[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-minimax-brand-promo-video-generator":3,"mdc--mzlfe9-key":36,"related-org-minimax-brand-promo-video-generator":705,"related-repo-minimax-brand-promo-video-generator":906},{"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},"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},"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},"Marketing","marketing",{"name":21,"slug":22,"type":16},"Creative","creative",{"name":24,"slug":25,"type":16},"Video","video",1132,"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-H3","2026-08-08T04:19:08.155902",null,59,[],{"repoUrl":27,"stars":26,"forks":30,"topics":33,"description":29},[],"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-H3\u002Ftree\u002FHEAD\u002Fskills\u002Fbrand-promo-video-generator","---\nname: brand-promo-video-generator\ndescription: 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.\nallowed-tools:\n- webfetch\n- hub_image_search\n- hub_analyse_media\n- hub_canvas_get_node\n- hub_canvas_group_recent_outputs\n- hub_generate_image\n- hub_generate_video\n- hub_generate_audio\n- hub_generate_music\n- hub_synthesize_speech\n- hub_video_edit\n- hub_audio_meta\n- task\n---\n\n# Brand Promo Video Generator\n\nCreate a polished short promo video for a brand, product, website, app, shop, or personal project. Use this Skill when the user has a logo, product images, screenshots, a website link, or just a clear idea and wants the agent to turn those materials into a clean brand reel.\n\nThis Hub adaptation replaces third-party Vibe Motion \u002F Remotion implementation details with Hub-native orchestration: source research, asset verification, story planning, image\u002Fvideo generation, optional speech or music, and editing assembly. Do not initialize external projects or depend on npm validators during normal execution.\n\n## Tool Coverage Rule\n\nThe `allowed-tools` list must cover the full production promise in this Skill: source lookup, image preparation\u002Fgeneration, video clip generation, optional speech\u002Fmusic\u002Faudio generation, final editing\u002Fassembly, media inspection, and canvas grouping. If a runtime does not provide one of the listed generation or editing tools, downgrade the deliverable explicitly to a pre-production package instead of claiming that a final promo video can be generated.\n\n## STEP 1: Intake assets and resolve the brief\n\nBefore any story planning or generation, run a required user intake. Ask the user to upload or provide links to the elements that must be verified:\n\n- Logo files or official logo source pages\n- Font files, font names, typography guidance, or official website pages that show brand typography\n- Brand colors, color system, style guide, or pages that clearly show official colors\n- Product images, UI screenshots, packaging, renders, footage, or other brand imagery\n- Product information: official product name, feature list, launch focus, claims, CTA, disclaimers, and target audience\n- Company\u002Fproduct official URL or official source package\n\nTreat user-uploaded assets as usable by default for pre-production and concept planning. Do not repeatedly ask a standalone rights\u002Fpermission question during the first intake unless there is a concrete risk signal, such as a visible third-party watermark, obviously scraped marketplace imagery, contradictory user wording, legal\u002Fmedical\u002Ffinancial compliance claims, or the user asks for commercial publication. Record the source as \"user-provided\" and surface rights caveats in the source summary instead of blocking the flow.\n\nIn the same opening intake, ask the user to choose:\n\n- Target duration, normally 15-30 seconds; recommend 15 seconds when the user wants a fast launch film\n- Aspect ratio; offer common choices such as 16:9, 9:16, 1:1, 4:3, 3:4, or match a supplied reference\n\nAlso identify campaign focus, distribution channel, narration language, on-screen copy language, and visible copy needs when they are not already clear. Do not proceed to creative direction until the user has supplied the usable materials or explicitly confirms which elements are unavailable.\n\nLanguage rule for promo content: choose narration and on-screen copy language from the brand materials, target audience, and platform context, not mechanically from the chat language. If the brand assets and visible source copy are primarily English or global corporate English, default narration and on-screen copy to English unless the user explicitly asks for Chinese localization. If the user is Chinese but says they are testing as a new user, keep chat replies in Chinese, but plan the actual video copy in the language that best fits the brand campaign.\n\nIf a logo, product UI, person, mascot, packaging, font, color system, or other identity-bearing asset cannot be authenticated, stop and ask for an authorized original instead of generating a plausible substitute.\n\n## STEP 2: Build the brand truth sheet\n\nResearch or inspect the strongest available sources and summarize the brand truth sheet before creative production:\n\n1. User-provided original exports\n2. Official company website, static bundle, newsroom, brand portal, media kit, press kit, or official repository\n3. Company-controlled media library\n4. Licensed stock or authorized partner kit\n\nExtract:\n\n- Exact logo variants, clear space, and usage constraints\n- Official fonts or visible typographic behavior\n- Primary, secondary, and dynamic brand colors\n- Brand tone, principles, visual motifs, and interaction language\n- Current product names, features, scenarios, metrics, slogans, CTA, and disclaimers\n- Official photography, renders, UI screenshots, footage, press assets, and media kit material\n\nDo not use logo aggregation sites, search thumbnails, fan recreations, Pinterest reposts, or AI-generated substitutes as identity-bearing sources. Procedural graphics are allowed only as non-representational motion layers: masks, gradients, color fields, grids, glows, particles, trails, typography, verified-data charts, and transition geometry.