[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-minimax-music-video-subtitle-generator":3,"mdc-ujjcgn-key":36,"related-org-minimax-music-video-subtitle-generator":1029,"related-repo-minimax-music-video-subtitle-generator":1228},{"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},"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},"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},"Content Creation","content-creation","tag",{"name":18,"slug":19,"type":16},"Creative","creative",{"name":21,"slug":22,"type":16},"Video","video",{"name":24,"slug":25,"type":16},"Typography","typography",1132,"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-H3","2026-08-08T04:19:18.794688",null,59,[],{"repoUrl":27,"stars":26,"forks":30,"topics":33,"description":29},[],"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-H3\u002Ftree\u002FHEAD\u002Fskills\u002Fmv-subtitle-skill-confirmed","---\nname: music-video-subtitle-generator\ndescription: |\n  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.\ntrigger-words: [MV, music video, lyric typography, on-screen text, prompt audit, Trap MV, Gospel hip-hop, Dark-pop, Cyber-grunge, MV提示词, 歌词文字, 字幕MV, 贴字MV, 卡点MV, 多镜头拼接]\n---\n\n# Music Aesthetics MV\n\n## Purpose\n\nUse this Skill when the user wants to create, revise, audit, or generate music-video prompts or emotional short-film prompts where music, lyrics, typography, references, rhythm, performance, and camera language must be designed together. The workflow adapts MV prompt rules into Hub execution: key creative decisions are confirmed, locked prompts are written to canvas text nodes, and media creation is delegated to Hub agents.\n\nDo not use it for ordinary subtitle burn-in, generic video editing, non-music product ads, or simple single-image \u002F single-clip requests without MV structure.\n\n## Hub compatibility rules\n\n- Do not assume third-party tools, shell scripts, browser plugins, or external generation APIs.\n- Write locked prompts and revisions to Hub canvas text nodes.\n- Delegate character cards, scene cards, typography cards, video clips, BGM, and final assembly to Hub image, video, music, and editing agents.\n- Do not hardcode output paths; always use Hub-returned paths.\n- If the user says “skip confirmation \u002F just do it”, apply it only to the current run unless the outer orchestrator has active session authorization.\n- If the user only wants a prompt, stop after delivery. If the user wants a finished MV, continue to generation and assembly after confirmation.\n\n## Core principles\n\n1. Understand the work before choosing a structure. Templates organize, but are not mandatory forms.\n2. Use the latest confirmed creative intent.\n3. Omit irrelevant fields instead of filling placeholders.\n4. Do not mechanically add performance, typography, transitions, camera moves, or character actions just because a preset includes them.\n5. On-screen text is a designed visual layer, not ordinary subtitles, unless the user explicitly requests subtitles.\n6. If the user uploads a real song or beat, it is the master music bed unless they request replacement.\n7. **Natural multi-shot stitching for >15s videos**: when duration exceeds the model single-generation limit, use “multi-shot storyboard breakdown + tail\u002Fhead frame continuation + beat hard cuts + global master-audio alignment”. Every segment must preserve the same groove, tempo feel, aspect ratio, character logic, visual preset, lighting language, and typography motion rules.\n8. If the user wants a finished music-aesthetic MV without lyrics, generate and lock original lyrics first. The final MV must reference character, typography packaging, and scene cards together. The typography packaging card controls only text packaging style, font texture, graphic design, layout ratio, and motion language.\n\n## STEP 1: Pre-flight lock\n\nBefore writing the final production prompt, confirm the minimum foundation with concise recommended choices.\n\n### 1.1 Video format\n\nOffer fixed options:\n\n| Use case | Aspect ratio | Resolution |\n| :--- | ---: | ---: |\n| TikTok \u002F Reels \u002F Shorts vertical | 9:16 | 1080×1920 |\n| YouTube \u002F Bilibili horizontal | 16:9 | 1920×1080 |\n| Feed square | 1:1 | 1080×1080 |\n| Dense vertical ad test | 9:16 | 720×1280 |\n| Cinematic widescreen MV | 21:9 | 2560×1080 |\n\nThe selected ratio must be reused across character cards, scene cards, typography references, shot prompts, video clips, and final assembly.\n\n### 1.2 Target duration and multi-shot structure\n\nBefore prompt writing or video generation, confirm target MV duration. Never silently use the model default as user intent.\n\nOffer a compact duration card:\n\n1. **10-second test**: one or two shots to verify character, scene, typography, and audio style.\n2. **15-second hook**: 2–4 short shots for a more complete chorus \u002F hook \u002F performance phrase.\n3. **30-second or longer complete MV (multi-shot stitching)**: because many models have a 15-second single-generation ceiling, automatically use a Multi-Shot stitching workflow. First generate or lock one continuous song \u002F BGM, split 30 seconds into 4–8 dynamic 2–5 second shots, then stitch via beat sync and head\u002Ftail frame continuity.\n4. **Custom duration**: user provides duration; plan shot count and stitching based on the selected model’s single-clip limit.\n\nIf uploaded music exists, the confirmed duration is the music window length.\n\n### 1.3 Music window\n\nIf uploaded or specified music is longer than the confirmed duration, lock a segment before writing prompts:\n\n1. Recommended window: assistant identifies the strongest chorus \u002F hook \u002F emotional turn and requests confirmation.\n2. User timestamps: user provides start and end seconds; verify both are inside the audio.\n3. Multi-variant: only for ad-hook testing or multiple creative directions.\n\nIf music is shorter than the target duration, use the full audio unless the user explicitly asks to stretch or extend it.\n\n### 1.3.0 Lyrics lock and lyrics-first fallback\n\nBefore final video prompts or generation, determine lyric ownership:\n\n1. If the user provides lyrics, those are locked lyrics. Do not generate, add, rewrite, expand, translate, paraphrase, or replace them unless explicitly requested.\n2. If the user wants a finished music-aesthetic MV without lyrics, generate short original lyrics matching the music style, vocal mode, duration, emotion, and visual preset, then lock them.\n3. Locked lyrics are the only source text for rap\u002Fsinging performance and visible typography.\n4. Split locked lyrics into each shot’s `Rap line:`, `Vocal line:`, `Soft vocal line:`, or `Spoken line:`.