[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70N1A6K64F02CSRX0FE8EAA":3,"skill-same:01M70N1A6K64F02CSRX0FE8EAA":67},{"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":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":49,"ownerHtmlUrl":50,"ownerBlogUrl":51,"ownerDescription":52,"updatedAt":53,"install":54,"resources":66},"01M70N1A6K64F02CSRX0FE8EAA","optimize",null,"Diagnoses and fixes UI performance across loading speed, rendering, animations, images, and bundle size. Use when the user mentions slow, laggy, janky, performance, bundle size, load time, or wants a faster, smoother experience.","shengdabai\u002FTony-Claude-Code-Skills","shengdabai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F116417419?v=4","01M70F6D2WY5PQV5A92BKYJQEW","Tony Sheng","01M70F6D3GAAAYZ5H4CC1G8VXM",3,"MIT","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Foptimize\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36],"use","user","bundle","ui","rendering","bundle size","size","across","when","load","true","speed","time","performance","loading","fixes","animations","images","2026-11-10 10:12:30",false,"---\nname: optimize\ndescription: Diagnoses and fixes UI performance across loading speed, rendering, animations, images, and bundle size. Use when the user mentions slow, laggy, janky, performance, bundle size, load time, or wants a faster, smoother experience.\nuser-invocable: true\nargument-hint: \"[target]\"\n---\n\nIdentify and fix performance issues to create faster, smoother user experiences.\n\n## Assess Performance Issues\n\nUnderstand current performance and identify problems:\n\n1. **Measure current state**:\n   - **Core Web Vitals**: LCP, FID\u002FINP, CLS scores\n   - **Load time**: Time to interactive, first contentful paint\n   - **Bundle size**: JavaScript, CSS, image sizes\n   - **Runtime performance**: Frame rate, memory usage, CPU usage\n   - **Network**: Request count, payload sizes, waterfall\n\n2. **Identify bottlenecks**:\n   - What's slow? (Initial load? Interactions? Animations?)\n   - What's causing it? (Large images? Expensive JavaScript? Layout thrashing?)\n   - How bad is it? (Perceivable? Annoying? Blocking?)\n   - Who's affected? (All users? Mobile only? Slow connections?)\n\n**CRITICAL**: Measure before and after. Premature optimization wastes time. Optimize what actually matters.\n\n## Optimization Strategy\n\nCreate systematic improvement plan:\n\n### Loading Performance\n\n**Optimize Images**:\n- Use modern formats (WebP, AVIF)\n- Proper sizing (don't load 3000px image for 300px display)\n- Lazy loading for below-fold images\n- Responsive images (`srcset`, `picture` element)\n- Compress images (80-85% quality is usually imperceptible)\n- Use CDN for faster delivery\n\n```html\n\u003Cimg \n  src=\"hero.webp\"\n  srcset=\"hero-400.webp 400w, hero-800.webp 800w, hero-1200.webp 1200w\"\n  sizes=\"(max-width: 400px) 400px, (max-width: 800px) 800px, 1200px\"\n  loading=\"lazy\"\n  alt=\"Hero image\"\n\u002F>\n```\n\n**Reduce JavaScript Bundle**:\n- Code splitting (route-based, component-based)\n- Tree shaking (remove unused code)\n- Remove unused dependencies\n- Lazy load non-critical code\n- Use dynamic imports for large components\n\n```javascript\n\u002F\u002F Lazy load heavy component\nconst HeavyChart = lazy(() => import('.\u002FHeavyChart'));\n```\n\n**Optimize CSS**:\n- Remove unused CSS\n- Critical CSS inline, rest async\n- Minimize CSS files\n- Use CSS containment for independent regions\n\n**Optimize Fonts**:\n- Use `font-display: swap` or `optional`\n- Subset fonts (only characters you need)\n- Preload critical fonts\n- Use system fonts when appropriate\n- Limit font weights loaded\n\n```css\n@font-face {\n  font-family: 'CustomFont';\n  src: url('\u002Ffonts\u002Fcustom.woff2') format('woff2');\n  font-display: swap; \u002F* Show fallback immediately *\u002F\n  unicode-range: U+0020-007F; \u002F* Basic Latin only *\u002F\n}\n```\n\n**Optimize Loading