with minor acceptable drift\n\nFor batch work, group the outputs by item number and keep the user's original line or story beat attached to its result.\n\n## Failure Handling\n\n- If the production plan defaults to silent video, correct it to collage SFX only unless the user explicitly asked for silence.\n- If the production plan includes BGM, voiceover\u002F口播, or subtitles without explicit user request, remove them and present BGM, voiceover\u002F口播, and subtitles as optional choices.\n- If the production plan feels too literal, return to Gate 1 and make the visual proposition more object-driven.\n- 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.\n- If the still or clip is too visually busy, reduce paper layers, simplify the object count, and restore negative space.\n- If the video lacks assembly motion, reduce the number of objects and make the step-by-step arrival order more explicit.\n- If motion feels like smooth digital layers, rewrite the prompt around stop-motion beats: appear → light bounce → press flat → pause → lock.\n- If the paper looks too flat, add subtle torn edges, fiber texture, layered seams, and soft shadows.\n- If the paper looks over-aged or dirty, remove kraft-paper, brown\u002Fyellowed base, heavy wrinkles, stains, and distressed treatment.\n- If the opening color clashes with the approved still, start from the same main background color as the still.\n- If the final frame drifts too far from the still, strengthen the instruction that the approved still is the completed final composition.\n- 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\u002Fpost-sync SFX.\n- If generated audio contains unwanted BGM or voiceover, remove or regenerate it before final delivery.\n- If precise layer control is required, recommend a layered animation or editing workflow instead of continuing this Skill.\n",{"data":40,"body":51},{"name":4,"description":6,"trigger-words":41,"exported-by":50},[42,43,44,45,46,47,48,49],"paper collage explainer","paper-collage animation","halftone collage","collage explainer","纸拼贴","拼贴科普","定格拼贴","拼贴动画","MiniMax-hub",{"type":52,"children":53},"root",[54,62,68,73,80,85,120,125,148,154,159,226,232,245,305,311,316,389,395,400,433,438,444,449,454,461,499,505,510,548,554,566,571,577,582,615,620,626,631,636,689,694,706,711,744,749,755,760,765,808,813,819,824,829,862,867,876,882,887,892,950,969,975,980,1038,1043,1049,1054,1059,1064,1092,1097,1103],{"type":55,"tag":56,"props":57,"children":58},"element","h1",{"id":4},[59],{"type":60,"value":61},"text","Paper Collage Explainer Generator",{"type":55,"tag":63,"props":64,"children":65},"p",{},[66],{"type":60,"value":67},"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":55,"tag":63,"props":69,"children":70},{},[71],{"type":60,"value":72},"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":55,"tag":74,"props":75,"children":77},"h2",{"id":76},"when-to-use",[78],{"type":60,"value":79},"When to Use",{"type":55,"tag":63,"props":81,"children":82},{},[83],{"type":60,"value":84},"Use this Skill when the user wants:",{"type":55,"tag":86,"props":87,"children":88},"ul",{},[89,95,100,105,110,115],{"type":55,"tag":90,"props":91,"children":92},"li",{},[93],{"type":60,"value":94},"A short script line turned into a visual-metaphor collage animation",{"type":55,"tag":90,"props":96,"children":97},{},[98],{"type":60,"value":99},"A simple story or literary topic explained through collage B-roll",{"type":55,"tag":90,"props":101,"children":102},{},[103],{"type":60,"value":104},"Editorial paper-collage animation for narration or social video",{"type":55,"tag":90,"props":106,"children":107},{},[108],{"type":60,"value":109},"Halftone collage animation with objects assembling from an empty color field",{"type":55,"tag":90,"props":111,"children":112},{},[113],{"type":60,"value":114},"A batch of short abstract sentences or story beats converted into separate visual-metaphor animation clips",{"type":55,"tag":90,"props":116,"children":117},{},[118],{"type":60,"value":119},"A tactile knowledge explainer that may include paper clicks, pops, slides, presses, and rustles but not automatic music or voiceover",{"type":55,"tag":63,"props":121,"children":122},{},[123],{"type":60,"value":124},"Do not use this Skill when the user needs:",{"type":55,"tag":86,"props":126,"children":127},{},[128,133,138,143],{"type":55,"tag":90,"props":129,"children":130},{},[131],{"type":60,"value":132},"A realistic product ad or presenter-led video",{"type":55,"tag":90,"props":134,"children":135},{},[136],{"type":60,"value":137},"Precise editable layers, timeline keyframes, or transparent cut-out assets",{"type":55,"tag":90,"props":139,"children":140},{},[141],{"type":60,"value":142},"Exact logo placement or readable typography",{"type":55,"tag":90,"props":144,"children":145},{},[146],{"type":60,"value":147},"Only a written video prompt without generation",{"type":55,"tag":74,"props":149,"children":151},{"id":150},"default-creative-targets",[152],{"type":60,"value":153},"Default Creative Targets",{"type":55,"tag":63,"props":155,"children":156},{},[157],{"type":60,"value":158},"Unless the user specifies otherwise:",{"type":55,"tag":86,"props":160,"children":161},{},[162,167,172,177,182,187,192,197,202,216,221],{"type":55,"tag":90,"props":163,"children":164},{},[165],{"type":60,"value":166},"Output ratio: 16:9 landscape",{"type":55,"tag":90,"props":168,"children":169},{},[170],{"type":60,"value":171},"Clip length: about 4 seconds per segment",{"type":55,"tag":90,"props":173,"children":174},{},[175],{"type":60,"value":176},"Audio