\n5. Every `Typography:` field must come from the same locked lyrics. During vocal performance, visible text must word-for-word match the performed phrase.\n6. In the final typography MV, the performer must rap or sing the locked lyrics with visible lip shapes, jaw motion, breath, facial accents, nods, and hand accents following phrasing and rhythm.\n\n### 1.3.1 Default multi-shot stitching for >15s videos\n\nFor >15s MVs such as 30 seconds, the global multi-shot prompt script is the authoritative source:\n\n1. **Lock complete Master Audio**: lock one continuous song \u002F BGM track with the full vocal and groove as the only audio baseline.\n2. **Build a Shotlist Timeline**: split 30 seconds into 4–8 short shots of 2–5 seconds, mapped precisely to lyric timestamps and beats such as snare, 808, and drop.\n3. **Head\u002Ftail frame and scene continuity**: if Shot B continues the same scene, use Shot A’s tail frame as Shot B’s head frame. If it is a hard cut, preserve the same character card, wardrobe, lighting prompt, and use same-direction camera motion or match-cut visual elements.\n4. **Generation and edit assembly**: the video agent generates each shot from the Shotlist. The editing agent aligns all clips to the global Master Audio beat grid, trimming, speed-ramping, and stitching for natural lip-sync, beat sync, and transitions.\n\n## STEP 2: Creative Contract\n\nBefore final prompts, create a concise creative contract:\n\n- Music genre, instrumentation, tempo\u002FBPM feel, vocal mode, and emotional temperature.\n- Lyric source and locked lyrics.\n- Target duration and multi-shot breakdown, e.g. 30s split into 6 short shots.\n- Reference image roles: character card, scene card, typography packaging card.\n- Camera language, shot sizes, focus, beat-cut density, and transition logic.\n- Exclusions such as no fades, no glossy AI beauty face, no single-shot overstretching that causes deformation.\n\n## STEP 3: Reference roles and scene sampling\n\nAssign each reference image one narrow job:\n\n- **Typography reference card**: controls only text packaging style, font texture, graphic design, layout ratio, and motion language. It must not contribute people or scenes.\n- **Character reference card**: controls character identity, facial aura, hairstyle, clothing silhouette, proportions, posture, and presence.\n- **Scene reference card**: controls scene style, spatial atmosphere, image texture, background depth, and lighting mood.\n\n### 3.1 Close-up scene switching and multi-shot sampling\n\nFor Trap, Dark-pop, Cyber-grunge, and other fast-paced MVs, switch quickly among multiple close-up spaces:\n\n- Keep scene mood unified, but each shot’s space must differ clearly, such as local background, tunnel, wall, light strip, or reflective floor.\n- Scene switches must be triggered by musical impacts: bass hit, 808 drop, snare, vocal accent, or typography smash.\n- Shot switches are “visual samples” on the trap beat: hard cuts, jump cuts, scan-glitch cuts, flash cuts, or action match cuts.\n\n## STEP 4: Preset grammar, Dark-pop \u002F Cyber-grunge and Trap example\n\n### Visual and editing language\n\n- Realistic high-fashion texture and film-magazine texture, referencing late-90s \u002F early-00s indie magazines, photocopy paper, film scans, and zine collage.\n- Heavy grain, slight film jitter, halftone dots, rough print edges, scan offsets.\n- **Editing must use hard cuts only**. No fades, dissolves, or soft transitions.\n- Image and typography strongly respond to beat cues: hi-hat roll creates micro-shake \u002F frame skips, snare triggers scale-up \u002F hard cut \u002F shoulder drop, 808 bass hit creates low-frequency compression \u002F stretch \u002F offset.\n\n### Typography packaging rules\n\n- Typography is a dynamic graphic subject in space, not a subtitle bar. It may sit in foreground, midground, background, or be occluded by shoulders \u002F hands.\n- Text must never cover eyes or main facial expression; avoid the mouth during critical lip-sync.\n- With vocals, visible words must exactly match the performed lyrics. Each shot has only one main typography event.\n\n## STEP 5: Prompt structure template\n\nA multi-shot script must be modular by shot, with accurate duration and audio mapping:\n\n```text\n[Global Aesthetic & Character Lock]: (global character and aesthetic anchor prompt)\n\nShot 1 (0.0s - 3.5s)\nVocal Line: \"...\"\nTypography: \"...\"\nVisual & Action: ...\nCamera & Motion: ...\nTransition Out: hard cut to Shot 2 on bass hit \u002F same-direction whip pan\n\nShot 2 (3.5s - 7.0s)\nVocal Line: \"...\"\nTypography: \"...\"\nVisual & Action: ...\nCamera & Motion: ...\nTransition Out: ...\n```\n\n## STEP 6: BGM continuity and natural multi-shot stitching system\n\n### 6.1 Global audio continuity\n\nThe entire MV must bind to one Master Audio track. During segmented video generation, do not use independent disconnected clip audio. All video clips are aligned to their corresponding timestamps on the Master Audio timeline during edit assembly.\n\n### 6.2 Natural Stitching Protocol\n\nFor >15s stitching, enforce five continuity locks:\n\n**Vocal & Lip Continuity**: Cut points must land on lyric pauses, breaths, snare, or drop. Do not hard cut inside an active vowel or lyric unless the next shot is an extreme close-up with continuous mouth shape.\n\n**Rhythm & Beat Matching**: Cut points must hit the 1\u002F4 or 1\u002F8 beat grid. Use speed ramping to align head nods, hand gestures, and blinks to beats.\n\n**Aesthetic & Color Grading**: Every cross-shot generation carries the same aesthetic header prompt: grain level, LUT direction, and light direction. Final assembly uses unified 35mm film grain and LUT to hide batch color differences.\n\n**Transition & Motion Continuity**: For long-shot continuation, use the previous tail frame as the next head frame and prompt continuation of action. For hard scene switches, use kinetic continuity such as same-direction pan or hand-occlusion match cut.\n\n**Typography Motion Stitching**: Text in the previous shot should shatter, sweep out, or smash-screen on a bass hit; next-shot text smashes in or unfolds on the accent, transferring visual momentum.\n\n## STEP 7: Checklist\n\nSilently verify before delivery:\n\n- [ ] If target duration exceeds 15s, has Multi-Shot breakdown been used automatically?\n- [ ] Is one global Master Audio locked, and are cut points beat-aligned?\n- [ ] Do cuts avoid mid-lyric vocal breaks, with natural lip and breath continuity?\n- [ ] Do adjacent shots have clear stitching logic such as tail\u002Fhead continuation, same-direction motion, match cut, or beat hard cut?\n- [ ] Is the edit style strictly hard-cut, with no fades or soft transitions?\n- [ ] Are character \u002F scene \u002F typography cards isolated without cross-contamination?