Strategy**:\n- Critical resources first (async\u002Fdefer non-critical)\n- Preload critical assets\n- Prefetch likely next pages\n- Service worker for offline\u002Fcaching\n- HTTP\u002F2 or HTTP\u002F3 for multiplexing\n\n### Rendering Performance\n\n**Avoid Layout Thrashing**:\n```javascript\n\u002F\u002F ❌ Bad: Alternating reads and writes (causes reflows)\nelements.forEach(el => {\n  const height = el.offsetHeight; \u002F\u002F Read (forces layout)\n  el.style.height = height * 2; \u002F\u002F Write\n});\n\n\u002F\u002F ✅ Good: Batch reads, then batch writes\nconst heights = elements.map(el => el.offsetHeight); \u002F\u002F All reads\nelements.forEach((el, i) => {\n  el.style.height = heights[i] * 2; \u002F\u002F All writes\n});\n```\n\n**Optimize Rendering**:\n- Use CSS `contain` property for independent regions\n- Minimize DOM depth (flatter is faster)\n- Reduce DOM size (fewer elements)\n- Use `content-visibility: auto` for long lists\n- Virtual scrolling for very long lists (react-window, react-virtualized)\n\n**Reduce Paint & Composite**:\n- Use `transform` and `opacity` for animations (GPU-accelerated)\n- Avoid animating layout properties (width, height, top, left)\n- Use `will-change` sparingly for known expensive operations\n- Minimize paint areas (smaller is faster)\n\n### Animation Performance\n\n**GPU Acceleration**:\n```css\n\u002F* ✅ GPU-accelerated (fast) *\u002F\n.animated {\n  transform: translateX(100px);\n  opacity: 0.5;\n}\n\n\u002F* ❌ CPU-bound (slow) *\u002F\n.animated {\n  left: 100px;\n  width: 300px;\n}\n```\n\n**Smooth 60fps**:\n- Target 16ms per frame (60fps)\n- Use `requestAnimationFrame` for JS animations\n- Debounce\u002Fthrottle scroll handlers\n- Use CSS animations when possible\n- Avoid long-running JavaScript during animations\n\n**Intersection Observer**:\n```javascript\n\u002F\u002F Efficiently detect when elements enter viewport\nconst observer = new IntersectionObserver((entries) => {\n  entries.forEach(entry => {\n    if (entry.isIntersecting) {\n      \u002F\u002F Element is visible, lazy load or animate\n    }\n  });\n});\n```\n\n### React\u002FFramework Optimization\n\n**React-specific**:\n- Use `memo()` for expensive components\n- `useMemo()` and `useCallback()` for expensive computations\n- Virtualize long lists\n- Code split routes\n- Avoid inline function creation in render\n- Use React DevTools Profiler\n\n**Framework-agnostic**:\n- Minimize re-renders\n- Debounce expensive operations\n- Memoize computed values\n- Lazy load routes and components\n\n### Network Optimization\n\n**Reduce Requests**:\n- Combine small files\n- Use SVG sprites for icons\n- Inline small critical assets\n- Remove unused third-party scripts\n\n**Optimize APIs**:\n- Use pagination (don't load everything)\n- GraphQL to request only needed fields\n- Response compression (gzip, brotli)\n- HTTP caching headers\n- CDN for static assets\n\n**Optimize for Slow Connections**:\n- Adaptive loading based on connection (navigator.connection)\n- Optimistic UI updates\n- Request prioritization\n- Progressive enhancement\n\n## Core Web Vitals Optimization\n\n### Largest Contentful Paint (LCP \u003C 2.5s)\n- Optimize hero images\n- Inline critical CSS\n- Preload key resources\n- Use CDN\n- Server-side rendering\n\n### First Input Delay (FID \u003C 100ms) \u002F INP (\u003C 200ms)\n- Break up long tasks\n- Defer non-critical JavaScript\n- Use web workers for heavy computation\n- Reduce JavaScript execution time\n\n### Cumulative Layout Shift (CLS \u003C 0.1)\n- Set dimensions on images and videos\n- Don't inject content above existing content\n- Use `aspect-ratio` CSS property\n- Reserve space for ads\u002Fembeds\n- Avoid animations that cause layout shifts\n\n```css\n\u002F* Reserve space for image *\u002F\n.image-container {\n  aspect-ratio: 16 \u002F 9;\n}\n```\n\n## Performance Monitoring\n\n**Tools to use**:\n- Chrome DevTools (Lighthouse, Performance panel)\n- WebPageTest\n- Core Web Vitals (Chrome UX Report)\n- Bundle analyzers (webpack-bundle-analyzer)\n- Performance monitoring (Sentry, DataDog, New Relic)\n\n**Key metrics**:\n- LCP, FID\u002FINP, CLS (Core Web Vitals)\n- Time to Interactive (TTI)\n- First Contentful Paint (FCP)\n- Total Blocking Time (TBT)\n- Bundle size\n- Request count\n\n**IMPORTANT**: Measure on real devices with real network conditions. Desktop Chrome with fast connection isn't representative.