default: keep or generate tactile paper-collage sound effects only, such as paper slide, pop, press, light rustle, and soft tap sounds",{"type":55,"tag":90,"props":178,"children":179},{},[180],{"type":60,"value":181},"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",{"type":55,"tag":90,"props":183,"children":184},{},[185],{"type":60,"value":186},"Default: do not add voiceover, spoken narration, or presenter narration. You may ask whether the user wants narration\u002F口播 when the project may benefit, but write, synthesize, or add spoken audio only after explicit user confirmation",{"type":55,"tag":90,"props":188,"children":189},{},[190],{"type":60,"value":191},"Default: do not add subtitles. You may ask whether the user wants subtitles, but create or burn in subtitles only after explicit user confirmation",{"type":55,"tag":90,"props":193,"children":194},{},[195],{"type":60,"value":196},"Visual style: premium editorial halftone paper collage",{"type":55,"tag":90,"props":198,"children":199},{},[200],{"type":60,"value":201},"Motion style: tactile stop-motion assembly, not slow zoom, generic drifting, or smooth digital layer movement",{"type":55,"tag":90,"props":203,"children":204},{},[205,207,214],{"type":60,"value":206},"Default video generation model: ",{"type":55,"tag":208,"props":209,"children":211},"code",{"className":210},[],[212],{"type":60,"value":213},"MiniMax-H3",{"type":60,"value":215},", unless the user explicitly specifies another model, the model is unavailable, or a hard capability requirement excludes it",{"type":55,"tag":90,"props":217,"children":218},{},[219],{"type":60,"value":220},"Text in image\u002Fvideo: avoid readable letters, numerals, UI, subtitles, watermark, and logos",{"type":55,"tag":90,"props":222,"children":223},{},[224],{"type":60,"value":225},"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":55,"tag":74,"props":227,"children":229},{"id":228},"audio-policy",[230],{"type":60,"value":231},"Audio Policy",{"type":55,"tag":63,"props":233,"children":234},{},[235,237,243],{"type":60,"value":236},"This Skill's default delivery is ",{"type":55,"tag":238,"props":239,"children":240},"strong",{},[241],{"type":60,"value":242},"with collage SFX, and without BGM, voiceover, or subtitles",{"type":60,"value":244},".",{"type":55,"tag":246,"props":247,"children":248},"ol",{},[249,254,280,285,290,295,300],{"type":55,"tag":90,"props":250,"children":251},{},[252],{"type":60,"value":253},"During the first production-plan confirmation, state the default media approach explicitly: tactile paper-collage sound effects are kept or generated; BGM, voiceover\u002F口播, and subtitles are not added by default.",{"type":55,"tag":90,"props":255,"children":256},{},[257,259,264,266,271,273,278],{"type":60,"value":258},"It is acceptable to ask the user whether they want ",{"type":55,"tag":238,"props":260,"children":261},{},[262],{"type":60,"value":263},"voiceover narration\u002F口播",{"type":60,"value":265},", ",{"type":55,"tag":238,"props":267,"children":268},{},[269],{"type":60,"value":270},"BGM",{"type":60,"value":272},", or ",{"type":55,"tag":238,"props":274,"children":275},{},[276],{"type":60,"value":277},"subtitles",{"type":60,"value":279},", especially for explainers, but present all three as optional add-ons, not defaults.",{"type":55,"tag":90,"props":281,"children":282},{},[283],{"type":60,"value":284},"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.",{"type":55,"tag":90,"props":286,"children":287},{},[288],{"type":60,"value":289},"Do not infer that a social video automatically needs BGM or subtitles. If the user does not choose them, keep the clip SFX only.",{"type":55,"tag":90,"props":291,"children":292},{},[293],{"type":60,"value":294},"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.",{"type":55,"tag":90,"props":296,"children":297},{},[298],{"type":60,"value":299},"During final assembly, preserve the original clip audio tracks when they contain collage SFX. Do not drop audio by default.",{"type":55,"tag":90,"props":301,"children":302},{},[303],{"type":60,"value":304},"Remove or replace audio only when the user asked for silence, when the generated audio contains unwanted speech\u002Fmusic, or when the user requests a separate music\u002Fnarration mix. Create subtitles only when the user explicitly asks for them.",{"type":55,"tag":74,"props":306,"children":308},{"id":307},"global-style-rules",[309],{"type":60,"value":310},"Global Style Rules",{"type":55,"tag":63,"props":312,"children":313},{},[314],{"type":60,"value":315},"Apply these rules to every still and video in the project:",{"type":55,"tag":246,"props":317,"children":318},{},[319,329,339,349,359,369,379],{"type":55,"tag":90,"props":320,"children":321},{},[322,327],{"type":55,"tag":238,"props":323,"children":324},{},[325],{"type":60,"value":326},"Unify the overall visual style.",{"type":60,"value":328}," 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.",{"type":55,"tag":90,"props":330,"children":331},{},[332,337],{"type":55,"tag":238,"props":333,"children":334},{},[335],{"type":60,"value":336},"Control the paper texture intensity.",{"type":60,"value":338}," 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.",{"type":55,"tag":90,"props":340,"children":341},{},[342,347],{"type":55,"tag":238,"props":343,"children":344},{},[345],{"type":60,"value":346},"Unify the color tone.",{"type":60,"value":348}," 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.",{"type":55,"tag":90,"props":350,"children":351},{},[352,357],{"type":55,"tag":238,"props":353,"children":354},{},[355],{"type":60,"value":356},"Make