\n\n## STEP 3: Create a provenance manifest\n\nRecord every identity-bearing asset in a compact manifest that can be delivered to the user. The manifest may be a text node or table and should include:\n\n- Stable asset ID and role\n- Local path or canvas node reference when available\n- Exact source URL or user-provided source note\n- Source type, such as official website, media kit, user-provided original, or licensed stock\n- Verification target used for comparison\n- Rights or publication note\n- Authenticity status: verified, user-supplied, licensed, or blocked\n\nThe manifest does not grant publication rights by itself. If authorization is unclear, label the video as an unofficial concept and tell the user commercial publication requires permission.\n\n## STEP 4: Choose the story spine\n\nPresent 2-3 concise creative directions when the user has not already chosen one, recommend one, and continue after confirmation. Use the product category to pick a spine:\n\n- AI \u002F SaaS: user intent -> thinking or planning -> capabilities -> execution -> useful output -> proof -> logo\n- Physical product: hero reveal -> interaction -> feature macro -> usage context -> result -> logo\n- Service \u002F company: context -> process -> evidence -> outcome -> promise -> logo\n- Image-led brand: authentic imagery -> visual motif -> benefit -> emotional payoff -> logo\n\nKeep the story product-specific. Show actual features, interactions, scenarios, outputs, and proof instead of hiding the story behind abstract effects.\n\n## STEP 5: Plan exact beats\n\nPlan a frame-aware timeline before generation. Use 30fps as the planning convention unless the output pipeline requires otherwise.\n\nFor a 15-second film, target 5-8 major beats. For a 30-second film, target 8-12 major beats. Each beat should define:\n\n- Start and end time or frame range\n- Visual owner and authentic asset IDs\n- Primary action\n- Product or brand proof shown in the shot\n- Copy and readable hold\n- Color state\n- Incoming and outgoing transition\n- Motion intent: setup, anticipation, commitment, impact, brake, settle\n\nA useful 15-second pattern is: brand hook, user intent or setup, product mechanism, capabilities or scenarios, output or proof, product payoff, final logo and CTA. Use 6-12 frame overlaps when outgoing motion naturally supplies the next shot.\n\n## STEP 6: Direct the motion language\n\nBuild intensity with control:\n\n- Let product motion, cursor paths, UI flow, light, scrolling content, object edges, or matched geometry drive transitions\n- Use 2-5 deliberate color states tied to meaning\n- Keep one primary action per beat; delay secondary layers slightly\n- Establish 2-3 high-energy peaks and quieter braking moments\n- Preserve readable silhouettes, copy, and logo clear space\n- Avoid fake HUDs, arbitrary glass cards, decorative text walls, unverified metrics, and identical easing everywhere\n\nFor AI products, include at least one readable chain such as: prompt -> planning -> parallel capabilities -> generated result -> proof. For physical or service products, show cause and effect from user action to concrete outcome.\n\n## STEP 7: Hard confirmation before generation\n\nBefore generating any video, image sequence, speech, music, or final edit, stop and show the user the completed pre-production package:\n\n- Provenance manifest or source summary\n- Brand truth sheet\n- Chosen creative direction\n- Exact beat \u002F shot plan\n- Visible copy, CTA, narration, and audio plan\n- Known authenticity, rights, or placeholder caveats\n\nUse a concise confirmation step before generation. If the user clearly expresses approval or intent to proceed after seeing the pre-production package — for example \"confirm\", \"generate\", \"go ahead\", \"continue\", \"next\", \"可以\", \"继续\", \"下一步\", or similar — treat it as permission to generate, unless the message also asks for changes. If the user asks to skip the process, still provide a compact source summary, brand truth sheet, and beat plan first, then proceed when they indicate approval. Offer revision choices only when the user's reply is ambiguous or requests changes.\n\n## STEP 8: Produce Hub assets\n\nUse Hub-native generation and editing only after the hard confirmation gate has passed. Keep each dispatch self-contained with the chosen model, aspect ratio, authentic reference paths, and original request.\n\nTypical production flow:\n\n1. Generate or prepare verified still frames, UI plates, product hero frames, or motion-ready story images.\n2. Generate video clips from those frames or from precise text prompts, preserving the same ratio and brand assets.\n3. Default audio policy for native brand reels: when the user asks for BGM, music, soundtrack, ambient sound, or says nothing beyond needing a finished promo video, prefer video-native audio from the selected video model instead of generating a separate music track. For the default MiniMax H3 route, set native audio on (`generate_audio=true`) and prompt for brand-safe instrumental music \u002F UI sound design inside the video prompt.