[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BSE8S4ZGQWEDPMJMGS09AR":3,"skill-same:01M7BSE8S4ZGQWEDPMJMGS09AR":71},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":44,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M7BSE8S4ZGQWEDPMJMGS09AR","video-shortform",null,"Short-form video generation skill — 3-10 second clips for product\nreveals, motion teasers, ambient loops. Defaults to Seedance 2 but\nworks the same with Kling 3 \u002F 4, Veo 3 or Sora 2. Output is one MP4\nsaved to the project folder. When the workspace also ships an\ninteractive-video \u002F hyperframes skill, prefer composing several short\nshots into a single timeline rather than one long monolithic clip.","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002Fplugins\u002F_official\u002Fexamples\u002Fvideo-shortform\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: video-shortform\ndescription: |\n  Short-form video generation skill — 3-10 second clips for product\n  reveals, motion teasers, ambient loops. Defaults to Seedance 2 but\n  works the same with Kling 3 \u002F 4, Veo 3 or Sora 2. Output is one MP4\n  saved to the project folder. When the workspace also ships an\n  interactive-video \u002F hyperframes skill, prefer composing several short\n  shots into a single timeline rather than one long monolithic clip.\ntriggers:\n  - \"video\"\n  - \"clip\"\n  - \"shortform\"\n  - \"reel\"\n  - \"短视频\"\n  - \"动效\"\nod:\n  mode: video\n  surface: video\n  scenario: marketing\n  preview:\n    type: html\n    entry: example.html\n  design_system:\n    requires: false\n  example_prompt: |\n    5-second product reveal — ceramic coffee mug rotating on a soft\n    paper backdrop, warm side-light from camera-left, micro dust motes\n    drifting through the beam. Cinematic, 16:9, slow drift on the camera.\n---\n\n# Video Shortform Skill\n\nShort-form (≤ 10s) is the sweet spot for current text-to-video models —\nthey're great at one **shot** with one **idea**, weaker at multi-cut\nnarratives. Plan one shot per call.\n\nSpecial case: `hyperframes-html` is **not** a photoreal text-to-video\nmodel. It's a local HTML-to-MP4 renderer. For that model, do not roleplay\ncinematography or \"real-world\" camera physics. Treat the brief as a motion\ndesign card \u002F title-frame \u002F product interstitial, ask at most one\nclarifying question, then dispatch immediately.\n\n## Resource map\n\n```\nvideo-shortform\u002F\n├── SKILL.md\n└── example.html\n```\n\n## Workflow\n\n### Step 0 — Read the project metadata\n\n`videoModel`, `videoLength` (seconds), `videoAspect`. These are\nhard-locks — clamp the prompt to whatever the chosen model supports\n(Seedance 2 caps at 10s; Kling 4 supports up to 10s + image-to-video;\nVeo 3 supports 8s with audio).\n\n### Step 1 — Plan the shot\n\nWrite the shotlist BEFORE calling the model:\n\n| Slot | Content |\n|---|---|\n| Subject | What's in frame? |\n| Camera | Static \u002F pan \u002F push-in \u002F orbit? |\n| Lighting | Key direction + temperature |\n| Motion | What moves, at what pace? Subject motion vs camera motion. |\n| Sound | Ambient bed? (only if the model supports audio) |\n\nNormally, show this to the user as a one-sentence plan before\ndispatching — they can redirect cheaply.\n\nFor `hyperframes-html`, skip the extra pre-dispatch narration once the\nuser has answered the discovery form. Collapse the plan into the actual\ngeneration prompt and dispatch immediately.\n\n### Step 2 — Compose the prompt\n\nUse the format the upstream model prefers (Seedance: motion + camera +\nmood; Kling: subject + camera + style; Veo: subject + cinematography +\nsound). Bind the project's `videoAspect` and `videoLength` directly to\nthe API parameters; never put them in prose.\n\nFor `hyperframes-html`, write a concise motion-design brief instead of a\ncamera-realism prompt. Focus on subject, layout, palette, motion\ncharacter, and overall tone. Do not spend turns narrating environment\nchecks, missing side files, or \"I am about to dispatch\" status updates.\n\n### Step 3 — Dispatch via the media contract\n\nUse the unified dispatcher — do **not** call provider APIs by hand:\n\n```bash\n\"$OD_NODE_BIN\" \"$OD_BIN\" media generate \\\n  --project \"$OD_PROJECT_ID\" \\\n  --surface video \\\n  --model \"\u003CvideoModel from metadata>\" \\\n  --aspect \"\u003CvideoAspect from metadata>\" \\\n  --length \u003CvideoLength seconds> \\\n  --output \"\u003Cshort-slug>-\u003Cseconds>s.mp4\" \\\n  --prompt \"\u003Cassembled shot prompt from Step 2>\"\n```\n\nThe command prints one line of JSON: `{\"file\": {\"name\": \"...\", ...}}`.\nThe bytes land in the project; the FileViewer plays it automatically.\n\n### Step 4 — Hand off\n\nReply with: shot summary, the filename returned by the dispatcher, and\none sentence on what to try if the user wants a variation.\n\nFor `hyperframes-html`, keep the reply especially short: what was\nrendered, the filename, and one concrete variation idea.\n\n## Hard rules\n\n- One shot per turn. Multi-shot timelines belong in a hyperframes \u002F\n  interactive-video skill, not here.\n- Match `videoAspect` exactly — re-renders are slow.\n- Never ship a video without saving the file — the user expects\n  something to play in the file viewer.\n- When the underlying model fails (NSFW filter, content policy,\n  timeout), report the error verbatim. Don't silently retry.\n- Do not claim a render has been \"sent\", \"started\", or \"is running\"\n  unless you have already called `\"$OD_NODE_BIN\" \"$OD_BIN\" media generate`.