motion read as stop-motion collage.",{"type":60,"value":358}," 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.",{"type":55,"tag":90,"props":360,"children":361},{},[362,367],{"type":55,"tag":238,"props":363,"children":364},{},[365],{"type":60,"value":366},"Keep segments coordinated.",{"type":60,"value":368}," 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.",{"type":55,"tag":90,"props":370,"children":371},{},[372,377],{"type":55,"tag":238,"props":373,"children":374},{},[375],{"type":60,"value":376},"Default to polished 16:9 layered scenes.",{"type":60,"value":378}," Unless the user explicitly requests another platform frame, plan and generate in 16:9 landscape. Use the wider canvas to build attractive foreground \u002F midground \u002F background separation, richer environment props, clear subject hierarchy, and cinematic lateral composition without turning the frame into clutter.",{"type":55,"tag":90,"props":380,"children":381},{},[382,387],{"type":55,"tag":238,"props":383,"children":384},{},[385],{"type":60,"value":386},"Emphasize paper-collage craft.",{"type":60,"value":388}," 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":55,"tag":74,"props":390,"children":392},{"id":391},"step-1-parse-the-input",[393],{"type":60,"value":394},"STEP 1: Parse the Input",{"type":55,"tag":63,"props":396,"children":397},{},[398],{"type":60,"value":399},"For each line, concept, story, or topic, extract:",{"type":55,"tag":86,"props":401,"children":402},{},[403,408,413,418,423,428],{"type":55,"tag":90,"props":404,"children":405},{},[406],{"type":60,"value":407},"Core meaning: what the viewer should understand",{"type":55,"tag":90,"props":409,"children":410},{},[411],{"type":60,"value":412},"Emotion: calm, urgent, ironic, surprising, absurd, clarifying, reflective, mysterious, or playful",{"type":55,"tag":90,"props":414,"children":415},{},[416],{"type":60,"value":417},"Action verb: open, connect, leak, archive, compress, split, illuminate, bind, assemble, reveal, fall, chase, transform, collide",{"type":55,"tag":90,"props":419,"children":420},{},[421],{"type":60,"value":422},"Visual metaphor: a concrete image that expresses the idea without writing the script on screen",{"type":55,"tag":90,"props":424,"children":425},{},[426],{"type":60,"value":427},"Key objects: three to six large readable paper groups",{"type":55,"tag":90,"props":429,"children":430},{},[431],{"type":60,"value":432},"Audio implication: whether the beat benefits from paper slide, pop, press, tap, rustle, or snap SFX",{"type":55,"tag":63,"props":434,"children":435},{},[436],{"type":60,"value":437},"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":55,"tag":74,"props":439,"children":441},{"id":440},"step-2-gate-1-production-plan-document-approval",[442],{"type":60,"value":443},"STEP 2: Gate 1 — Production Plan Document Approval",{"type":55,"tag":63,"props":445,"children":446},{},[447],{"type":60,"value":448},"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":55,"tag":63,"props":450,"children":451},{},[452],{"type":60,"value":453},"The production plan must include:",{"type":55,"tag":455,"props":456,"children":458},"h3",{"id":457},"brief",[459],{"type":60,"value":460},"Brief",{"type":55,"tag":86,"props":462,"children":463},{},[464,469,474,479,484,489,494],{"type":55,"tag":90,"props":465,"children":466},{},[467],{"type":60,"value":468},"Topic or source line",{"type":55,"tag":90,"props":470,"children":471},{},[472],{"type":60,"value":473},"Intended audience \u002F use context when known",{"type":55,"tag":90,"props":475,"children":476},{},[477],{"type":60,"value":478},"Aspect ratio and duration assumptions",{"type":55,"tag":90,"props":480,"children":481},{},[482],{"type":60,"value":483},"Tone and pacing",{"type":55,"tag":90,"props":485,"children":486},{},[487],{"type":60,"value":488},"Visual style summary",{"type":55,"tag":90,"props":490,"children":491},{},[492],{"type":60,"value":493},"Media approach, stated as: default collage SFX are kept or generated; BGM, voiceover\u002F口播, and subtitles are not added unless the user explicitly requests them",{"type":55,"tag":90,"props":495,"children":496},{},[497],{"type":60,"value":498},"Optional add-on question when useful: ask whether the user wants voiceover narration\u002F口播, BGM, or subtitles, but keep them optional",{"type":55,"tag":455,"props":500,"children":502},{"id":501},"visual-metaphors",[503],{"type":60,"value":504},"Visual Metaphors",{"type":55,"tag":63,"props":506,"children":507},{},[508],{"type":60,"value":509},"For each planned segment:",{"type":55,"tag":86,"props":511,"children":512},{},[513,518,523,528,533,538,543],{"type":55,"tag":90,"props":514,"children":515},{},[516],{"type":60,"value":517},"Core meaning",{"type":55,"tag":90,"props":519,"children":520},{},[521],{"type":60,"value":522},"Emotion",{"type":55,"tag":90,"props":524,"children":525},{},[526],{"type":60,"value":527},"One-sentence visual proposition",{"type":55,"tag":90,"props":529,"children":530},{},[531],{"type":60,"value":532},"Three to six key objects",{"type":55,"tag":90,"props":534,"children":535},{},[536],{"type":60,"value":537},"Suggested background color and accent colors",{"type":55,"tag":90,"props":539,"children":540},{},[541],{"type":60,"value":542},"Expected assembly order",{"type":55,"tag":90,"props":544,"children":545},{},[546],{"type":60,"value":547},"Expected collage SFX moments, such as slide, pop, press, tap, rustle, or snap",{"type":55,"tag":455,"props":549,"children":551},{"id":550},"script-visual-beat-track",[552],{"type":60,"value":553},"Script \u002F Visual Beat Track",{"type":55,"tag":63,"props":555,"children":556},{},[557,559,564],{"type":60,"value":558},"If the user explicitly requests narration, write a concise voiceover script. If the user has not explicitly requested narration, do ",{"type":55,"tag":238,"props":560,"children":561},{},[562],{"type":60,"value":563},"not",{"type":60,"value":565}," write a voiceover script; instead write a silent visual beat track explaining what the audience understands from the sequence.",{"type":55,"tag":63,"props":567,"children":568},{},[569],{"type":60,"value":570},"If the user only needs B-roll for an existing line, preserve the original line as context instead of inventing narration.",{"type":55,"tag":455,"props":572,"children":574},{"id":573},"storyboard",[575],{"type":60,"value":576},"Storyboard",{"type":55,"tag":63,"props":578,"children":579},{},[580],{"type":60,"value":581},"For each segment, include:",{"type":55,"tag":86,"props":583,"children":584},{},[585,590,595,600,605,610],{"type":55,"tag":90,"props":586,"children":587},{},[588],{"type":60,"value":589},"Segment title",{"type":55,"tag":90,"props":591,"children":592},{},[593],{"type":60,"value":594},"Final-frame description",{"type":55,"tag":90,"props":596,"children":597},{},[598],{"type":60,"value":599},"Motion idea",{"type":55,"tag":90,"props":601,"children":602},{},[603],{"type":60,"value":604},"Approximate duration",{"type":55,"tag":90,"props":606,"children":607},{},[608],{"type":60,"value":609},"Collage SFX idea",{"type":55,"tag":90,"props":611,"children":612},{},[613],{"type":60,"value":614},"Notes on style continuity and color harmony",{"type":55,"tag":63,"props":616,"children":617},{},[618],{"type":60,"value":619},"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":55,"tag":74,"props":621,"children":623},{"id":622},"step-3-build-still-frame-specifications",[624],{"type":60,"value":625},"STEP 3: Build Still-Frame Specifications",{"type":55,"tag":63,"props":627,"children":628},{},[629],{"type":60,"value":630},"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":55,"tag":63,"props":632,"children":633},{},[634],{"type":60,"value":635},"Include:",{"type":55,"tag":86,"props":637,"children":638},{},[639,644,649,654,659,664,669,674,679,684],{"type":55,"tag":90,"props":640,"children":641},{},[642],{"type":60,"value":643},"Script meaning or story beat",{"type":55,"tag":90,"props":645,"children":646},{},[647],{"type":60,"value":648},"Visual metaphor",{"type":55,"tag":90,"props":650,"children":651},{},[652],{"type":60,"value":653},"Aspect ratio",{"type":55,"tag":90,"props":655,"children":656},{},[657],{"type":60,"value":658},"Background color field",{"type":55,"tag":90,"props":660,"children":661},{},[662],{"type":60,"value":663},"Accent colors",{"type":55,"tag":90,"props":665,"children":666},{},[667],{"type":60,"value":668},"Key object groups and their roles",{"type":55,"tag":90,"props":670,"children":671},{},[672],{"type":60,"value":673},"Composition, foreground \u002F midground \u002F background depth, and negative space",{"type":55,"tag":90,"props":675,"children":676},{},[677],{"type":60,"value":678},"Final frame relationship",{"type":55,"tag":90,"props":680,"children":681},{},[682],{"type":60,"value":683},"Style continuity notes",{"type":55,"tag":90,"props":685,"children":686},{},[687],{"type":60,"value":688},"Avoid list for this specific still",{"type":55,"tag":63,"props":690,"children":691},{},[692],{"type":60,"value":693},"Use this style signature:",{"type":55,"tag":695,"props":696,"children":701},"pre",{"className":697,"code":699,"language":60,"meta":700},[698],"language-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\n","",[702],{"type":55,"tag":208,"props":703,"children":704},{"__ignoreMap":700},[705],{"type":60,"value":699},{"type":55,"tag":63,"props":707,"children":708},{},[709],{"type":60,"value":710},"Color guidance:",{"type":55,"tag":86,"props":712,"children":713},{},[714,719,724,729,734,739],{"type":55,"tag":90,"props":715,"children":716},{},[717],{"type":60,"value":718},"Burnt orange or red: labor, time pressure, urgency",{"type":55,"tag":90,"props":720,"children":721},{},[722],{"type":60,"value":723},"Mustard yellow: tools, warning, accumulated errors",{"type":55,"tag":90,"props":725,"children":726},{},[727],{"type":60,"value":728},"Ink green: cognition, reset, judgment, surreal calm",{"type":55,"tag":90,"props":730,"children":731},{},[732],{"type":60,"value":733},"Deep purple: memory, structure, mystery, dream logic",{"type":55,"tag":90,"props":735,"children":736},{},[737],{"type":60,"value":738},"Teal: collaboration, execution, system flow",{"type":55,"tag":90,"props":740,"children":741},{},[742],{"type":60,"value":743},"Rose red: absurdity, ceremony, theatrical tension",{"type":55,"tag":63,"props":745,"children":746},{},[747],{"type":60,"value":748},"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":55,"tag":74,"props":750,"children":752},{"id":751},"step-4-gate-2-generate-and-approve-still-frames",[753],{"type":60,"value":754},"STEP 4: Gate 2 — Generate and Approve Still Frames",{"type":55,"tag":63,"props":756,"children":757},{},[758],{"type":60,"value":759},"Generate one final still frame per approved segment. The still must look like the completed last frame of the future animation.",{"type":55,"tag":63,"props":761,"children":762},{},[763],{"type":60,"value":764},"Still-frame requirements:",{"type":55,"tag":86,"props":766,"children":767},{},[768,773,778,783,788,793,798,803],{"type":55,"tag":90,"props":769,"children":770},{},[771],{"type":60,"value":772},"Use