\n4. Generate separate speech or music only when the user explicitly needs controllable narration, voiceover, dialogue, replaceable standalone BGM, exact music duration independent of the video, post-production remixing, or when the selected video model cannot generate suitable audio. Do not duplicate a soundtrack between video-native audio and separate audio generation.\n5. Assemble clips, any explicitly separate audio, and final brand lockup in editing. Add subtitles only when the user explicitly asks for subtitles.\n\nDo not redraw or approximate logos, wordmarks, product UI, packaging, mascot, person, or brand scene. Use generated material only for abstract motion, atmosphere, transition geometry, or clearly conceptual scenes that do not impersonate official product evidence.\n\n## STEP 9: Verify before delivery\n\nBefore final response, check:\n\n- The logo and identity-bearing assets came from verified or user-authorized sources\n- Product names, feature wording, claims, metrics, slogans, and CTA match official sources or are clearly marked as concept copy\n- The video duration, aspect ratio, and language match the brief\n- Copy is readable and not overcrowded\n- The final logo is not stretched, cropped, or rebuilt\n- Motion has clear visual ownership and does not obscure the product\n- The output is on the canvas and multi-asset outputs are grouped\n\nIf the output fails an authenticity check, replace the questionable asset with an official\u002Fuser-authorized source or stop and ask for the asset. Never improve an imitation.\n\n## STEP 10: Deliver\n\nProvide:\n\n- Final video path or canvas output\n- Duration, aspect ratio, and language\n- Short creative summary\n- Provenance manifest or source summary\n- Rights\u002Fdisclaimer note when needed\n- Specific suggestions for the next iteration, such as pacing, claim clarity, CTA, audio, or platform crop\n\n## Failure recovery\n\n- Wrong or approximate logo: remove it, locate the current official file or ask for the user's original, then regenerate or re-edit.\n- Fake-looking product\u002FUI: replace with official, user-supplied, or licensed media. Do not polish the imitation.\n- Beautiful but generic: add a complete product interaction, verified claim, or real output.\n- Fast but chaotic: reduce simultaneous actions, assign a visual owner, and preserve matched motion across cuts.\n- Smooth but slow: shorten holds, overlap transitions, and brake only around key messages.\n- Asset unavailable: ask for an authorized original; never guess.\n",{"data":37,"body":52},{"name":4,"description":6,"allowed-tools":38},[39,40,41,42,43,44,45,46,47,48,49,50,51],"webfetch","hub_image_search","hub_analyse_media","hub_canvas_get_node","hub_canvas_group_recent_outputs","hub_generate_image","hub_generate_video","hub_generate_audio","hub_generate_music","hub_synthesize_speech","hub_video_edit","hub_audio_meta","task",{"type":53,"children":54},"root",[55,63,69,74,81,95,101,106,141,146,151,164,169,174,179,185,190,214,219,252,257,263,268,306,311,317,322,345,350,356,361,366,409,414,420,425,458,463,469,474,507,512,518,523,528,564,569,575,580,618,623,629,634,666,672],{"type":56,"tag":57,"props":58,"children":59},"element","h1",{"id":4},[60],{"type":61,"value":62},"text","Brand Promo Video Generator",{"type":56,"tag":64,"props":65,"children":66},"p",{},[67],{"type":61,"value":68},"Create a polished short promo video for a brand, product, website, app, shop, or personal project. Use this Skill when the user has a logo, product images, screenshots, a website link, or just a clear idea and wants the agent to turn those materials into a clean brand reel.",{"type":56,"tag":64,"props":70,"children":71},{},[72],{"type":61,"value":73},"This Hub adaptation replaces third-party Vibe Motion \u002F Remotion implementation details with Hub-native orchestration: source research, asset verification, story planning, image\u002Fvideo generation, optional speech or music, and editing assembly. Do not initialize external projects or depend on npm validators during normal execution.",{"type":56,"tag":75,"props":76,"children":78},"h2",{"id":77},"tool-coverage-rule",[79],{"type":61,"value":80},"Tool Coverage Rule",{"type":56,"tag":64,"props":82,"children":83},{},[84,86,93],{"type":61,"value":85},"The ",{"type":56,"tag":87,"props":88,"children":90},"code",{"className":89},[],[91],{"type":61,"value":92},"allowed-tools",{"type":61,"value":94}," list must cover the full production promise in this Skill: source lookup, image preparation\u002Fgeneration, video clip generation, optional speech\u002Fmusic\u002Faudio generation, final editing\u002Fassembly, media inspection, and canvas grouping. If a runtime does not provide one of the listed generation or editing tools, downgrade the deliverable explicitly to a pre-production package instead of claiming that a final promo video can be generated.",{"type":56,"tag":75,"props":96,"children":98},{"id":97},"step-1-intake-assets-and-resolve-the-brief",[99],{"type":61,"value":100},"STEP 1: Intake assets and resolve the brief",{"type":56,"tag":64,"props":102,"children":103},{},[104],{"type":61,"value":105},"Before any story planning or generation, run a required user intake. Ask the user to upload or provide links to the elements that must be verified:",{"type":56,"tag":107,"props":108,"children":109},"ul",{},[110,116,121,126,131,136],{"type":56,"tag":111,"props":112,"children":113},"li",{},[114],{"type":61,"value":115},"Logo files or official logo source pages",{"type":56,"tag":111,"props":117,"children":118},{},[119],{"type":61,"value":120},"Font files, font names, typography guidance, or official website pages that show brand typography",{"type":56,"tag":111,"props":122,"children":123},{},[124],{"type":61,"value":125},"Brand colors, color system, style guide, or pages that clearly show official