\n- [ ] Is typography a spatial layer that never blocks eyes or main facial expression?\n- [ ] Are image quality, grain, color, and lighting consistent globally?\n\n## STEP 8: Canvas delivery\n\nAfter the complete MV prompt script is locked, write it to a dedicated canvas text node named `Complete MV Prompt` or `完整MV Prompt`. The node must contain the full multi-shot prompt script and stitching notes. Later revisions update the same node.\n\n## STEP 9: Final MV generation and assembly workflow\n\n1. **Prompt lock and canvas write**: confirm the full multi-shot prompt script with timestamps, lyric mapping, and transition logic is written to canvas.\n2. **Parallel shot generation**: the video agent generates each 2–5s shot from the Shotlist. For continuation shots, extract the prior shot’s tail frame as the next I2V head frame.\n3. **Multi-track editing and stitching**: the editing agent imports the global Master Audio, aligns all shot videos by timestamp, trims and speed-ramps on the beat grid, and checks seams with same-direction motion or flash-cut masking.\n4. **Finishing**: apply unified Movie LUT and 35mm film grain overlay to reduce AI plasticity and lock visual consistency.\n5. **Delivery**: output the seamless complete MV video file.\n",{"data":37,"body":54},{"name":4,"description":6,"trigger-words":38},[39,40,41,42,43,44,45,46,47,48,49,50,51,52,53],"MV","music video","lyric typography","on-screen text","prompt audit","Trap MV","Gospel hip-hop","Dark-pop","Cyber-grunge","MV提示词","歌词文字","字幕MV","贴字MV","卡点MV","多镜头拼接",{"type":55,"children":56},"root",[57,66,73,79,84,90,125,131,181,187,192,199,204,328,333,339,344,349,392,397,403,408,426,431,437,442,515,521,526,569,575,580,613,619,624,657,663,668,686,692,698,726,732,750,756,761,773,779,785,790,796,801,811,821,831,841,851,857,862,943,949,970,976],{"type":58,"tag":59,"props":60,"children":62},"element","h1",{"id":61},"music-aesthetics-mv",[63],{"type":64,"value":65},"text","Music Aesthetics MV",{"type":58,"tag":67,"props":68,"children":70},"h2",{"id":69},"purpose",[71],{"type":64,"value":72},"Purpose",{"type":58,"tag":74,"props":75,"children":76},"p",{},[77],{"type":64,"value":78},"Use this Skill when the user wants to create, revise, audit, or generate music-video prompts or emotional short-film prompts where music, lyrics, typography, references, rhythm, performance, and camera language must be designed together. The workflow adapts MV prompt rules into Hub execution: key creative decisions are confirmed, locked prompts are written to canvas text nodes, and media creation is delegated to Hub agents.",{"type":58,"tag":74,"props":80,"children":81},{},[82],{"type":64,"value":83},"Do not use it for ordinary subtitle burn-in, generic video editing, non-music product ads, or simple single-image \u002F single-clip requests without MV structure.",{"type":58,"tag":67,"props":85,"children":87},{"id":86},"hub-compatibility-rules",[88],{"type":64,"value":89},"Hub compatibility rules",{"type":58,"tag":91,"props":92,"children":93},"ul",{},[94,100,105,110,115,120],{"type":58,"tag":95,"props":96,"children":97},"li",{},[98],{"type":64,"value":99},"Do not assume third-party tools, shell scripts, browser plugins, or external generation APIs.",{"type":58,"tag":95,"props":101,"children":102},{},[103],{"type":64,"value":104},"Write locked prompts and revisions to Hub canvas text nodes.",{"type":58,"tag":95,"props":106,"children":107},{},[108],{"type":64,"value":109},"Delegate character cards, scene cards, typography cards, video clips, BGM, and final assembly to Hub image, video, music, and editing agents.",{"type":58,"tag":95,"props":111,"children":112},{},[113],{"type":64,"value":114},"Do not hardcode output paths; always use Hub-returned paths.",{"type":58,"tag":95,"props":116,"children":117},{},[118],{"type":64,"value":119},"If the user says “skip confirmation \u002F just do it”, apply it only to the current run unless the outer orchestrator has active session authorization.",{"type":58,"tag":95,"props":121,"children":122},{},[123],{"type":64,"value":124},"If the user only wants a prompt, stop after delivery. If the user wants a finished MV, continue to generation and assembly after confirmation.",{"type":58,"tag":67,"props":126,"children":128},{"id":127},"core-principles",[129],{"type":64,"value":130},"Core principles",{"type":58,"tag":132,"props":133,"children":134},"ol",{},[135,140,145,150,155,160,165,176],{"type":58,"tag":95,"props":136,"children":137},{},[138],{"type":64,"value":139},"Understand the work before choosing a structure. Templates organize, but are not mandatory forms.",{"type":58,"tag":95,"props":141,"children":142},{},[143],{"type":64,"value":144},"Use the latest confirmed creative intent.",{"type":58,"tag":95,"props":146,"children":147},{},[148],{"type":64,"value":149},"Omit irrelevant fields instead of filling placeholders.",{"type":58,"tag":95,"props":151,"children":152},{},[153],{"type":64,"value":154},"Do not mechanically add performance, typography, transitions, camera moves, or character actions just because a preset includes them.",{"type":58,"tag":95,"props":156,"children":157},{},[158],{"type":64,"value":159},"On-screen text is a designed visual layer, not ordinary subtitles, unless the user explicitly requests subtitles.",{"type":58,"tag":95,"props":161,"children":162},{},[163],{"type":64,"value":164},"If the user uploads a real song or beat, it is the master music bed unless they request replacement.",{"type":58,"tag":95,"props":166,"children":167},{},[168,174],{"type":58,"tag":169,"props":170,"children":171},"strong",{},[172],{"type":64,"value":173},"Natural multi-shot stitching for >15s videos",{"type":64,"value":175},": when duration exceeds the model single-generation limit, use “multi-shot storyboard breakdown + tail\u002Fhead frame continuation + beat hard cuts + global master-audio alignment”. Every segment must preserve the same groove, tempo feel, aspect ratio, character logic, visual preset, lighting language, and typography motion rules.",{"type":58,"tag":95,"props":177,"children":178},{},[179],{"type":64,"value":180},"If the user wants a finished music-aesthetic MV without lyrics, generate and lock original lyrics first. The final MV must reference character, typography packaging, and scene cards together. The typography packaging card controls only text packaging style, font texture, graphic design, layout ratio, and motion language.",{"type":58,"tag":67,"props":182,"children":184},{"id":183},"step-1-pre-flight-lock",[185],{"type":64,"value":186},"STEP 1: Pre-flight lock",{"type":58,"tag":74,"props":188,"children":189},{},[190],{"type":64,"value":191},"Before writing the final production prompt, confirm the minimum foundation with concise