\n","# Video Shortform Skill\n\nShort-form (≤ 10s) is the sweet spot for current text-to-video models —\nthey're great at one **shot** with one **idea**, weaker at multi-cut\nnarratives. Plan one shot per call.\n\nSpecial case: `hyperframes-html` is **not** a photoreal text-to-video\nmodel. It's a local HTML-to-MP4 renderer. For that model, do not roleplay\ncinematography or \"real-world\" camera physics. Treat the brief as a motion\ndesign card \u002F title-frame \u002F product interstitial, ask at most one\nclarifying question, then dispatch immediately.\n\n## Resource map\n\n```\nvideo-shortform\u002F\n├── SKILL.md\n└── example.html\n```\n\n## Workflow\n\n### Step 0 — Read the project metadata\n\n`videoModel`, `videoLength` (seconds), `videoAspect`. These are\nhard-locks — clamp the prompt to whatever the chosen model supports\n(Seedance 2 caps at 10s; Kling 4 supports up to 10s + image-to-video;\nVeo 3 supports 8s with audio).\n\n### Step 1 — Plan the shot\n\nWrite the shotlist BEFORE calling the model:\n\n| Slot | Content |\n|---|---|\n| Subject | What's in frame? |\n| Camera | Static \u002F pan \u002F push-in \u002F orbit? |\n| Lighting | Key direction + temperature |\n| Motion | What moves, at what pace? Subject motion vs camera motion. |\n| Sound | Ambient bed? (only if the model supports audio) |\n\nNormally, show this to the user as a one-sentence plan before\ndispatching — they can redirect cheaply.\n\nFor `hyperframes-html`, skip the extra pre-dispatch narration once the\nuser has answered the discovery form. Collapse the plan into the actual\ngeneration prompt and dispatch immediately.\n\n### Step 2 — Compose the prompt\n\nUse the format the upstream model prefers (Seedance: motion + camera +\nmood; Kling: subject + camera + style; Veo: subject + cinematography +\nsound). Bind the project's `videoAspect` and `videoLength` directly to\nthe API parameters; never put them in prose.\n\nFor `hyperframes-html`, write a concise motion-design brief instead of a\ncamera-realism prompt. Focus on subject, layout, palette, motion\ncharacter, and overall tone. Do not spend turns narrating environment\nchecks, missing side files, or \"I am about to dispatch\" status updates.\n\n### Step 3 — Dispatch via the media contract\n\nUse the unified dispatcher — do **not** call provider APIs by hand:\n\n```bash\n\"$OD_NODE_BIN\" \"$OD_BIN\" media generate \\\n  --project \"$OD_PROJECT_ID\" \\\n  --surface video \\\n  --model \"\u003CvideoModel from metadata>\" \\\n  --aspect \"\u003CvideoAspect from metadata>\" \\\n  --length \u003CvideoLength seconds> \\\n  --output \"\u003Cshort-slug>-\u003Cseconds>s.mp4\" \\\n  --prompt \"\u003Cassembled shot prompt from Step 2>\"\n```\n\nThe command prints one line of JSON: `{\"file\": {\"name\": \"...\", ...}}`.\nThe bytes land in the project; the FileViewer plays it automatically.\n\n### Step 4 — Hand off\n\nReply with: shot summary, the filename returned by the dispatcher, and\none sentence on what to try if the user wants a variation.\n\nFor `hyperframes-html`, keep the reply especially short: what was\nrendered, the filename, and one concrete variation idea.\n\n## Hard rules\n\n- One shot per turn. Multi-shot timelines belong in a hyperframes \u002F\n  interactive-video skill, not here.\n- Match `videoAspect` exactly — re-renders are slow.\n- Never ship a video without saving the file — the user expects\n  something to play in the file viewer.\n- When the underlying model fails (NSFW filter, content policy,\n  timeout), report the error verbatim. Don't silently retry.\n- Do not claim a render has been \"sent\", \"started\", or \"is running\"\n  unless you have already called `\"$OD_NODE_BIN\" \"$OD_BIN\" media generate`.\n",{"od":24,"name":5,"triggers":32,"description":38},{"mode":25,"preview":26,"surface":25,"scenario":29,"design_system":30,"example_prompt":31},"video",{"type":27,"entry":28},"html","example.html","marketing",{"requires":20},"5-second product reveal — ceramic coffee mug rotating on a soft\npaper backdrop, warm side-light from camera-left, micro dust motes\ndrifting through the beam. Cinematic, 16:9, slow drift on the camera.",[25,33,34,35,36,37],"clip","shortform","reel","短视频","动效","Short-form video generation skill — 3-10 second clips for product\nreveals, motion teasers, ambient loops. Defaults to Seedance 2 but\nworks the same with Kling 3 \u002F 4, Veo 3 or Sora 2. Output is one MP4\nsaved to the project folder. When the workspace also ships an\ninteractive-video \u002F hyperframes skill, prefer composing several short\nshots into a single timeline rather than one long monolithic clip.\n","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002Fplugins\u002F_official\u002Fexamples\u002Fvideo-shortform",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill video-shortform",{"tool":54,"command":55},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill video-shortform",{"tool":57,"command":58},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill video-shortform","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002Fplugins\u002F_official\u002Fexamples\u002Fvideo-shortform\u002FSKILL.md",true,[62,67],{"path":28,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"REFERENCE","参考文档",3561,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002Fplugins\u002F_official\u002Fexamples\u002Fvideo-shortform\u002Fexample.html",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"open-design.json",11802,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002Fplugins\u002F_official\u002Fexamples\u002Fvideo-shortform\u002Fopen-design.json",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]