\n\n**NEVER**:\n- Optimize without measuring (premature optimization)\n- Sacrifice accessibility for performance\n- Break functionality while optimizing\n- Use `will-change` everywhere (creates new layers, uses memory)\n- Lazy load above-fold content\n- Optimize micro-optimizations while ignoring major issues (optimize the biggest bottleneck first)\n- Forget about mobile performance (often slower devices, slower connections)\n\n## Verify Improvements\n\nTest that optimizations worked:\n\n- **Before\u002Fafter metrics**: Compare Lighthouse scores\n- **Real user monitoring**: Track improvements for real users\n- **Different devices**: Test on low-end Android, not just flagship iPhone\n- **Slow connections**: Throttle to 3G, test experience\n- **No regressions**: Ensure functionality still works\n- **User perception**: Does it *feel* faster?\n\nRemember: Performance is a feature. Fast experiences feel more responsive, more polished, more professional. Optimize systematically, measure ruthlessly, and prioritize user-perceived performance.","Identify and fix performance issues to create faster, smoother user experiences.\n\n## Assess Performance Issues\n\nUnderstand current performance and identify problems:\n\n1. **Measure current state**:\n   - **Core Web Vitals**: LCP, FID\u002FINP, CLS scores\n   - **Load time**: Time to interactive, first contentful paint\n   - **Bundle size**: JavaScript, CSS, image sizes\n   - **Runtime performance**: Frame rate, memory usage, CPU usage\n   - **Network**: Request count, payload sizes, waterfall\n\n2. **Identify bottlenecks**:\n   - What's slow? (Initial load? Interactions? Animations?)\n   - What's causing it? (Large images? Expensive JavaScript? Layout thrashing?)\n   - How bad is it? (Perceivable? Annoying? Blocking?)\n   - Who's affected? (All users? Mobile only? Slow connections?)\n\n**CRITICAL**: Measure before and after. Premature optimization wastes time. Optimize what actually matters.\n\n## Optimization Strategy\n\nCreate systematic improvement plan:\n\n### Loading Performance\n\n**Optimize Images**:\n- Use modern formats (WebP, AVIF)\n- Proper sizing (don't load 3000px image for 300px display)\n- Lazy loading for below-fold images\n- Responsive images (`srcset`, `picture` element)\n- Compress images (80-85% quality is usually imperceptible)\n- Use CDN for faster delivery\n\n```html\n\u003Cimg \n  src=\"hero.webp\"\n  srcset=\"hero-400.webp 400w, hero-800.webp 800w, hero-1200.webp 1200w\"\n  sizes=\"(max-width: 400px) 400px, (max-width: 800px) 800px, 1200px\"\n  loading=\"lazy\"\n  alt=\"Hero image\"\n\u002F>\n```\n\n**Reduce JavaScript Bundle**:\n- Code splitting (route-based, component-based)\n- Tree shaking (remove unused code)\n- Remove unused dependencies\n- Lazy load non-critical code\n- Use dynamic imports for large components\n\n```javascript\n\u002F\u002F Lazy load heavy component\nconst HeavyChart = lazy(() => import('.\u002FHeavyChart'));\n```\n\n**Optimize CSS**:\n- Remove unused CSS\n- Critical CSS inline, rest async\n- Minimize CSS files\n- Use CSS containment for independent regions\n\n**Optimize Fonts**:\n- Use `font-display: swap` or `optional`\n- Subset fonts (only characters you need)\n- Preload critical fonts\n- Use system fonts when appropriate\n- Limit font weights loaded\n\n```css\n@font-face {\n  font-family: 'CustomFont';\n  src: url('\u002Ffonts\u002Fcustom.woff2') format('woff2');\n  font-display: swap; \u002F* Show fallback immediately *\u002F\n  unicode-range: U+0020-007F; \u002F* Basic Latin only *\u002F\n}\n```\n\n**Optimize