recommended choices.",{"type":58,"tag":193,"props":194,"children":196},"h3",{"id":195},"_11-video-format",[197],{"type":64,"value":198},"1.1 Video format",{"type":58,"tag":74,"props":200,"children":201},{},[202],{"type":64,"value":203},"Offer fixed options:",{"type":58,"tag":205,"props":206,"children":207},"table",{},[208,234],{"type":58,"tag":209,"props":210,"children":211},"thead",{},[212],{"type":58,"tag":213,"props":214,"children":215},"tr",{},[216,223,229],{"type":58,"tag":217,"props":218,"children":220},"th",{"align":219},"left",[221],{"type":64,"value":222},"Use case",{"type":58,"tag":217,"props":224,"children":226},{"align":225},"right",[227],{"type":64,"value":228},"Aspect ratio",{"type":58,"tag":217,"props":230,"children":231},{"align":225},[232],{"type":64,"value":233},"Resolution",{"type":58,"tag":235,"props":236,"children":237},"tbody",{},[238,257,275,293,310],{"type":58,"tag":213,"props":239,"children":240},{},[241,247,252],{"type":58,"tag":242,"props":243,"children":244},"td",{"align":219},[245],{"type":64,"value":246},"TikTok \u002F Reels \u002F Shorts vertical",{"type":58,"tag":242,"props":248,"children":249},{"align":225},[250],{"type":64,"value":251},"9:16",{"type":58,"tag":242,"props":253,"children":254},{"align":225},[255],{"type":64,"value":256},"1080×1920",{"type":58,"tag":213,"props":258,"children":259},{},[260,265,270],{"type":58,"tag":242,"props":261,"children":262},{"align":219},[263],{"type":64,"value":264},"YouTube \u002F Bilibili horizontal",{"type":58,"tag":242,"props":266,"children":267},{"align":225},[268],{"type":64,"value":269},"16:9",{"type":58,"tag":242,"props":271,"children":272},{"align":225},[273],{"type":64,"value":274},"1920×1080",{"type":58,"tag":213,"props":276,"children":277},{},[278,283,288],{"type":58,"tag":242,"props":279,"children":280},{"align":219},[281],{"type":64,"value":282},"Feed square",{"type":58,"tag":242,"props":284,"children":285},{"align":225},[286],{"type":64,"value":287},"1:1",{"type":58,"tag":242,"props":289,"children":290},{"align":225},[291],{"type":64,"value":292},"1080×1080",{"type":58,"tag":213,"props":294,"children":295},{},[296,301,305],{"type":58,"tag":242,"props":297,"children":298},{"align":219},[299],{"type":64,"value":300},"Dense vertical ad test",{"type":58,"tag":242,"props":302,"children":303},{"align":225},[304],{"type":64,"value":251},{"type":58,"tag":242,"props":306,"children":307},{"align":225},[308],{"type":64,"value":309},"720×1280",{"type":58,"tag":213,"props":311,"children":312},{},[313,318,323],{"type":58,"tag":242,"props":314,"children":315},{"align":219},[316],{"type":64,"value":317},"Cinematic widescreen MV",{"type":58,"tag":242,"props":319,"children":320},{"align":225},[321],{"type":64,"value":322},"21:9",{"type":58,"tag":242,"props":324,"children":325},{"align":225},[326],{"type":64,"value":327},"2560×1080",{"type":58,"tag":74,"props":329,"children":330},{},[331],{"type":64,"value":332},"The selected ratio must be reused across character cards, scene cards, typography references, shot prompts, video clips, and final assembly.",{"type":58,"tag":193,"props":334,"children":336},{"id":335},"_12-target-duration-and-multi-shot-structure",[337],{"type":64,"value":338},"1.2 Target duration and multi-shot structure",{"type":58,"tag":74,"props":340,"children":341},{},[342],{"type":64,"value":343},"Before prompt writing or video generation, confirm target MV duration. Never silently use the model default as user intent.",{"type":58,"tag":74,"props":345,"children":346},{},[347],{"type":64,"value":348},"Offer a compact duration card:",{"type":58,"tag":132,"props":350,"children":351},{},[352,362,372,382],{"type":58,"tag":95,"props":353,"children":354},{},[355,360],{"type":58,"tag":169,"props":356,"children":357},{},[358],{"type":64,"value":359},"10-second test",{"type":64,"value":361},": one or two shots to verify character, scene, typography, and audio style.",{"type":58,"tag":95,"props":363,"children":364},{},[365,370],{"type":58,"tag":169,"props":366,"children":367},{},[368],{"type":64,"value":369},"15-second hook",{"type":64,"value":371},": 2–4 short shots for a more complete chorus \u002F hook \u002F performance phrase.",{"type":58,"tag":95,"props":373,"children":374},{},[375,380],{"type":58,"tag":169,"props":376,"children":377},{},[378],{"type":64,"value":379},"30-second or longer complete MV (multi-shot stitching)",{"type":64,"value":381},": because many models have a 15-second single-generation ceiling, automatically use a Multi-Shot stitching workflow. First generate or lock one continuous song \u002F BGM, split 30 seconds into 4–8 dynamic 2–5 second shots, then stitch via beat sync and head\u002Ftail frame continuity.",{"type":58,"tag":95,"props":383,"children":384},{},[385,390],{"type":58,"tag":169,"props":386,"children":387},{},[388],{"type":64,"value":389},"Custom duration",{"type":64,"value":391},": user provides duration; plan shot count and stitching based on the selected model’s single-clip limit.",{"type":58,"tag":74,"props":393,"children":394},{},[395],{"type":64,"value":396},"If uploaded music exists, the confirmed duration is the music window length.",{"type":58,"tag":193,"props":398,"children":400},{"id":399},"_13-music-window",[401],{"type":64,"value":402},"1.3 Music window",{"type":58,"tag":74,"props":404,"children":405},{},[406],{"type":64,"value":407},"If uploaded or specified music is longer than the confirmed duration, lock a segment before writing prompts:",{"type":58,"tag":132,"props":409,"children":410},{},[411,416,421],{"type":58,"tag":95,"props":412,"children":413},{},[414],{"type":64,"value":415},"Recommended window: assistant identifies the strongest chorus \u002F hook \u002F emotional turn and requests confirmation.",{"type":58,"tag":95,"props":417,"children":418},{},[419],{"type":64,"value":420},"User timestamps: user provides start and end seconds; verify both are inside the audio.",{"type":58,"tag":95,"props":422,"children":423},{},[424],{"type":64,"value":425},"Multi-variant: only for ad-hook testing or multiple creative directions.",{"type":58,"tag":74,"props":427,"children":428},{},[429],{"type":64,"value":430},"If music is shorter than the target duration, use the full audio unless the user explicitly asks to stretch or extend it.",{"type":58,"tag":193,"props":432,"children":434},{"id":433},"_130-lyrics-lock-and-lyrics-first-fallback",[435],{"type":64,"value":436},"1.3.0 Lyrics lock and lyrics-first fallback",{"type":58,"tag":74,"props":438,"children":439},{},[440],{"type":64,"value":441},"Before final video prompts or generation, determine lyric ownership:",{"type":58,"tag":132,"props":443,"children":444},{},[445,450,455,460,497,510],{"type":58,"tag":95,"props":446,"children":447},{},[448],{"type":64,"value":449},"If