the user-specified aspect ratio; otherwise default to 16:9 landscape",{"type":55,"tag":90,"props":774,"children":775},{},[776],{"type":60,"value":777},"Flat bold paper background with subtle fiber texture",{"type":55,"tag":90,"props":779,"children":780},{},[781],{"type":60,"value":782},"Three to six large separable object groups, unless the approved storyboard requires slightly more",{"type":55,"tag":90,"props":784,"children":785},{},[786],{"type":60,"value":787},"Clear central subject, strong visual hierarchy, generous clean negative space, and visible foreground \u002F midground \u002F background layering",{"type":55,"tag":90,"props":789,"children":790},{},[791],{"type":60,"value":792},"Black-and-white halftone photographic cut-outs as the main structure, combined with rich but readable scene props that support the story beat",{"type":55,"tag":90,"props":794,"children":795},{},[796],{"type":60,"value":797},"Selective colored cardstock accents only where they clarify hierarchy",{"type":55,"tag":90,"props":799,"children":800},{},[801],{"type":60,"value":802},"Warm cream keylines, soft physical paper shadows, refined torn edges, and subtle layered paper seams",{"type":55,"tag":90,"props":804,"children":805},{},[806],{"type":60,"value":807},"No readable text, fake letters, numerals, subtitles, UI, watermark, or logos unless explicitly requested",{"type":55,"tag":63,"props":809,"children":810},{},[811],{"type":60,"value":812},"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\u002Fbrown paper texture, revise the still before video generation.",{"type":55,"tag":74,"props":814,"children":816},{"id":815},"step-5-plan-the-stop-motion-assembly",[817],{"type":60,"value":818},"STEP 5: Plan the Stop-Motion Assembly",{"type":55,"tag":63,"props":820,"children":821},{},[822],{"type":60,"value":823},"For each approved still frame, prepare a motion plan that treats the approved still as the completed final frame.",{"type":55,"tag":63,"props":825,"children":826},{},[827],{"type":60,"value":828},"Default motion order:",{"type":55,"tag":246,"props":830,"children":831},{},[832,837,842,847,852,857],{"type":55,"tag":90,"props":833,"children":834},{},[835],{"type":60,"value":836},"Start from a clean paper color field matching the approved still's main background, not a mismatched kraft-paper or brown base.",{"type":55,"tag":90,"props":838,"children":839},{},[840],{"type":60,"value":841},"Base structure appears as paper pieces that slide, pop, or press into place.",{"type":55,"tag":90,"props":843,"children":844},{},[845],{"type":60,"value":846},"Character, card, object, or main metaphor element enters.",{"type":55,"tag":90,"props":848,"children":849},{},[850],{"type":60,"value":851},"Secondary objects assemble one by one with small bounce, press-flat, and pause beats.",{"type":55,"tag":90,"props":853,"children":854},{},[855],{"type":60,"value":856},"Final relationship locks into the approved composition.",{"type":55,"tag":90,"props":858,"children":859},{},[860],{"type":60,"value":861},"Hold the completed still-like frame briefly at the end.",{"type":55,"tag":63,"props":863,"children":864},{},[865],{"type":60,"value":866},"Motion prompt guidance:",{"type":55,"tag":695,"props":868,"children":871},{"className":869,"code":870,"language":60,"meta":700},[698],"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\u002Fyellowed 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.\n",[872],{"type":55,"tag":208,"props":873,"children":874},{"__ignoreMap":700},[875],{"type":60,"value":870},{"type":55,"tag":74,"props":877,"children":879},{"id":878},"step-6-generate-collage-sfx-b-roll-clips",[880],{"type":60,"value":881},"STEP 6: Generate Collage-SFX B-roll Clips",{"type":55,"tag":63,"props":883,"children":884},{},[885],{"type":60,"value":886},"After Gate 2 approval, generate one video clip per approved still frame.",{"type":55,"tag":63,"props":888,"children":889},{},[890],{"type":60,"value":891},"Generation requirements:",{"type":55,"tag":86,"props":893,"children":894},{},[895,900,905,910,915,920,925,930,935,940,945],{"type":55,"tag":90,"props":896,"children":897},{},[898],{"type":60,"value":899},"Use the approved still as the visual reference \u002F final-frame anchor whenever the selected Hub video model supports it",{"type":55,"tag":90,"props":901,"children":902},{},[903],{"type":60,"value":904},"Use the same ratio as the still frame",{"type":55,"tag":90,"props":906,"children":907},{},[908],{"type":60,"value":909},"Target about four seconds unless the user requested a different length",{"type":55,"tag":90,"props":911,"children":912},{},[913],{"type":60,"value":914},"Generate or preserve tactile collage SFX by default when supported: paper slide, pop, press-flat tap, light rustle, tiny snap",{"type":55,"tag":90,"props":916,"children":917},{},[918],{"type":60,"value":919},"Default: do not generate or add BGM unless the user explicitly requested music",{"type":55,"tag":90,"props":921,"children":922},{},[923],{"type":60,"value":924},"Default: do not generate or add voiceover, spoken narration, or presenter audio unless the user explicitly requested narration\u002F口播",{"type":55,"tag":90,"props":926,"children":927},{},[928],{"type":60,"value":929},"If a generated clip contains useful collage SFX, preserve it during post-production and final assembly",{"type":55,"tag":90,"props":931,"children":932},{},[933],{"type":60,"value":934},"If a generated clip contains unwanted speech, music, fake UI sound, or noisy ambience, remove