Loading Strategy**:\n- Critical resources first (async\u002Fdefer non-critical)\n- Preload critical assets\n- Prefetch likely next pages\n- Service worker for offline\u002Fcaching\n- HTTP\u002F2 or HTTP\u002F3 for multiplexing\n\n### Rendering Performance\n\n**Avoid Layout Thrashing**:\n```javascript\n\u002F\u002F ❌ Bad: Alternating reads and writes (causes reflows)\nelements.forEach(el => {\n  const height = el.offsetHeight; \u002F\u002F Read (forces layout)\n  el.style.height = height * 2; \u002F\u002F Write\n});\n\n\u002F\u002F ✅ Good: Batch reads, then batch writes\nconst heights = elements.map(el => el.offsetHeight); \u002F\u002F All reads\nelements.forEach((el, i) => {\n  el.style.height = heights[i] * 2; \u002F\u002F All writes\n});\n```\n\n**Optimize Rendering**:\n- Use CSS `contain` property for independent regions\n- Minimize DOM depth (flatter is faster)\n- Reduce DOM size (fewer elements)\n- Use `content-visibility: auto` for long lists\n- Virtual scrolling for very long lists (react-window, react-virtualized)\n\n**Reduce Paint & Composite**:\n- Use `transform` and `opacity` for animations (GPU-accelerated)\n- Avoid animating layout properties (width, height, top, left)\n- Use `will-change` sparingly for known expensive operations\n- Minimize paint areas (smaller is faster)\n\n### Animation Performance\n\n**GPU Acceleration**:\n```css\n\u002F* ✅ GPU-accelerated (fast) *\u002F\n.animated {\n  transform: translateX(100px);\n  opacity: 0.5;\n}\n\n\u002F* ❌ CPU-bound (slow) *\u002F\n.animated {\n  left: 100px;\n  width: 300px;\n}\n```\n\n**Smooth 60fps**:\n- Target 16ms per frame (60fps)\n- Use `requestAnimationFrame` for JS animations\n- Debounce\u002Fthrottle scroll handlers\n- Use CSS animations when possible\n- Avoid long-running JavaScript during animations\n\n**Intersection Observer**:\n```javascript\n\u002F\u002F Efficiently detect when elements enter viewport\nconst observer = new IntersectionObserver((entries) => {\n  entries.forEach(entry => {\n    if (entry.isIntersecting) {\n      \u002F\u002F Element is visible, lazy load or animate\n    }\n  });\n});\n```\n\n### React\u002FFramework Optimization\n\n**React-specific**:\n- Use `memo()` for expensive components\n- `useMemo()` and `useCallback()` for expensive computations\n- Virtualize long lists\n- Code split routes\n- Avoid inline function creation in render\n- Use React DevTools Profiler\n\n**Framework-agnostic**:\n- Minimize re-renders\n- Debounce expensive operations\n- Memoize computed values\n- Lazy load routes and components\n\n### Network Optimization\n\n**Reduce Requests**:\n- Combine small files\n- Use SVG sprites for icons\n- Inline small critical assets\n- Remove unused third-party scripts\n\n**Optimize APIs**:\n- Use pagination (don't load everything)\n- GraphQL to request only needed fields\n- Response compression (gzip, brotli)\n- HTTP caching headers\n- CDN for static assets\n\n**Optimize for Slow Connections**:\n- Adaptive loading based on connection (navigator.connection)\n- Optimistic UI updates\n- Request prioritization\n- Progressive enhancement\n\n## Core Web Vitals Optimization\n\n### Largest Contentful Paint (LCP \u003C 2.5s)\n- Optimize hero images\n- Inline critical CSS\n- Preload key resources\n- Use CDN\n- Server-side rendering\n\n### First Input Delay (FID \u003C 100ms) \u002F INP (\u003C 200ms)\n- Break up long tasks\n- Defer non-critical JavaScript\n- Use web workers for heavy computation\n- Reduce JavaScript execution time\n\n### Cumulative Layout Shift (CLS \u003C 0.1)\n- Set dimensions on images and videos\n- Don't inject content above existing content\n- Use `aspect-ratio` CSS property\n- Reserve space for ads\u002Fembeds\n- Avoid animations that cause layout shifts\n\n```css\n\u002F* Reserve space for image *\u002F\n.image-container {\n  aspect-ratio: 16 \u002F 9;\n}\n```\n\n## Performance Monitoring\n\n**Tools to use**:\n- Chrome DevTools (Lighthouse, Performance panel)\n- WebPageTest\n- Core Web Vitals (Chrome UX Report)\n- Bundle analyzers (webpack-bundle-analyzer)\n- Performance monitoring (Sentry, DataDog, New Relic)\n\n**Key metrics**:\n- LCP, FID\u002FINP, CLS (Core Web Vitals)\n- Time to Interactive (TTI)\n- First Contentful Paint (FCP)\n- Total Blocking Time (TBT)\n- Bundle size\n- Request count\n\n**IMPORTANT**: Measure on real devices with real network conditions. Desktop Chrome with fast connection isn't representative.