the user provides lyrics, those are locked lyrics. Do not generate, add, rewrite, expand, translate, paraphrase, or replace them unless explicitly requested.",{"type":58,"tag":95,"props":451,"children":452},{},[453],{"type":64,"value":454},"If the user wants a finished music-aesthetic MV without lyrics, generate short original lyrics matching the music style, vocal mode, duration, emotion, and visual preset, then lock them.",{"type":58,"tag":95,"props":456,"children":457},{},[458],{"type":64,"value":459},"Locked lyrics are the only source text for rap\u002Fsinging performance and visible typography.",{"type":58,"tag":95,"props":461,"children":462},{},[463,465,472,474,480,481,487,489,495],{"type":64,"value":464},"Split locked lyrics into each shot’s ",{"type":58,"tag":466,"props":467,"children":469},"code",{"className":468},[],[470],{"type":64,"value":471},"Rap line:",{"type":64,"value":473},", ",{"type":58,"tag":466,"props":475,"children":477},{"className":476},[],[478],{"type":64,"value":479},"Vocal line:",{"type":64,"value":473},{"type":58,"tag":466,"props":482,"children":484},{"className":483},[],[485],{"type":64,"value":486},"Soft vocal line:",{"type":64,"value":488},", or ",{"type":58,"tag":466,"props":490,"children":492},{"className":491},[],[493],{"type":64,"value":494},"Spoken line:",{"type":64,"value":496},".",{"type":58,"tag":95,"props":498,"children":499},{},[500,502,508],{"type":64,"value":501},"Every ",{"type":58,"tag":466,"props":503,"children":505},{"className":504},[],[506],{"type":64,"value":507},"Typography:",{"type":64,"value":509}," field must come from the same locked lyrics. During vocal performance, visible text must word-for-word match the performed phrase.",{"type":58,"tag":95,"props":511,"children":512},{},[513],{"type":64,"value":514},"In the final typography MV, the performer must rap or sing the locked lyrics with visible lip shapes, jaw motion, breath, facial accents, nods, and hand accents following phrasing and rhythm.",{"type":58,"tag":193,"props":516,"children":518},{"id":517},"_131-default-multi-shot-stitching-for-15s-videos",[519],{"type":64,"value":520},"1.3.1 Default multi-shot stitching for >15s videos",{"type":58,"tag":74,"props":522,"children":523},{},[524],{"type":64,"value":525},"For >15s MVs such as 30 seconds, the global multi-shot prompt script is the authoritative source:",{"type":58,"tag":132,"props":527,"children":528},{},[529,539,549,559],{"type":58,"tag":95,"props":530,"children":531},{},[532,537],{"type":58,"tag":169,"props":533,"children":534},{},[535],{"type":64,"value":536},"Lock complete Master Audio",{"type":64,"value":538},": lock one continuous song \u002F BGM track with the full vocal and groove as the only audio baseline.",{"type":58,"tag":95,"props":540,"children":541},{},[542,547],{"type":58,"tag":169,"props":543,"children":544},{},[545],{"type":64,"value":546},"Build a Shotlist Timeline",{"type":64,"value":548},": split 30 seconds into 4–8 short shots of 2–5 seconds, mapped precisely to lyric timestamps and beats such as snare, 808, and drop.",{"type":58,"tag":95,"props":550,"children":551},{},[552,557],{"type":58,"tag":169,"props":553,"children":554},{},[555],{"type":64,"value":556},"Head\u002Ftail frame and scene continuity",{"type":64,"value":558},": if Shot B continues the same scene, use Shot A’s tail frame as Shot B’s head frame. If it is a hard cut, preserve the same character card, wardrobe, lighting prompt, and use same-direction camera motion or match-cut visual elements.",{"type":58,"tag":95,"props":560,"children":561},{},[562,567],{"type":58,"tag":169,"props":563,"children":564},{},[565],{"type":64,"value":566},"Generation and edit assembly",{"type":64,"value":568},": the video agent generates each shot from the Shotlist. The editing agent aligns all clips to the global Master Audio beat grid, trimming, speed-ramping, and stitching for natural lip-sync, beat sync, and transitions.",{"type":58,"tag":67,"props":570,"children":572},{"id":571},"step-2-creative-contract",[573],{"type":64,"value":574},"STEP 2: Creative Contract",{"type":58,"tag":74,"props":576,"children":577},{},[578],{"type":64,"value":579},"Before final prompts, create a concise creative contract:",{"type":58,"tag":91,"props":581,"children":582},{},[583,588,593,598,603,608],{"type":58,"tag":95,"props":584,"children":585},{},[586],{"type":64,"value":587},"Music genre, instrumentation, tempo\u002FBPM feel, vocal mode, and emotional temperature.",{"type":58,"tag":95,"props":589,"children":590},{},[591],{"type":64,"value":592},"Lyric source and locked lyrics.",{"type":58,"tag":95,"props":594,"children":595},{},[596],{"type":64,"value":597},"Target duration and multi-shot breakdown, e.g. 30s split into 6 short shots.",{"type":58,"tag":95,"props":599,"children":600},{},[601],{"type":64,"value":602},"Reference image roles: character card, scene card, typography packaging card.",{"type":58,"tag":95,"props":604,"children":605},{},[606],{"type":64,"value":607},"Camera language, shot sizes, focus, beat-cut density, and transition logic.",{"type":58,"tag":95,"props":609,"children":610},{},[611],{"type":64,"value":612},"Exclusions such as no fades, no glossy AI beauty face, no single-shot overstretching that causes deformation.",{"type":58,"tag":67,"props":614,"children":616},{"id":615},"step-3-reference-roles-and-scene-sampling",[617],{"type":64,"value":618},"STEP 3: Reference roles and scene sampling",{"type":58,"tag":74,"props":620,"children":621},{},[622],{"type":64,"value":623},"Assign each reference image one narrow job:",{"type":58,"tag":91,"props":625,"children":626},{},[627,637,647],{"type":58,"tag":95,"props":628,"children":629},{},[630,635],{"type":58,"tag":169,"props":631,"children":632},{},[633],{"type":64,"value":634},"Typography reference card",{"type":64,"value":636},": controls only text packaging style, font texture, graphic design, layout ratio, and motion language. It must not contribute people or scenes.",{"type":58,"tag":95,"props":638,"children":639},{},[640,645],{"type":58,"tag":169,"props":641,"children":642},{},[643],{"type":64,"value":644},"Character reference card",{"type":64,"value":646},": controls character identity, facial aura, hairstyle, clothing silhouette, proportions, posture, and presence.",{"type":58,"tag":95,"props":648,"children":649},{},[650,655],{"type":58,"tag":169,"props":651,"children":652},{},[653],{"type":64,"value":654},"Scene reference card",{"type":64,"value":656},": controls scene style, spatial atmosphere, image texture, background depth, and lighting mood.",{"type":58,"tag":193,"props":658,"children":660},{"id":659},"_31-close-up-scene-switching-and-multi-shot-sampling",[661],{"type":64,"value":662},"3.1 Close-up scene switching and multi-shot