colors",{"type":56,"tag":111,"props":127,"children":128},{},[129],{"type":61,"value":130},"Product images, UI screenshots, packaging, renders, footage, or other brand imagery",{"type":56,"tag":111,"props":132,"children":133},{},[134],{"type":61,"value":135},"Product information: official product name, feature list, launch focus, claims, CTA, disclaimers, and target audience",{"type":56,"tag":111,"props":137,"children":138},{},[139],{"type":61,"value":140},"Company\u002Fproduct official URL or official source package",{"type":56,"tag":64,"props":142,"children":143},{},[144],{"type":61,"value":145},"Treat user-uploaded assets as usable by default for pre-production and concept planning. Do not repeatedly ask a standalone rights\u002Fpermission question during the first intake unless there is a concrete risk signal, such as a visible third-party watermark, obviously scraped marketplace imagery, contradictory user wording, legal\u002Fmedical\u002Ffinancial compliance claims, or the user asks for commercial publication. Record the source as \"user-provided\" and surface rights caveats in the source summary instead of blocking the flow.",{"type":56,"tag":64,"props":147,"children":148},{},[149],{"type":61,"value":150},"In the same opening intake, ask the user to choose:",{"type":56,"tag":107,"props":152,"children":153},{},[154,159],{"type":56,"tag":111,"props":155,"children":156},{},[157],{"type":61,"value":158},"Target duration, normally 15-30 seconds; recommend 15 seconds when the user wants a fast launch film",{"type":56,"tag":111,"props":160,"children":161},{},[162],{"type":61,"value":163},"Aspect ratio; offer common choices such as 16:9, 9:16, 1:1, 4:3, 3:4, or match a supplied reference",{"type":56,"tag":64,"props":165,"children":166},{},[167],{"type":61,"value":168},"Also identify campaign focus, distribution channel, narration language, on-screen copy language, and visible copy needs when they are not already clear. Do not proceed to creative direction until the user has supplied the usable materials or explicitly confirms which elements are unavailable.",{"type":56,"tag":64,"props":170,"children":171},{},[172],{"type":61,"value":173},"Language rule for promo content: choose narration and on-screen copy language from the brand materials, target audience, and platform context, not mechanically from the chat language. If the brand assets and visible source copy are primarily English or global corporate English, default narration and on-screen copy to English unless the user explicitly asks for Chinese localization. If the user is Chinese but says they are testing as a new user, keep chat replies in Chinese, but plan the actual video copy in the language that best fits the brand campaign.",{"type":56,"tag":64,"props":175,"children":176},{},[177],{"type":61,"value":178},"If a logo, product UI, person, mascot, packaging, font, color system, or other identity-bearing asset cannot be authenticated, stop and ask for an authorized original instead of generating a plausible substitute.",{"type":56,"tag":75,"props":180,"children":182},{"id":181},"step-2-build-the-brand-truth-sheet",[183],{"type":61,"value":184},"STEP 2: Build the brand truth sheet",{"type":56,"tag":64,"props":186,"children":187},{},[188],{"type":61,"value":189},"Research or inspect the strongest available sources and summarize the brand truth sheet before creative production:",{"type":56,"tag":191,"props":192,"children":193},"ol",{},[194,199,204,209],{"type":56,"tag":111,"props":195,"children":196},{},[197],{"type":61,"value":198},"User-provided original exports",{"type":56,"tag":111,"props":200,"children":201},{},[202],{"type":61,"value":203},"Official company website, static bundle, newsroom, brand portal, media kit, press kit, or official repository",{"type":56,"tag":111,"props":205,"children":206},{},[207],{"type":61,"value":208},"Company-controlled media library",{"type":56,"tag":111,"props":210,"children":211},{},[212],{"type":61,"value":213},"Licensed stock or authorized partner kit",{"type":56,"tag":64,"props":215,"children":216},{},[217],{"type":61,"value":218},"Extract:",{"type":56,"tag":107,"props":220,"children":221},{},[222,227,232,237,242,247],{"type":56,"tag":111,"props":223,"children":224},{},[225],{"type":61,"value":226},"Exact logo variants, clear space, and usage constraints",{"type":56,"tag":111,"props":228,"children":229},{},[230],{"type":61,"value":231},"Official fonts or visible typographic behavior",{"type":56,"tag":111,"props":233,"children":234},{},[235],{"type":61,"value":236},"Primary, secondary, and dynamic brand colors",{"type":56,"tag":111,"props":238,"children":239},{},[240],{"type":61,"value":241},"Brand tone, principles, visual motifs, and interaction language",{"type":56,"tag":111,"props":243,"children":244},{},[245],{"type":61,"value":246},"Current product names, features, scenarios, metrics, slogans, CTA, and disclaimers",{"type":56,"tag":111,"props":248,"children":249},{},[250],{"type":61,"value":251},"Official photography, renders, UI screenshots, footage, press assets, and media kit material",{"type":56,"tag":64,"props":253,"children":254},{},[255],{"type":61,"value":256},"Do not use logo aggregation sites, search thumbnails, fan recreations, Pinterest reposts, or AI-generated substitutes as identity-bearing sources. Procedural graphics are allowed only as non-representational motion layers: masks, gradients, color fields, grids, glows, particles, trails, typography, verified-data charts, and transition geometry.",{"type":56,"tag":75,"props":258,"children":260},{"id":259},"step-3-create-a-provenance-manifest",[261],{"type":61,"value":262},"STEP 3: Create a provenance