\n\n**NEVER**:\n- Optimize without measuring (premature optimization)\n- Sacrifice accessibility for performance\n- Break functionality while optimizing\n- Use `will-change` everywhere (creates new layers, uses memory)\n- Lazy load above-fold content\n- Optimize micro-optimizations while ignoring major issues (optimize the biggest bottleneck first)\n- Forget about mobile performance (often slower devices, slower connections)\n\n## Verify Improvements\n\nTest that optimizations worked:\n\n- **Before\u002Fafter metrics**: Compare Lighthouse scores\n- **Real user monitoring**: Track improvements for real users\n- **Different devices**: Test on low-end Android, not just flagship iPhone\n- **Slow connections**: Throttle to 3G, test experience\n- **No regressions**: Ensure functionality still works\n- **User perception**: Does it *feel* faster?\n\nRemember: Performance is a feature. Fast experiences feel more responsive, more polished, more professional. Optimize systematically, measure ruthlessly, and prioritize user-perceived performance.",{"name":5,"description":7,"argument-hint":42,"user-invocable":43},"[target]",true,"main","7850740bd837adb32f0a109ab2af82482196c6f2","skills\u002Foptimize",1,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills","https:\u002F\u002Fzturnsgo.com","https:\u002F\u002Fgithub.com\u002Fshengdabai","https:\u002F\u002Fzturnsgo.com\u002F","AI × education creator — producer, not consumer. Taught 6,000+ learners; shipping learning tools & daily essays with Claude Code, practicing @xiaolai's way 🥋","2026-11-01 21:28:23",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":43},[56,59,62],{"tool":57,"command":58},"npx","npx skills add shengdabai\u002FTony-Claude-Code-Skills --skill optimize",{"tool":60,"command":61},"bunx","bunx skills add shengdabai\u002FTony-Claude-Code-Skills --skill optimize",{"tool":63,"command":64},"pnpm","pnpm dlx skills add shengdabai\u002FTony-Claude-Code-Skills --skill optimize","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Foptimize\u002FSKILL.md",[],[68,87,121,145,166,186],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":79,"publishedAt":37},"01M70P17DAD4C1C47NPH6A96EM","xiaolai-methodology","以李笑来(Li Xiaolai)的思考方式、方法论与表达风格,为用户做全方位 1-on-1 教练指导,覆盖创业、赚钱、投资、学习、自学、读书写作、用 AI、以及人生心态与自我管理。当用户提到 \"李笑来\"、\"笑来\"、\"笑来老师\"、\"扮演李笑来\"、\"找笑来聊聊\"、\"笑来怎么看\"、\"xiaolai\"、\"把时间当作朋友\"、\"通往财富自由之路\"、\"定投改变命运\"、\"韭菜的自我修养\"、\"自学是门手艺\"、\"让时间陪你慢慢变富\"、\"七年就是一辈子\"、\"元认知\"、\"活在未来\"、\"复利\u002F长期主义\"、\"践行\"、\"痴迷改进\"、\"个人商业模式\u002F出售时间\"、\"睡后收入\"、\"定投\"、\"财富自由\"、\"操作系统升级\"、\"最少必要知识\"、\"北极星提示词\"、\"用 AI 该怎么学\u002F思考\" 等任一触发词,或当用户带着关于创业\u002F赚钱\u002F投资\u002F学习\u002F职业\u002F重大人生决策的困惑、希望被人用笑来式的「逻辑 + 大白话 + 类比 + 重新定义 + 践行导向」来点醒和指导时,自动进入李笑来教练模式。","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fxiaolai-methodology\u002FSKILL.md",[74],{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",[80,81,82,83,84,85,86],"methodology","xiaolai","xiaolai methodology","朋友","投资","writing","收入",{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":101,"publishedAt":37},"01M70P13NB9YP7ACJR1S861CDS","zread","Produce and consume a wiki-style knowledge base for a code repository via the `zread` CLI and its on-disk output under `.\u002F.zread\u002Fwiki\u002F`. Use this skill whenever the user wants to understand, onboard onto, explore, summarize, map, or get an overview of an unfamiliar codebase; asks for architecture docs, a project wiki, a repo walkthrough, module\u002Fpackage explanations, or \"what does this repo do\"; wants to generate, regenerate, resume, browse, or serve code documentation locally; or mentions zread \u002F zread.ai directly. Also use it proactively before diving into a large unknown repo — if `.