sampling",{"type":58,"tag":74,"props":664,"children":665},{},[666],{"type":64,"value":667},"For Trap, Dark-pop, Cyber-grunge, and other fast-paced MVs, switch quickly among multiple close-up spaces:",{"type":58,"tag":91,"props":669,"children":670},{},[671,676,681],{"type":58,"tag":95,"props":672,"children":673},{},[674],{"type":64,"value":675},"Keep scene mood unified, but each shot’s space must differ clearly, such as local background, tunnel, wall, light strip, or reflective floor.",{"type":58,"tag":95,"props":677,"children":678},{},[679],{"type":64,"value":680},"Scene switches must be triggered by musical impacts: bass hit, 808 drop, snare, vocal accent, or typography smash.",{"type":58,"tag":95,"props":682,"children":683},{},[684],{"type":64,"value":685},"Shot switches are “visual samples” on the trap beat: hard cuts, jump cuts, scan-glitch cuts, flash cuts, or action match cuts.",{"type":58,"tag":67,"props":687,"children":689},{"id":688},"step-4-preset-grammar-dark-pop-cyber-grunge-and-trap-example",[690],{"type":64,"value":691},"STEP 4: Preset grammar, Dark-pop \u002F Cyber-grunge and Trap example",{"type":58,"tag":193,"props":693,"children":695},{"id":694},"visual-and-editing-language",[696],{"type":64,"value":697},"Visual and editing language",{"type":58,"tag":91,"props":699,"children":700},{},[701,706,711,721],{"type":58,"tag":95,"props":702,"children":703},{},[704],{"type":64,"value":705},"Realistic high-fashion texture and film-magazine texture, referencing late-90s \u002F early-00s indie magazines, photocopy paper, film scans, and zine collage.",{"type":58,"tag":95,"props":707,"children":708},{},[709],{"type":64,"value":710},"Heavy grain, slight film jitter, halftone dots, rough print edges, scan offsets.",{"type":58,"tag":95,"props":712,"children":713},{},[714,719],{"type":58,"tag":169,"props":715,"children":716},{},[717],{"type":64,"value":718},"Editing must use hard cuts only",{"type":64,"value":720},". No fades, dissolves, or soft transitions.",{"type":58,"tag":95,"props":722,"children":723},{},[724],{"type":64,"value":725},"Image and typography strongly respond to beat cues: hi-hat roll creates micro-shake \u002F frame skips, snare triggers scale-up \u002F hard cut \u002F shoulder drop, 808 bass hit creates low-frequency compression \u002F stretch \u002F offset.",{"type":58,"tag":193,"props":727,"children":729},{"id":728},"typography-packaging-rules",[730],{"type":64,"value":731},"Typography packaging rules",{"type":58,"tag":91,"props":733,"children":734},{},[735,740,745],{"type":58,"tag":95,"props":736,"children":737},{},[738],{"type":64,"value":739},"Typography is a dynamic graphic subject in space, not a subtitle bar. It may sit in foreground, midground, background, or be occluded by shoulders \u002F hands.",{"type":58,"tag":95,"props":741,"children":742},{},[743],{"type":64,"value":744},"Text must never cover eyes or main facial expression; avoid the mouth during critical lip-sync.",{"type":58,"tag":95,"props":746,"children":747},{},[748],{"type":64,"value":749},"With vocals, visible words must exactly match the performed lyrics. Each shot has only one main typography event.",{"type":58,"tag":67,"props":751,"children":753},{"id":752},"step-5-prompt-structure-template",[754],{"type":64,"value":755},"STEP 5: Prompt structure template",{"type":58,"tag":74,"props":757,"children":758},{},[759],{"type":64,"value":760},"A multi-shot script must be modular by shot, with accurate duration and audio mapping:",{"type":58,"tag":762,"props":763,"children":768},"pre",{"className":764,"code":766,"language":64,"meta":767},[765],"language-text","[Global Aesthetic & Character Lock]: (global character and aesthetic anchor prompt)\n\nShot 1 (0.0s - 3.5s)\nVocal Line: \"...\"\nTypography: \"...\"\nVisual & Action: ...\nCamera & Motion: ...\nTransition Out: hard cut to Shot 2 on bass hit \u002F same-direction whip pan\n\nShot 2 (3.5s - 7.0s)\nVocal Line: \"...\"\nTypography: \"...\"\nVisual & Action: ...\nCamera & Motion: ...\nTransition Out: ...\n","",[769],{"type":58,"tag":466,"props":770,"children":771},{"__ignoreMap":767},[772],{"type":64,"value":766},{"type":58,"tag":67,"props":774,"children":776},{"id":775},"step-6-bgm-continuity-and-natural-multi-shot-stitching-system",[777],{"type":64,"value":778},"STEP 6: BGM continuity and natural multi-shot stitching system",{"type":58,"tag":193,"props":780,"children":782},{"id":781},"_61-global-audio-continuity",[783],{"type":64,"value":784},"6.1 Global audio continuity",{"type":58,"tag":74,"props":786,"children":787},{},[788],{"type":64,"value":789},"The entire MV must bind to one Master Audio track. During segmented video generation, do not use independent disconnected clip audio. All video clips are aligned to their corresponding timestamps on the Master Audio timeline during edit assembly.",{"type":58,"tag":193,"props":791,"children":793},{"id":792},"_62-natural-stitching-protocol",[794],{"type":64,"value":795},"6.2 Natural Stitching Protocol",{"type":58,"tag":74,"props":797,"children":798},{},[799],{"type":64,"value":800},"For >15s stitching, enforce five continuity locks:",{"type":58,"tag":74,"props":802,"children":803},{},[804,809],{"type":58,"tag":169,"props":805,"children":806},{},[807],{"type":64,"value":808},"Vocal & Lip Continuity",{"type":64,"value":810},": Cut points must land on lyric pauses, breaths, snare, or drop. Do not hard cut inside an active vowel or lyric unless the next shot is an extreme close-up with continuous mouth shape.",{"type":58,"tag":74,"props":812,"children":813},{},[814,819],{"type":58,"tag":169,"props":815,"children":816},{},[817],{"type":64,"value":818},"Rhythm & Beat Matching",{"type":64,"value":820},": Cut points must hit the 1\u002F4 or 1\u002F8 beat grid. Use speed ramping to align head nods, hand gestures, and blinks to beats.",{"type":58,"tag":74,"props":822,"children":823},{},[824,829],{"type":58,"tag":169,"props":825,"children":826},{},[827],{"type":64,"value":828},"Aesthetic & Color Grading",{"type":64,"value":830},": Every cross-shot generation carries the same aesthetic header prompt: grain level, LUT direction, and light direction. Final assembly uses unified 35mm film grain and LUT to hide batch color differences.",{"type":58,"tag":74,"props":832,"children":833},{},[834,839],{"type":58,"tag":169,"props":835,"children":836},{},[837],{"type":64,"value":838},"Transition & Motion Continuity",{"type":64,"value":840},": For long-shot continuation, use the previous tail frame as the next head frame and prompt continuation of action. For hard scene switches, use kinetic continuity such as same-direction pan or hand-occlusion match cut.",{"type":58,"tag":74,"props":842,"children":843},{},[844,849],{"type":58,"tag":169,"props":845,"children":846},{},[847],{"type":64,"value":848},"Typography