manifest",{"type":56,"tag":64,"props":264,"children":265},{},[266],{"type":61,"value":267},"Record every identity-bearing asset in a compact manifest that can be delivered to the user. The manifest may be a text node or table and should include:",{"type":56,"tag":107,"props":269,"children":270},{},[271,276,281,286,291,296,301],{"type":56,"tag":111,"props":272,"children":273},{},[274],{"type":61,"value":275},"Stable asset ID and role",{"type":56,"tag":111,"props":277,"children":278},{},[279],{"type":61,"value":280},"Local path or canvas node reference when available",{"type":56,"tag":111,"props":282,"children":283},{},[284],{"type":61,"value":285},"Exact source URL or user-provided source note",{"type":56,"tag":111,"props":287,"children":288},{},[289],{"type":61,"value":290},"Source type, such as official website, media kit, user-provided original, or licensed stock",{"type":56,"tag":111,"props":292,"children":293},{},[294],{"type":61,"value":295},"Verification target used for comparison",{"type":56,"tag":111,"props":297,"children":298},{},[299],{"type":61,"value":300},"Rights or publication note",{"type":56,"tag":111,"props":302,"children":303},{},[304],{"type":61,"value":305},"Authenticity status: verified, user-supplied, licensed, or blocked",{"type":56,"tag":64,"props":307,"children":308},{},[309],{"type":61,"value":310},"The manifest does not grant publication rights by itself. If authorization is unclear, label the video as an unofficial concept and tell the user commercial publication requires permission.",{"type":56,"tag":75,"props":312,"children":314},{"id":313},"step-4-choose-the-story-spine",[315],{"type":61,"value":316},"STEP 4: Choose the story spine",{"type":56,"tag":64,"props":318,"children":319},{},[320],{"type":61,"value":321},"Present 2-3 concise creative directions when the user has not already chosen one, recommend one, and continue after confirmation. Use the product category to pick a spine:",{"type":56,"tag":107,"props":323,"children":324},{},[325,330,335,340],{"type":56,"tag":111,"props":326,"children":327},{},[328],{"type":61,"value":329},"AI \u002F SaaS: user intent -> thinking or planning -> capabilities -> execution -> useful output -> proof -> logo",{"type":56,"tag":111,"props":331,"children":332},{},[333],{"type":61,"value":334},"Physical product: hero reveal -> interaction -> feature macro -> usage context -> result -> logo",{"type":56,"tag":111,"props":336,"children":337},{},[338],{"type":61,"value":339},"Service \u002F company: context -> process -> evidence -> outcome -> promise -> logo",{"type":56,"tag":111,"props":341,"children":342},{},[343],{"type":61,"value":344},"Image-led brand: authentic imagery -> visual motif -> benefit -> emotional payoff -> logo",{"type":56,"tag":64,"props":346,"children":347},{},[348],{"type":61,"value":349},"Keep the story product-specific. Show actual features, interactions, scenarios, outputs, and proof instead of hiding the story behind abstract effects.",{"type":56,"tag":75,"props":351,"children":353},{"id":352},"step-5-plan-exact-beats",[354],{"type":61,"value":355},"STEP 5: Plan exact beats",{"type":56,"tag":64,"props":357,"children":358},{},[359],{"type":61,"value":360},"Plan a frame-aware timeline before generation. Use 30fps as the planning convention unless the output pipeline requires otherwise.",{"type":56,"tag":64,"props":362,"children":363},{},[364],{"type":61,"value":365},"For a 15-second film, target 5-8 major beats. For a 30-second film, target 8-12 major beats. Each beat should define:",{"type":56,"tag":107,"props":367,"children":368},{},[369,374,379,384,389,394,399,404],{"type":56,"tag":111,"props":370,"children":371},{},[372],{"type":61,"value":373},"Start and end time or frame range",{"type":56,"tag":111,"props":375,"children":376},{},[377],{"type":61,"value":378},"Visual owner and authentic asset IDs",{"type":56,"tag":111,"props":380,"children":381},{},[382],{"type":61,"value":383},"Primary action",{"type":56,"tag":111,"props":385,"children":386},{},[387],{"type":61,"value":388},"Product or brand proof shown in the shot",{"type":56,"tag":111,"props":390,"children":391},{},[392],{"type":61,"value":393},"Copy and readable hold",{"type":56,"tag":111,"props":395,"children":396},{},[397],{"type":61,"value":398},"Color state",{"type":56,"tag":111,"props":400,"children":401},{},[402],{"type":61,"value":403},"Incoming and outgoing transition",{"type":56,"tag":111,"props":405,"children":406},{},[407],{"type":61,"value":408},"Motion intent: setup, anticipation, commitment, impact, brake, settle",{"type":56,"tag":64,"props":410,"children":411},{},[412],{"type":61,"value":413},"A useful 15-second pattern is: brand hook, user intent or setup, product mechanism, capabilities or scenarios, output or proof, product payoff, final logo and CTA. Use 6-12 frame overlaps when outgoing motion naturally supplies the next shot.",{"type":56,"tag":75,"props":415,"children":417},{"id":416},"step-6-direct-the-motion-language",[418],{"type":61,"value":419},"STEP 6: Direct the motion language",{"type":56,"tag":64,"props":421,"children":422},{},[423],{"type":61,"value":424},"Build intensity with control:",{"type":56,"tag":107,"props":426,"children":427},{},[428,433,438,443,448,453],{"type":56,"tag":111,"props":429,"children":430},{},[431],{"type":61,"value":432},"Let product motion, cursor paths, UI flow, light, scrolling content, object edges, or matched geometry drive transitions",{"type":56,"tag":111,"props":434,"children":435},{},[436],{"type":61,"value":437},"Use 2-5 deliberate color states tied to meaning",{"type":56,"tag":111,"props":439,"children":440},{},[441],{"type":61,"value":442},"Keep one primary action per beat; delay secondary layers