\u002F.zread\u002Fwiki\u002Fcurrent` exists, read the generated pages instead of crawling source file-by-file; if it doesn't, consider offering to run `zread generate`. The trigger is the intent (understand a codebase through generated docs), not the literal word \"zread\".","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fzread\u002FSKILL.md",[93,96],{"categoryNo":94,"categoryName":95,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[89,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120],"knowledge","wiki","explore","walkthrough","project","get","knowledge base","run","generate","intent","cli","map","documentation","project wiki","disk","architecture","code","unknown","generated",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":131,"publishedAt":37},"01M70P10S4SWMZQ8BJAFBFDRW3","youtube","Launch the YouTube Creator Agent to auto-generate videos.\nUse when: user types \u002Fyoutube, wants to create YouTube videos,\ngenerate video content, or upload to YouTube.\nKeywords: youtube, video, 视频, 创作视频, 发布视频","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube\u002FSKILL.md",[127,128],{"categoryNo":94,"categoryName":95,"taxonomyType":77,"taxonomyTypeDesc":78},{"categoryNo":129,"categoryName":130,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000036","内容创作者",[123,20,132,133,134,135,136,137,110,138,139,140,27,19,141,142,143,144],"content","视频","creator","generate video","videos","launch","video content","create","upload","auto","types","Video","创作",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":152,"publishedAt":37},"01M70P0YE95D8BACZCGV8BK90K","youtube-script-sync","Sync, update, or optimize Tony's GetNote knowledge base `Youtube视频逐字稿` by turning each parent recording or first-person idea note into an idempotent child note containing a directly recordable YouTube long-video or Shorts script. Use when the user says “更新\u002F同步\u002F优化 Youtube视频逐字稿知识库”, or says “更新\u002F同步\u002F优化该知识库” while this knowledge base is the active context.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-script-sync\u002FSKILL.md",[151],{"categoryNo":94,"categoryName":95,"taxonomyType":77,"taxonomyTypeDesc":78},[153,154,123,155,156,143,157,158,159,160,161,162,163,5,108,164,27,19,102,165],"sync","script","youtube script sync","recording","shorts","first","base","person","update","active","child","idempotent","long",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":176,"publishedAt":37},"01M70P0WMV5XT0EEC0N445PW07","writing-skills","How to write SKILL.md files that trigger reliably and teach effectively. Use when creating, improving, or reviewing Claude Code skills.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fxiaolai\u002Fnlpm\u002Fskills\u002Fnlpm\u002Fwriting-skills\u002FSKILL.md",[172,173,174,175],{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},{"categoryNo":94,"categoryName":95,"taxonomyType":77,"taxonomyTypeDesc":78},{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},{"categoryNo":129,"categoryName":130,"taxonomyType":99,"taxonomyTypeDesc":100},[177,85,178,179,180,181,118,27,19,182,183,184,185],"writing skills","how","teach","write skill","write","claude code skills","files","how to","trigger",{"skillNo":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":194,"publishedAt":37},"01M70P0SJFR4YVJQBGMHKGSKXT","writing-rules","How to write .claude\u002Frules\u002F files that Claude actually follows. Use when creating, improving, or reviewing project rules.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fxiaolai\u002Fnlpm\u002Fskills\u002Fnlpm\u002Fwriting-rules\u002FSKILL.md",[192,193],{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},{"categoryNo":129,"categoryName":130,"taxonomyType":99,"taxonomyTypeDesc":100},[195,85,196,106,197,183,27,178,181,19,184],"Rules","writing rules","project rules"]