Motion Stitching",{"type":64,"value":850},": Text in the previous shot should shatter, sweep out, or smash-screen on a bass hit; next-shot text smashes in or unfolds on the accent, transferring visual momentum.",{"type":58,"tag":67,"props":852,"children":854},{"id":853},"step-7-checklist",[855],{"type":64,"value":856},"STEP 7: Checklist",{"type":58,"tag":74,"props":858,"children":859},{},[860],{"type":64,"value":861},"Silently verify before delivery:",{"type":58,"tag":91,"props":863,"children":866},{"className":864},[865],"contains-task-list",[867,880,889,898,907,916,925,934],{"type":58,"tag":95,"props":868,"children":871},{"className":869},[870],"task-list-item",[872,878],{"type":58,"tag":873,"props":874,"children":877},"input",{"disabled":875,"type":876},true,"checkbox",[],{"type":64,"value":879}," If target duration exceeds 15s, has Multi-Shot breakdown been used automatically?",{"type":58,"tag":95,"props":881,"children":883},{"className":882},[870],[884,887],{"type":58,"tag":873,"props":885,"children":886},{"disabled":875,"type":876},[],{"type":64,"value":888}," Is one global Master Audio locked, and are cut points beat-aligned?",{"type":58,"tag":95,"props":890,"children":892},{"className":891},[870],[893,896],{"type":58,"tag":873,"props":894,"children":895},{"disabled":875,"type":876},[],{"type":64,"value":897}," Do cuts avoid mid-lyric vocal breaks, with natural lip and breath continuity?",{"type":58,"tag":95,"props":899,"children":901},{"className":900},[870],[902,905],{"type":58,"tag":873,"props":903,"children":904},{"disabled":875,"type":876},[],{"type":64,"value":906}," Do adjacent shots have clear stitching logic such as tail\u002Fhead continuation, same-direction motion, match cut, or beat hard cut?",{"type":58,"tag":95,"props":908,"children":910},{"className":909},[870],[911,914],{"type":58,"tag":873,"props":912,"children":913},{"disabled":875,"type":876},[],{"type":64,"value":915}," Is the edit style strictly hard-cut, with no fades or soft transitions?",{"type":58,"tag":95,"props":917,"children":919},{"className":918},[870],[920,923],{"type":58,"tag":873,"props":921,"children":922},{"disabled":875,"type":876},[],{"type":64,"value":924}," Are character \u002F scene \u002F typography cards isolated without cross-contamination?",{"type":58,"tag":95,"props":926,"children":928},{"className":927},[870],[929,932],{"type":58,"tag":873,"props":930,"children":931},{"disabled":875,"type":876},[],{"type":64,"value":933}," Is typography a spatial layer that never blocks eyes or main facial expression?",{"type":58,"tag":95,"props":935,"children":937},{"className":936},[870],[938,941],{"type":58,"tag":873,"props":939,"children":940},{"disabled":875,"type":876},[],{"type":64,"value":942}," Are image quality, grain, color, and lighting consistent globally?",{"type":58,"tag":67,"props":944,"children":946},{"id":945},"step-8-canvas-delivery",[947],{"type":64,"value":948},"STEP 8: Canvas delivery",{"type":58,"tag":74,"props":950,"children":951},{},[952,954,960,962,968],{"type":64,"value":953},"After the complete MV prompt script is locked, write it to a dedicated canvas text node named ",{"type":58,"tag":466,"props":955,"children":957},{"className":956},[],[958],{"type":64,"value":959},"Complete MV Prompt",{"type":64,"value":961}," or ",{"type":58,"tag":466,"props":963,"children":965},{"className":964},[],[966],{"type":64,"value":967},"完整MV Prompt",{"type":64,"value":969},". The node must contain the full multi-shot prompt script and stitching notes. Later revisions update the same node.",{"type":58,"tag":67,"props":971,"children":973},{"id":972},"step-9-final-mv-generation-and-assembly-workflow",[974],{"type":64,"value":975},"STEP 9: Final MV generation and assembly workflow",{"type":58,"tag":132,"props":977,"children":978},{},[979,989,999,1009,1019],{"type":58,"tag":95,"props":980,"children":981},{},[982,987],{"type":58,"tag":169,"props":983,"children":984},{},[985],{"type":64,"value":986},"Prompt lock and canvas write",{"type":64,"value":988},": confirm the full multi-shot prompt script with timestamps, lyric mapping, and transition logic is written to canvas.",{"type":58,"tag":95,"props":990,"children":991},{},[992,997],{"type":58,"tag":169,"props":993,"children":994},{},[995],{"type":64,"value":996},"Parallel shot generation",{"type":64,"value":998},": the video agent generates each 2–5s shot from the Shotlist. For continuation shots, extract the prior shot’s tail frame as the next I2V head frame.",{"type":58,"tag":95,"props":1000,"children":1001},{},[1002,1007],{"type":58,"tag":169,"props":1003,"children":1004},{},[1005],{"type":64,"value":1006},"Multi-track editing and stitching",{"type":64,"value":1008},": the editing agent imports the global Master Audio, aligns all shot videos by timestamp, trims and speed-ramps on the beat grid, and checks seams with same-direction motion or flash-cut masking.",{"type":58,"tag":95,"props":1010,"children":1011},{},[1012,1017],{"type":58,"tag":169,"props":1013,"children":1014},{},[1015],{"type":64,"value":1016},"Finishing",{"type":64,"value":1018},": apply unified Movie LUT and 35mm film grain overlay to reduce AI plasticity and lock visual consistency.",{"type":58,"tag":95,"props":1020,"children":1021},{},[1022,1027],{"type":58,"tag":169,"props":1023,"children":1024},{},[1025],{"type":64,"value":1026},"Delivery",{"type":64,"value":1028},": output the seamless complete MV video file.",{"items":1030,"total":1227},[1031,1055,1069,1086,1101,1121,1139,1157,1172,1188,1207,1217],{"slug":1032,"name":1032,"fn":1033,"description":1034,"org":1035,"tags":1036,"stars":1052,"repoUrl":1053,"updatedAt":1054},"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},[1037,1040,1043,1046,1049],{"name":1038,"slug":1039,"type":16},"Accessibility","accessibility",{"name":1041,"slug":1042,"type":16},"Android","android",{"name":1044,"slug":1045,"type":16},"Kotlin","kotlin",{"name":1047,"slug":1048,"type":16},"Mobile","mobile",{"name":1050,"slug":1051,"type":16},"UI Components","ui-components",13030,"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002Fskills","2026-07-13T06:16:54.247834",{"slug":1056,"name":1056,"fn":1057,"description":1058,"org":1059,"tags":1060,"stars":1052,"repoUrl":1053,"updatedAt":1068},"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},[1061,1064,1067],{"name":1062,"slug":1063,"type":16},"Agents","agents",{"name":1065,"slug":1066,"type":16},"Audio","audio",{"name":18,"slug":19,"type":16},"2026-07-13T06:16:35.130644",{"slug":1070,"name":1070,"fn":1071,"description":1072,"org":1073,"tags":1074,"stars":1052,"repoUrl":1053,"updatedAt":1085},"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},[1075,1078,1081,1084],{"name":1076,"slug":1077,"type":16},"Design","design",{"name":1079,"slug":1080,"type":16},"Presentations","presentations",{"name":1082,"slug":1083,"type":16},"Themes","themes",{"name":24,"slug":25,"type":16},"2026-07-13T06:17:02.785587",{"slug":1087,"name":1087,"fn":1088,"description":1089,"org":1090,"tags":1091,"stars":1052,"repoUrl":1053,"updatedAt":1100},"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},[1092,1093,1096,1099],{"name":1076,"slug":1077,"type":16},{"name":1094,"slug":1095,"type":16},"Design