or regenerate the audio according to the user goal",{"type":55,"tag":90,"props":936,"children":937},{},[938],{"type":60,"value":939},"Keep the shot visually stable; do not add camera movement unless the user asks",{"type":55,"tag":90,"props":941,"children":942},{},[943],{"type":60,"value":944},"Preserve the collage material language, final composition, and established batch style",{"type":55,"tag":90,"props":946,"children":947},{},[948],{"type":60,"value":949},"When revising later clips, use the best approved previous clips as style\u002Fcadence references if helpful",{"type":55,"tag":63,"props":951,"children":952},{},[953,955,960,962,967],{"type":60,"value":954},"Use ",{"type":55,"tag":208,"props":956,"children":958},{"className":957},[],[959],{"type":60,"value":213},{"type":60,"value":961}," as the default video generation model for this Skill. Do not ask the user to choose a model unless ",{"type":55,"tag":208,"props":963,"children":965},{"className":964},[],[966],{"type":60,"value":213},{"type":60,"value":968}," 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":55,"tag":74,"props":970,"children":972},{"id":971},"step-7-quality-review",[973],{"type":60,"value":974},"STEP 7: Quality Review",{"type":55,"tag":63,"props":976,"children":977},{},[978],{"type":60,"value":979},"Review stills and clips against these standards:",{"type":55,"tag":86,"props":981,"children":982},{},[983,988,993,998,1003,1008,1013,1018,1023,1028,1033],{"type":55,"tag":90,"props":984,"children":985},{},[986],{"type":60,"value":987},"The metaphor or story beat is understandable without writing it on screen",{"type":55,"tag":90,"props":989,"children":990},{},[991],{"type":60,"value":992},"The still has a strong clean color field, attractive 16:9 composition by default, clear object hierarchy, and visible foreground \u002F midground \u002F background depth",{"type":55,"tag":90,"props":994,"children":995},{},[996],{"type":60,"value":997},"The number of object groups stays readable, not a screen full of fragments",{"type":55,"tag":90,"props":999,"children":1000},{},[1001],{"type":60,"value":1002},"The clip begins from a color field matching the approved still or batch palette",{"type":55,"tag":90,"props":1004,"children":1005},{},[1006],{"type":60,"value":1007},"The assembly is visible piece by piece, not a global fade-in",{"type":55,"tag":90,"props":1009,"children":1010},{},[1011],{"type":60,"value":1012},"Motion reads as stop-motion collage: separate paper groups pop in or slide in, lightly bounce, press flat, pause, and lock",{"type":55,"tag":90,"props":1014,"children":1015},{},[1016],{"type":60,"value":1017},"Defaults: tactile collage SFX are desirable; BGM, voiceover\u002F口播, and subtitles are absent unless explicitly requested",{"type":55,"tag":90,"props":1019,"children":1020},{},[1021],{"type":60,"value":1022},"Paper texture is controlled: not too flat, not over-aged, not brown\u002Fkraft unless approved",{"type":55,"tag":90,"props":1024,"children":1025},{},[1026],{"type":60,"value":1027},"Color tone is consistent across the batch",{"type":55,"tag":90,"props":1029,"children":1030},{},[1031],{"type":60,"value":1032},"The final frame remains close to the approved still",{"type":55,"tag":90,"props":1034,"children":1035},{},[1036],{"type":60,"value":1037},"There are no unwanted readable letters, fake UI, subtitles, watermark, or logos",{"type":55,"tag":63,"props":1039,"children":1040},{},[1041],{"type":60,"value":1042},"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\u002Fdirty paper texture, lost stop-motion assembly, unwanted BGM, or unwanted voiceover should be regenerated or post-processed depending on where the issue appears.",{"type":55,"tag":74,"props":1044,"children":1046},{"id":1045},"step-8-optional-assembly-music-narration-and-delivery",[1047],{"type":60,"value":1048},"STEP 8: Optional Assembly, Music, Narration, and Delivery",{"type":55,"tag":63,"props":1050,"children":1051},{},[1052],{"type":60,"value":1053},"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":55,"tag":63,"props":1055,"children":1056},{},[1057],{"type":60,"value":1058},"Add BGM, narration\u002F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":55,"tag":63,"props":1060,"children":1061},{},[1062],{"type":60,"value":1063},"For each completed item, deliver:",{"type":55,"tag":86,"props":1065,"children":1066},{},[1067,1072,1077,1082,1087],{"type":55,"tag":90,"props":1068,"children":1069},{},[1070],{"type":60,"value":1071},"Final B-roll video path or final assembled video path",{"type":55,"tag":90,"props":1073,"children":1074},{},[1075],{"type":60,"value":1076},"Approved still frame path when relevant",{"type":55,"tag":90,"props":1078,"children":1079},{},[1080],{"type":60,"value":1081},"A one-sentence explanation of how the script or visual beat became a visual metaphor",{"type":55,"tag":90,"props":1083,"children":1084},{},[1085],{"type":60,"value":1086},"Media note: collage SFX by default, and list any explicitly requested BGM, narration\u002F口播, or subtitle additions",{"type":55,"tag":90,"props":1088,"children":1089},{},[1090],{"type":60,"value":1091},"Any QA caveat if a clip passed with minor acceptable drift",{"type":55,"tag":63,"props":1093,"children":1094},{},[1095],{"type":60,"value":1096},"For batch work, group the outputs by item number and keep the user's original line or story beat attached to its result.",{"type":55,"tag":74,"props":1098,"children":1100},{"id":1099},"failure-handling",[1101],{"type":60,"value":1102},"Failure