slightly",{"type":56,"tag":111,"props":444,"children":445},{},[446],{"type":61,"value":447},"Establish 2-3 high-energy peaks and quieter braking moments",{"type":56,"tag":111,"props":449,"children":450},{},[451],{"type":61,"value":452},"Preserve readable silhouettes, copy, and logo clear space",{"type":56,"tag":111,"props":454,"children":455},{},[456],{"type":61,"value":457},"Avoid fake HUDs, arbitrary glass cards, decorative text walls, unverified metrics, and identical easing everywhere",{"type":56,"tag":64,"props":459,"children":460},{},[461],{"type":61,"value":462},"For AI products, include at least one readable chain such as: prompt -> planning -> parallel capabilities -> generated result -> proof. For physical or service products, show cause and effect from user action to concrete outcome.",{"type":56,"tag":75,"props":464,"children":466},{"id":465},"step-7-hard-confirmation-before-generation",[467],{"type":61,"value":468},"STEP 7: Hard confirmation before generation",{"type":56,"tag":64,"props":470,"children":471},{},[472],{"type":61,"value":473},"Before generating any video, image sequence, speech, music, or final edit, stop and show the user the completed pre-production package:",{"type":56,"tag":107,"props":475,"children":476},{},[477,482,487,492,497,502],{"type":56,"tag":111,"props":478,"children":479},{},[480],{"type":61,"value":481},"Provenance manifest or source summary",{"type":56,"tag":111,"props":483,"children":484},{},[485],{"type":61,"value":486},"Brand truth sheet",{"type":56,"tag":111,"props":488,"children":489},{},[490],{"type":61,"value":491},"Chosen creative direction",{"type":56,"tag":111,"props":493,"children":494},{},[495],{"type":61,"value":496},"Exact beat \u002F shot plan",{"type":56,"tag":111,"props":498,"children":499},{},[500],{"type":61,"value":501},"Visible copy, CTA, narration, and audio plan",{"type":56,"tag":111,"props":503,"children":504},{},[505],{"type":61,"value":506},"Known authenticity, rights, or placeholder caveats",{"type":56,"tag":64,"props":508,"children":509},{},[510],{"type":61,"value":511},"Use a concise confirmation step before generation. If the user clearly expresses approval or intent to proceed after seeing the pre-production package — for example \"confirm\", \"generate\", \"go ahead\", \"continue\", \"next\", \"可以\", \"继续\", \"下一步\", or similar — treat it as permission to generate, unless the message also asks for changes. If the user asks to skip the process, still provide a compact source summary, brand truth sheet, and beat plan first, then proceed when they indicate approval. Offer revision choices only when the user's reply is ambiguous or requests changes.",{"type":56,"tag":75,"props":513,"children":515},{"id":514},"step-8-produce-hub-assets",[516],{"type":61,"value":517},"STEP 8: Produce Hub assets",{"type":56,"tag":64,"props":519,"children":520},{},[521],{"type":61,"value":522},"Use Hub-native generation and editing only after the hard confirmation gate has passed. Keep each dispatch self-contained with the chosen model, aspect ratio, authentic reference paths, and original request.",{"type":56,"tag":64,"props":524,"children":525},{},[526],{"type":61,"value":527},"Typical production flow:",{"type":56,"tag":191,"props":529,"children":530},{},[531,536,541,554,559],{"type":56,"tag":111,"props":532,"children":533},{},[534],{"type":61,"value":535},"Generate or prepare verified still frames, UI plates, product hero frames, or motion-ready story images.",{"type":56,"tag":111,"props":537,"children":538},{},[539],{"type":61,"value":540},"Generate video clips from those frames or from precise text prompts, preserving the same ratio and brand assets.",{"type":56,"tag":111,"props":542,"children":543},{},[544,546,552],{"type":61,"value":545},"Default audio policy for native brand reels: when the user asks for BGM, music, soundtrack, ambient sound, or says nothing beyond needing a finished promo video, prefer video-native audio from the selected video model instead of generating a separate music track. For the default MiniMax H3 route, set native audio on (",{"type":56,"tag":87,"props":547,"children":549},{"className":548},[],[550],{"type":61,"value":551},"generate_audio=true",{"type":61,"value":553},") and prompt for brand-safe instrumental music \u002F UI sound design inside the video prompt.",{"type":56,"tag":111,"props":555,"children":556},{},[557],{"type":61,"value":558},"Generate separate speech or music only when the user explicitly needs controllable narration, voiceover, dialogue, replaceable standalone BGM, exact music duration independent of the video, post-production remixing, or when the selected video model cannot generate suitable audio. Do not duplicate a soundtrack between video-native audio and separate audio generation.",{"type":56,"tag":111,"props":560,"children":561},{},[562],{"type":61,"value":563},"Assemble clips, any explicitly separate audio, and final brand lockup in editing. Add subtitles only when the user explicitly asks for subtitles.",{"type":56,"tag":64,"props":565,"children":566},{},[567],{"type":61,"value":568},"Do not redraw or approximate logos, wordmarks, product UI, packaging, mascot, person, or brand scene. Use generated material only for abstract motion, atmosphere, transition geometry, or clearly conceptual scenes that do not impersonate official product evidence.",{"type":56,"tag":75,"props":570,"children":572},{"id":571},"step-9-verify-before-delivery",[573],{"type":61,"value":574},"STEP 9: Verify before delivery",{"type":56,"tag":64,"props":576,"children":577},{},[578],{"type":61,"value":579},"Before final response, check:",{"type":56,"tag":107,"props":581,"children":582},{},[583,588,593,598,603,608,613],{"type":56,"tag":111,"props":584,"children":585},{},[586],{"type":61,"value":587},"The