System","design-system",{"name":1097,"slug":1098,"type":16},"PowerPoint","powerpoint",{"name":1079,"slug":1080,"type":16},"2026-07-13T06:17:10.398389",{"slug":1102,"name":1102,"fn":1103,"description":1104,"org":1105,"tags":1106,"stars":1052,"repoUrl":1053,"updatedAt":1120},"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},[1107,1110,1113,1114,1117],{"name":1108,"slug":1109,"type":16},"Dart","dart",{"name":1111,"slug":1112,"type":16},"Flutter","flutter",{"name":1047,"slug":1048,"type":16},{"name":1115,"slug":1116,"type":16},"Performance","performance",{"name":1118,"slug":1119,"type":16},"State Management","state-management","2026-07-13T06:16:36.626679",{"slug":1122,"name":1122,"fn":1123,"description":1124,"org":1125,"tags":1126,"stars":1052,"repoUrl":1053,"updatedAt":1138},"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},[1127,1130,1131,1132,1135],{"name":1128,"slug":1129,"type":16},"Animation","animation",{"name":18,"slug":19,"type":16},{"name":1076,"slug":1077,"type":16},{"name":1133,"slug":1134,"type":16},"Frontend","frontend",{"name":1136,"slug":1137,"type":16},"Web Development","web-development","2026-07-13T06:16:39.108827",{"slug":1140,"name":1140,"fn":1141,"description":1142,"org":1143,"tags":1144,"stars":1052,"repoUrl":1053,"updatedAt":1156},"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},[1145,1148,1149,1152,1155],{"name":1146,"slug":1147,"type":16},"Backend","backend",{"name":1133,"slug":1134,"type":16},{"name":1150,"slug":1151,"type":16},"Full-stack","full-stack",{"name":1153,"slug":1154,"type":16},"REST API","rest-api",{"name":1136,"slug":1137,"type":16},"2026-07-13T06:16:43.219005",{"slug":1158,"name":1158,"fn":1159,"description":1160,"org":1161,"tags":1162,"stars":1052,"repoUrl":1053,"updatedAt":1171},"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},[1163,1164,1165,1168],{"name":1128,"slug":1129,"type":16},{"name":18,"slug":19,"type":16},{"name":1166,"slug":1167,"type":16},"Images","images",{"name":1169,"slug":1170,"type":16},"Media","media","2026-07-13T06:16:51.74461",{"slug":1173,"name":1173,"fn":1174,"description":1175,"org":1176,"tags":1177,"stars":1052,"repoUrl":1053,"updatedAt":1187},"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},[1178,1179,1182,1183,1186],{"name":1038,"slug":1039,"type":16},{"name":1180,"slug":1181,"type":16},"iOS","ios",{"name":1047,"slug":1048,"type":16},{"name":1184,"slug":1185,"type":16},"SwiftUI","swiftui",{"name":1050,"slug":1051,"type":16},"2026-07-13T06:16:55.686092",{"slug":1189,"name":1189,"fn":1190,"description":1191,"org":1192,"tags":1193,"stars":1052,"repoUrl":1053,"updatedAt":1206},"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},[1194,1197,1200,1203],{"name":1195,"slug":1196,"type":16},"Documents","documents",{"name":1198,"slug":1199,"type":16},"DOCX","docx",{"name":1201,"slug":1202,"type":16},"Office","office",{"name":1204,"slug":1205,"type":16},"Templates","templates","2026-07-13T06:16:40.461868",{"slug":1208,"name":1208,"fn":1209,"description":1210,"org":1211,"tags":1212,"stars":1052,"repoUrl":1053,"updatedAt":1216},"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},[1213,1214,1215],{"name":1065,"slug":1066,"type":16},{"name":18,"slug":19,"type":16},{"name":1169,"slug":1170,"type":16},"2026-07-13T06:16:50.381758",{"slug":1218,"name":1218,"fn":1219,"description":1220,"org":1221,"tags":1222,"stars":1052,"repoUrl":1053,"updatedAt":1226},"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},[1223,1224,1225],{"name":1065,"slug":1066,"type":16},{"name":18,"slug":19,"type":16},{"name":1169,"slug":1170,"type":16},"2026-07-13T06:16:57.002997",47,{"items":1229,"total":1317},[1230,1243,1256,1269,1284,1297,1310],{"slug":1231,"name":1231,"fn":1232,"description":1233,"org":1234,"tags":1235,"stars":26,"repoUrl":27,"updatedAt":1242},"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},[1236,1239,1240,1241],{"name":1237,"slug":1238,"type":16},"3D","3d",{"name":1128,"slug":1129,"type":16},{"name":18,"slug":19,"type":16},{"name":21,"slug":22,"type":16},"2026-08-08T04:19:20.46802",{"slug":1244,"name":1244,"fn":1245,"description":1246,"org":1247,"tags":1248,"stars":26,"repoUrl":27,"updatedAt":1255},"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},[1249,1250,1251,1254],{"name":14,"slug":15,"type":16},{"name":18,"slug":19,"type":16},{"name":1252,"slug":1253,"type":16},"Marketing","marketing",{"name":21,"slug":22,"type":16},"2026-08-08T04:19:08.155902",{"slug":1257,"name":1257,"fn":1258,"description":1259,"org":1260,"tags":1261,"stars":26,"repoUrl":27,"updatedAt":1268},"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},[1262,1263,1264,1265],{"name":1128,"slug":1129,"type":16},{"name":18,"slug":19,"type":16},{"name":1076,"slug":1077,"type":16},{"name":1266,"slug":1267,"type":16},"Game Development","game-development","2026-08-08T04:19:07.313539",{"slug":1270,"name":1270,"fn":1271,"description":1272,"org":1273,"tags":1274,"stars":26,"repoUrl":27,"updatedAt":1283},"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},[1275,1276,1279,1282],{"name":18,"slug":19,"type":16},{"name":1277,"slug":1278,"type":16},"Multimodal","multimodal",{"name":1280,"slug":1281,"type":16},"Prompt Engineering","prompt-engineering",{"name":21,"slug":22,"type":16},"2026-08-08T04:19:19.631186",{"slug":1285,"name":1285,"fn":1286,"description":1287,"org":1288,"tags":1289,"stars":26,"repoUrl":27,"updatedAt":1296},"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},[1290,1291,1292,1295],{"name":1128,"slug":1129,"type":16},{"name":18,"slug":19,"type":16},{"name":1293,"slug":1294,"type":16},"Generative Art","generative-art",{"name":21,"slug":22,"type":16},"2026-08-08T04:19:09.002948",{"slug":1298,"name":1298,"fn":1299,"description":1300,"org":1301,"tags":1302,"stars":26,"repoUrl":27,"updatedAt":1309},"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},[1303,1304,1307,1308],{"name":18,"slug":19,"type":16},{"name":1305,"slug":1306,"type":16},"E-commerce","e-commerce",{"name":1252,"slug":1253,"type":16},{"name":21,"slug":22,"type":16},"2026-08-08T04:19:12.135191",{"slug":4,"name":4,"fn":5,"description":6,"org":1311,"tags":1312,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1313,1314,1315,1316],{"name":14,"slug":15,"type":16},{"name":18,"slug":19,"type":16},{"name":24,"slug":25,"type":16},{"name":21,"slug":22,"type":16},9]