Handling",{"type":55,"tag":86,"props":1104,"children":1105},{},[1106,1111,1116,1121,1126,1131,1136,1141,1146,1151,1156,1161,1166,1171],{"type":55,"tag":90,"props":1107,"children":1108},{},[1109],{"type":60,"value":1110},"If the production plan defaults to silent video, correct it to collage SFX only unless the user explicitly asked for silence.",{"type":55,"tag":90,"props":1112,"children":1113},{},[1114],{"type":60,"value":1115},"If the production plan includes BGM, voiceover\u002F口播, or subtitles without explicit user request, remove them and present BGM, voiceover\u002F口播, and subtitles as optional choices.",{"type":55,"tag":90,"props":1117,"children":1118},{},[1119],{"type":60,"value":1120},"If the production plan feels too literal, return to Gate 1 and make the visual proposition more object-driven.",{"type":55,"tag":90,"props":1122,"children":1123},{},[1124],{"type":60,"value":1125},"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.",{"type":55,"tag":90,"props":1127,"children":1128},{},[1129],{"type":60,"value":1130},"If the still or clip is too visually busy, reduce paper layers, simplify the object count, and restore negative space.",{"type":55,"tag":90,"props":1132,"children":1133},{},[1134],{"type":60,"value":1135},"If the video lacks assembly motion, reduce the number of objects and make the step-by-step arrival order more explicit.",{"type":55,"tag":90,"props":1137,"children":1138},{},[1139],{"type":60,"value":1140},"If motion feels like smooth digital layers, rewrite the prompt around stop-motion beats: appear → light bounce → press flat → pause → lock.",{"type":55,"tag":90,"props":1142,"children":1143},{},[1144],{"type":60,"value":1145},"If the paper looks too flat, add subtle torn edges, fiber texture, layered seams, and soft shadows.",{"type":55,"tag":90,"props":1147,"children":1148},{},[1149],{"type":60,"value":1150},"If the paper looks over-aged or dirty, remove kraft-paper, brown\u002Fyellowed base, heavy wrinkles, stains, and distressed treatment.",{"type":55,"tag":90,"props":1152,"children":1153},{},[1154],{"type":60,"value":1155},"If the opening color clashes with the approved still, start from the same main background color as the still.",{"type":55,"tag":90,"props":1157,"children":1158},{},[1159],{"type":60,"value":1160},"If the final frame drifts too far from the still, strengthen the instruction that the approved still is the completed final composition.",{"type":55,"tag":90,"props":1162,"children":1163},{},[1164],{"type":60,"value":1165},"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\u002Fpost-sync SFX.",{"type":55,"tag":90,"props":1167,"children":1168},{},[1169],{"type":60,"value":1170},"If generated audio contains unwanted BGM or voiceover, remove or regenerate it before final delivery.",{"type":55,"tag":90,"props":1172,"children":1173},{},[1174],{"type":60,"value":1175},"If precise layer control is required, recommend a layered animation or editing workflow instead of continuing this Skill.",{"items":1177,"total":1374},[1178,1202,1216,1235,1250,1270,1286,1304,1319,1335,1354,1364],{"slug":1179,"name":1179,"fn":1180,"description":1181,"org":1182,"tags":1183,"stars":1199,"repoUrl":1200,"updatedAt":1201},"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},[1184,1187,1190,1193,1196],{"name":1185,"slug":1186,"type":16},"Accessibility","accessibility",{"name":1188,"slug":1189,"type":16},"Android","android",{"name":1191,"slug":1192,"type":16},"Kotlin","kotlin",{"name":1194,"slug":1195,"type":16},"Mobile","mobile",{"name":1197,"slug":1198,"type":16},"UI Components","ui-components",13030,"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002Fskills","2026-07-13T06:16:54.247834",{"slug":1203,"name":1203,"fn":1204,"description":1205,"org":1206,"tags":1207,"stars":1199,"repoUrl":1200,"updatedAt":1215},"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},[1208,1211,1214],{"name":1209,"slug":1210,"type":16},"Agents","agents",{"name":1212,"slug":1213,"type":16},"Audio","audio",{"name":14,"slug":15,"type":16},"2026-07-13T06:16:35.130644",{"slug":1217,"name":1217,"fn":1218,"description":1219,"org":1220,"tags":1221,"stars":1199,"repoUrl":1200,"updatedAt":1234},"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},[1222,1225,1228,1231],{"name":1223,"slug":1224,"type":16},"Design","design",{"name":1226,"slug":1227,"type":16},"Presentations","presentations",{"name":1229,"slug":1230,"type":16},"Themes","themes",{"name":1232,"slug":1233,"type":16},"Typography","typography","2026-07-13T06:17:02.785587",{"slug":1236,"name":1236,"fn":1237,"description":1238,"org":1239,"tags":1240,"stars":1199,"repoUrl":1200,"updatedAt":1249},"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},[1241,1242,1245,1248],{"name":1223,"slug":1224,"type":16},{"name":1243,"slug":1244,"type":16},"Design System","design-system",{"name":1246,"slug":1247,"type":16},"PowerPoint","powerpoint",{"name":1226,"slug":1227,"type":16},"2026-07-13T06:17:10.398389",{"slug":1251,"name":1251,"fn":1252,"description":1253,"org":1254,"tags":1255,"stars":1199,"repoUrl":1200,"updatedAt":1269},"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},[1256,1259,1262,1263,1266],{"name":1257,"slug":1258,"type":16},"Dart","dart",{"name":1260,"slug":1261,"type":16},"Flutter","flutter",{"name":1194,"slug":1195,"type":16},{"name":1264,"slug":1265,"type":16},"Performance","performance",{"name":1267,"slug":1268,"type":16},"State