logo and identity-bearing assets came from verified or user-authorized sources",{"type":56,"tag":111,"props":589,"children":590},{},[591],{"type":61,"value":592},"Product names, feature wording, claims, metrics, slogans, and CTA match official sources or are clearly marked as concept copy",{"type":56,"tag":111,"props":594,"children":595},{},[596],{"type":61,"value":597},"The video duration, aspect ratio, and language match the brief",{"type":56,"tag":111,"props":599,"children":600},{},[601],{"type":61,"value":602},"Copy is readable and not overcrowded",{"type":56,"tag":111,"props":604,"children":605},{},[606],{"type":61,"value":607},"The final logo is not stretched, cropped, or rebuilt",{"type":56,"tag":111,"props":609,"children":610},{},[611],{"type":61,"value":612},"Motion has clear visual ownership and does not obscure the product",{"type":56,"tag":111,"props":614,"children":615},{},[616],{"type":61,"value":617},"The output is on the canvas and multi-asset outputs are grouped",{"type":56,"tag":64,"props":619,"children":620},{},[621],{"type":61,"value":622},"If the output fails an authenticity check, replace the questionable asset with an official\u002Fuser-authorized source or stop and ask for the asset. Never improve an imitation.",{"type":56,"tag":75,"props":624,"children":626},{"id":625},"step-10-deliver",[627],{"type":61,"value":628},"STEP 10: Deliver",{"type":56,"tag":64,"props":630,"children":631},{},[632],{"type":61,"value":633},"Provide:",{"type":56,"tag":107,"props":635,"children":636},{},[637,642,647,652,656,661],{"type":56,"tag":111,"props":638,"children":639},{},[640],{"type":61,"value":641},"Final video path or canvas output",{"type":56,"tag":111,"props":643,"children":644},{},[645],{"type":61,"value":646},"Duration, aspect ratio, and language",{"type":56,"tag":111,"props":648,"children":649},{},[650],{"type":61,"value":651},"Short creative summary",{"type":56,"tag":111,"props":653,"children":654},{},[655],{"type":61,"value":481},{"type":56,"tag":111,"props":657,"children":658},{},[659],{"type":61,"value":660},"Rights\u002Fdisclaimer note when needed",{"type":56,"tag":111,"props":662,"children":663},{},[664],{"type":61,"value":665},"Specific suggestions for the next iteration, such as pacing, claim clarity, CTA, audio, or platform crop",{"type":56,"tag":75,"props":667,"children":669},{"id":668},"failure-recovery",[670],{"type":61,"value":671},"Failure recovery",{"type":56,"tag":107,"props":673,"children":674},{},[675,680,685,690,695,700],{"type":56,"tag":111,"props":676,"children":677},{},[678],{"type":61,"value":679},"Wrong or approximate logo: remove it, locate the current official file or ask for the user's original, then regenerate or re-edit.",{"type":56,"tag":111,"props":681,"children":682},{},[683],{"type":61,"value":684},"Fake-looking product\u002FUI: replace with official, user-supplied, or licensed media. Do not polish the imitation.",{"type":56,"tag":111,"props":686,"children":687},{},[688],{"type":61,"value":689},"Beautiful but generic: add a complete product interaction, verified claim, or real output.",{"type":56,"tag":111,"props":691,"children":692},{},[693],{"type":61,"value":694},"Fast but chaotic: reduce simultaneous actions, assign a visual owner, and preserve matched motion across cuts.",{"type":56,"tag":111,"props":696,"children":697},{},[698],{"type":61,"value":699},"Smooth but slow: shorten holds, overlap transitions, and brake only around key messages.",{"type":56,"tag":111,"props":701,"children":702},{},[703],{"type":61,"value":704},"Asset unavailable: ask for an authorized original; never guess.",{"items":706,"total":905},[707,731,745,764,779,799,817,835,850,866,885,895],{"slug":708,"name":708,"fn":709,"description":710,"org":711,"tags":712,"stars":728,"repoUrl":729,"updatedAt":730},"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},[713,716,719,722,725],{"name":714,"slug":715,"type":16},"Accessibility","accessibility",{"name":717,"slug":718,"type":16},"Android","android",{"name":720,"slug":721,"type":16},"Kotlin","kotlin",{"name":723,"slug":724,"type":16},"Mobile","mobile",{"name":726,"slug":727,"type":16},"UI Components","ui-components",13030,"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002Fskills","2026-07-13T06:16:54.247834",{"slug":732,"name":732,"fn":733,"description":734,"org":735,"tags":736,"stars":728,"repoUrl":729,"updatedAt":744},"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},[737,740,743],{"name":738,"slug":739,"type":16},"Agents","agents",{"name":741,"slug":742,"type":16},"Audio","audio",{"name":21,"slug":22,"type":16},"2026-07-13T06:16:35.130644",{"slug":746,"name":746,"fn":747,"description":748,"org":749,"tags":750,"stars":728,"repoUrl":729,"updatedAt":763},"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},[751,754,757,760],{"name":752,"slug":753,"type":16},"Design","design",{"name":755,"slug":756,"type":16},"Presentations","presentations",{"name":758,"slug":759,"type":16},"Themes","themes",{"name":761,"slug":762,"type":16},"Typography","typography","2026-07-13T06:17:02.785587",{"slug":765,"name":765,"fn":766,"description":767,"org":768,"tags":769,"stars":728,"repoUrl":729,"updatedAt":778},"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},[770,771,774,777],{"name":752,"slug":753,"type":16},{"name":772,"slug":773,"type":16},"Design System","design-system",{"name":775,"slug":776,"type":16},"PowerPoint","powerpoint",{"name":755,"slug":756,"type":16},"2026-07-13T06:17:10.398389",{"slug":780,"name":780,"fn":781,"description":782,"org":783,"tags":784,"stars":728,"repoUrl":729,"updatedAt":798},"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},[785,788,791,792,795],{"name":786,"slug":787,"type":16},"Dart","dart",{"name":789,"slug":790,"type":16},"Flutter","flutter",{"name":723,"slug":724,"type":16},{"name":793,"slug":794,"type":16},"Performance","performance",{"name":796,"slug":797,"type":16},"State Management","state-management","2026-07-13T06:16:36.626679",{"slug":800,"name":800,"fn":801,"description":802,"org":803,"tags":804,"stars":728,"repoUrl":729,"updatedAt":816},"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},[805,808,809,810,813],{"name":806,"slug":807,"type":16},"Animation","animation",{"name":21,"slug":22,"type":16},{"name":752,"slug":753,"type":16},{"name":811,"slug":812,"type":16},"Frontend","frontend",{"name":814,"slug":815,"type":16},"Web Development","web-development","2026-07-13T06:16:39.108827",{"slug":818,"name":818,"fn":819,"description":820,"org":821,"tags":822,"stars":728,"repoUrl":729,"updatedAt":834},"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},[823,826,827,830,833],{"name":824,"slug":825,"type":16},"Backend","backend",{"name":811,"slug":812,"type":16},{"name":828,"slug":829,"type":16},"Full-stack","full-stack",{"name":831,"slug":832,"type":16},"REST API","rest-api",{"name":814,"slug":815,"type":16},"2026-07-13T06:16:43.219005",{"slug":836,"name":836,"fn":837,"description":838,"org":839,"tags":840,"stars":728,"repoUrl":729,"updatedAt":849},"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},[841,842,843,846],{"name":806,"slug":807,"type":16},{"name":21,"slug":22,"type":16},{"name":844,"slug":845,"type":16},"Images","images",{"name":847,"slug":848,"type":16},"Media","media","2026-07-13T06:16:51.74461",{"slug":851,"name":851,"fn":852,"description":853,"org":854,"tags":855,"stars":728,"repoUrl":729,"updatedAt":865},"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},[856,857,860,861,864],{"name":714,"slug":715,"type":16},{"name":858,"slug":859,"type":16},"iOS","ios",{"name":723,"slug":724,"type":16},{"name":862,"slug":863,"type":16},"SwiftUI","swiftui",{"name":726,"slug":727,"type":16},"2026-07-13T06:16:55.686092",{"slug":867,"name":867,"fn":868,"description":869,"org":870,"tags":871,"stars":728,"repoUrl":729,"updatedAt":884},"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},[872,875,878,881],{"name":873,"slug":874,"type":16},"Documents","documents",{"name":876,"slug":877,"type":16},"DOCX","docx",{"name":879,"slug":880,"type":16},"Office","office",{"name":882,"slug":883,"type":16},"Templates","templates","2026-07-13T06:16:40.461868",{"slug":886,"name":886,"fn":887,"description":888,"org":889,"tags":890,"stars":728,"repoUrl":729,"updatedAt":894},"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},[891,892,893],{"name":741,"slug":742,"type":16},{"name":21,"slug":22,"type":16},{"name":847,"slug":848,"type":16},"2026-07-13T06:16:50.381758",{"slug":896,"name":896,"fn":897,"description":898,"org":899,"tags":900,"stars":728,"repoUrl":729,"updatedAt":904},"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},[901,902,903],{"name":741,"slug":742,"type":16},{"name":21,"slug":22,"type":16},{"name":847,"slug":848,"type":16},"2026-07-13T06:16:57.002997",47,{"items":907,"total":993},[908,921,928,941,956,969,982],{"slug":909,"name":909,"fn":910,"description":911,"org":912,"tags":913,"stars":26,"repoUrl":27,"updatedAt":920},"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},[914,917,918,919],{"name":915,"slug":916,"type":16},"3D","3d",{"name":806,"slug":807,"type":16},{"name":21,"slug":22,"type":16},{"name":24,"slug":25,"type":16},"2026-08-08T04:19:20.46802",{"slug":4,"name":4,"fn":5,"description":6,"org":922,"tags":923,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[924,925,926,927],{"name":14,"slug":15,"type":16},{"name":21,"slug":22,"type":16},{"name":18,"slug":19,"type":16},{"name":24,"slug":25,"type":16},{"slug":929,"name":929,"fn":930,"description":931,"org":932,"tags":933,"stars":26,"repoUrl":27,"updatedAt":940},"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},[934,935,936,937],{"name":806,"slug":807,"type":16},{"name":21,"slug":22,"type":16},{"name":752,"slug":753,"type":16},{"name":938,"slug":939,"type":16},"Game Development","game-development","2026-08-08T04:19:07.313539",{"slug":942,"name":942,"fn":943,"description":944,"org":945,"tags":946,"stars":26,"repoUrl":27,"updatedAt":955},"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},[947,948,951,954],{"name":21,"slug":22,"type":16},{"name":949,"slug":950,"type":16},"Multimodal","multimodal",{"name":952,"slug":953,"type":16},"Prompt Engineering","prompt-engineering",{"name":24,"slug":25,"type":16},"2026-08-08T04:19:19.631186",{"slug":957,"name":957,"fn":958,"description":959,"org":960,"tags":961,"stars":26,"repoUrl":27,"updatedAt":968},"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},[962,963,964,967],{"name":806,"slug":807,"type":16},{"name":21,"slug":22,"type":16},{"name":965,"slug":966,"type":16},"Generative Art","generative-art",{"name":24,"slug":25,"type":16},"2026-08-08T04:19:09.002948",{"slug":970,"name":970,"fn":971,"description":972,"org":973,"tags":974,"stars":26,"repoUrl":27,"updatedAt":981},"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},[975,976,979,980],{"name":21,"slug":22,"type":16},{"name":977,"slug":978,"type":16},"E-commerce","e-commerce",{"name":18,"slug":19,"type":16},{"name":24,"slug":25,"type":16},"2026-08-08T04:19:12.135191",{"slug":983,"name":983,"fn":984,"description":985,"org":986,"tags":987,"stars":26,"repoUrl":27,"updatedAt":992},"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},[988,989,990,991],{"name":14,"slug":15,"type":16},{"name":21,"slug":22,"type":16},{"name":761,"slug":762,"type":16},{"name":24,"slug":25,"type":16},"2026-08-08T04:19:18.794688",9]