Management","state-management","2026-07-13T06:16:36.626679",{"slug":1271,"name":1271,"fn":1272,"description":1273,"org":1274,"tags":1275,"stars":1199,"repoUrl":1200,"updatedAt":1285},"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},[1276,1277,1278,1279,1282],{"name":24,"slug":25,"type":16},{"name":14,"slug":15,"type":16},{"name":1223,"slug":1224,"type":16},{"name":1280,"slug":1281,"type":16},"Frontend","frontend",{"name":1283,"slug":1284,"type":16},"Web Development","web-development","2026-07-13T06:16:39.108827",{"slug":1287,"name":1287,"fn":1288,"description":1289,"org":1290,"tags":1291,"stars":1199,"repoUrl":1200,"updatedAt":1303},"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},[1292,1295,1296,1299,1302],{"name":1293,"slug":1294,"type":16},"Backend","backend",{"name":1280,"slug":1281,"type":16},{"name":1297,"slug":1298,"type":16},"Full-stack","full-stack",{"name":1300,"slug":1301,"type":16},"REST API","rest-api",{"name":1283,"slug":1284,"type":16},"2026-07-13T06:16:43.219005",{"slug":1305,"name":1305,"fn":1306,"description":1307,"org":1308,"tags":1309,"stars":1199,"repoUrl":1200,"updatedAt":1318},"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},[1310,1311,1312,1315],{"name":24,"slug":25,"type":16},{"name":14,"slug":15,"type":16},{"name":1313,"slug":1314,"type":16},"Images","images",{"name":1316,"slug":1317,"type":16},"Media","media","2026-07-13T06:16:51.74461",{"slug":1320,"name":1320,"fn":1321,"description":1322,"org":1323,"tags":1324,"stars":1199,"repoUrl":1200,"updatedAt":1334},"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},[1325,1326,1329,1330,1333],{"name":1185,"slug":1186,"type":16},{"name":1327,"slug":1328,"type":16},"iOS","ios",{"name":1194,"slug":1195,"type":16},{"name":1331,"slug":1332,"type":16},"SwiftUI","swiftui",{"name":1197,"slug":1198,"type":16},"2026-07-13T06:16:55.686092",{"slug":1336,"name":1336,"fn":1337,"description":1338,"org":1339,"tags":1340,"stars":1199,"repoUrl":1200,"updatedAt":1353},"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},[1341,1344,1347,1350],{"name":1342,"slug":1343,"type":16},"Documents","documents",{"name":1345,"slug":1346,"type":16},"DOCX","docx",{"name":1348,"slug":1349,"type":16},"Office","office",{"name":1351,"slug":1352,"type":16},"Templates","templates","2026-07-13T06:16:40.461868",{"slug":1355,"name":1355,"fn":1356,"description":1357,"org":1358,"tags":1359,"stars":1199,"repoUrl":1200,"updatedAt":1363},"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},[1360,1361,1362],{"name":1212,"slug":1213,"type":16},{"name":14,"slug":15,"type":16},{"name":1316,"slug":1317,"type":16},"2026-07-13T06:16:50.381758",{"slug":1365,"name":1365,"fn":1366,"description":1367,"org":1368,"tags":1369,"stars":1199,"repoUrl":1200,"updatedAt":1373},"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},[1370,1371,1372],{"name":1212,"slug":1213,"type":16},{"name":14,"slug":15,"type":16},{"name":1316,"slug":1317,"type":16},"2026-07-13T06:16:57.002997",47,{"items":1376,"total":1468},[1377,1390,1405,1418,1433,1444,1457],{"slug":1378,"name":1378,"fn":1379,"description":1380,"org":1381,"tags":1382,"stars":29,"repoUrl":30,"updatedAt":1389},"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},[1383,1386,1387,1388],{"name":1384,"slug":1385,"type":16},"3D","3d",{"name":24,"slug":25,"type":16},{"name":14,"slug":15,"type":16},{"name":27,"slug":28,"type":16},"2026-08-08T04:19:20.46802",{"slug":1391,"name":1391,"fn":1392,"description":1393,"org":1394,"tags":1395,"stars":29,"repoUrl":30,"updatedAt":1404},"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},[1396,1399,1400,1403],{"name":1397,"slug":1398,"type":16},"Content Creation","content-creation",{"name":14,"slug":15,"type":16},{"name":1401,"slug":1402,"type":16},"Marketing","marketing",{"name":27,"slug":28,"type":16},"2026-08-08T04:19:08.155902",{"slug":1406,"name":1406,"fn":1407,"description":1408,"org":1409,"tags":1410,"stars":29,"repoUrl":30,"updatedAt":1417},"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},[1411,1412,1413,1414],{"name":24,"slug":25,"type":16},{"name":14,"slug":15,"type":16},{"name":1223,"slug":1224,"type":16},{"name":1415,"slug":1416,"type":16},"Game Development","game-development","2026-08-08T04:19:07.313539",{"slug":1419,"name":1419,"fn":1420,"description":1421,"org":1422,"tags":1423,"stars":29,"repoUrl":30,"updatedAt":1432},"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},[1424,1425,1428,1431],{"name":14,"slug":15,"type":16},{"name":1426,"slug":1427,"type":16},"Multimodal","multimodal",{"name":1429,"slug":1430,"type":16},"Prompt Engineering","prompt-engineering",{"name":27,"slug":28,"type":16},"2026-08-08T04:19:19.631186",{"slug":1434,"name":1434,"fn":1435,"description":1436,"org":1437,"tags":1438,"stars":29,"repoUrl":30,"updatedAt":1443},"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},[1439,1440,1441,1442],{"name":24,"slug":25,"type":16},{"name":14,"slug":15,"type":16},{"name":18,"slug":19,"type":16},{"name":27,"slug":28,"type":16},"2026-08-08T04:19:09.002948",{"slug":1445,"name":1445,"fn":1446,"description":1447,"org":1448,"tags":1449,"stars":29,"repoUrl":30,"updatedAt":1456},"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},[1450,1451,1454,1455],{"name":14,"slug":15,"type":16},{"name":1452,"slug":1453,"type":16},"E-commerce","e-commerce",{"name":1401,"slug":1402,"type":16},{"name":27,"slug":28,"type":16},"2026-08-08T04:19:12.135191",{"slug":1458,"name":1458,"fn":1459,"description":1460,"org":1461,"tags":1462,"stars":29,"repoUrl":30,"updatedAt":1467},"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},[1463,1464,1465,1466],{"name":1397,"slug":1398,"type":16},{"name":14,"slug":15,"type":16},{"name":1232,"slug":1233,"type":16},{"name":27,"slug":28,"type":16},"2026-08-08T04:19:18.794688",9]