[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HCHBVPKACJCFAB96T594J":3,"skill-same:01M71HCHBVPKACJCFAB96T594J":85},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":25,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":55,"repositoryHtmlUrl":56,"repositoryHomepageUrl":6,"ownerHtmlUrl":57,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":58,"install":59,"resources":72},"01M71HCHBVPKACJCFAB96T594J","optimize-images",null,"This skill should be used when the user asks to \"optimize images\", \"compress images\", \"reduce image file size\", \"make images smaller\", \"optimize PNGs\", \"optimize JPEGs\", \"speed up website images\", \"reduce bundle size images\", or needs help with image compression for web projects. Provides workflows and scripts for batch image optimization using sharp.","JSGforever\u002Fskillguard","JSGforever","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F85541948?v=4","01M71FQD3E132VMR5F4TAYX3YS","01M71FQD4DYW0XJ4XQ4YQH75Y9",2,"GPL-3.0","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__b-open-io--optimize-images\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"optimize images","optimize","images","compress images","speed","Optimization","for","make","compress","scripts","sharp","bundle size","website","batch","image","reduce","when","workflows","up","projects","2026-11-10 10:12:30",false,"---\nname: optimize-images\ndescription: This skill should be used when the user asks to \"optimize images\", \"compress images\", \"reduce image file size\", \"make images smaller\", \"optimize PNGs\", \"optimize JPEGs\", \"speed up website images\", \"reduce bundle size images\", or needs help with image compression for web projects. Provides workflows and scripts for batch image optimization using sharp.\nversion: 1.0.0\n---\n\n# Image Optimization for Web Projects\n\nOptimize images for web performance using modern tools. This skill provides scripts and workflows for compressing PNG and JPEG images while maintaining visual quality.\n\n## When to Use This Skill\n\n- Preparing images for production web deployment\n- Reducing page load times\n- Optimizing public\u002Fimages directories\n- Batch compressing screenshots, watercolors, photos\n- Auditing image sizes before\u002Fafter optimization\n\n## Core Tool: Sharp\n\nSharp is the fastest Node.js image processing library, built on libvips. Use it for all image optimization tasks.\n\n### Install Sharp\n\n```bash\nbun add -d sharp\n# or\nnpm install -D sharp\n```\n\n## Quick Start Workflow\n\n### 1. Benchmark Current State\n\nBefore optimization, measure baseline metrics:\n\n```bash\n# Total size and count\ndu -sh public\u002Fimages\u002F\nfind public\u002Fimages -type f \\( -name \"*.png\" -o -name \"*.jpg\" -o -name \"*.jpeg\" \\) | wc -l\n\n# Size by format\nfind public\u002Fimages -name \"*.png\" -exec du -ch {} + | tail -1\nfind public\u002Fimages \\( -name \"*.jpg\" -o -name \"*.jpeg\" \\) -exec du -ch {} + | tail -1\n\n# Top 20 largest files\nfind public\u002Fimages -type f \\( -name \"*.png\" -o -name \"*.jpg\" \\) -exec ls -la {} \\; | \\\n  awk '{print $5, $9}' | sort -rn | head -20 | \\\n  awk '{printf \"%6.1fMB  %s\\n\", $1\u002F1048576, $2}'\n```\n\n### 2. Test on Single Image\n\nAlways test optimization settings on one image first:\n\n```bash\nbun run scripts\u002Foptimize-images.ts --file=public\u002Fimages\u002Flargest-image.png --dry-run\n```\n\n### 3. Run Full Optimization\n\nAfter verifying settings work well:\n\n```bash\nbun run scripts\u002Foptimize-images.ts\n```\n\n### 4. Verify Results\n\n```bash\n# Compare before\u002Fafter\ndu -sh public\u002Fimages\u002F\n\n# Visually inspect optimized images\n# Run production build\nbun run build\n```\n\n## Optimization Settings\n\n### PNG Optimization\n\nSharp's PNG encoder with palette mode for maximum compression:\n\n```typescript\nsharp(filePath)\n  .png({\n    quality: 80,           \u002F\u002F 1-100, lower = smaller\n    compressionLevel: 9,   \u002F\u002F 0-9, higher = more compression\n    adaptiveFiltering: true,\n    palette: true,         \u002F\u002F Use palette for smaller files\n  })\n  .toBuffer();\n```\n\n**Recommended settings:**\n- Screenshots: quality 80, compression 9\n- Photos: quality 85, compression 9\n- Icons\u002Flogos: quality 90, compression 9 (preserve crispness)\n\n### JPEG Optimization\n\nSharp with mozjpeg for superior compression:\n\n```typescript\nsharp(filePath)\n  .jpeg({\n    quality: 80,    \u002F\u002F 1-100, lower = smaller\n    mozjpeg: true,  \u002F\u002F Use mozjpeg encoder\n  })\n  .toBuffer();\n```\n\n**Recommended settings:**\n- Photos: quality 75-80\n- Screenshots: quality 80-85\n- Hero images: quality 85\n\n## The Optimization Script\n\nCopy `scripts\u002Foptimize-images.ts` to the project's scripts directory. The script:\n\n1. Recursively finds all PNG\u002FJPEG images\n2. Applies compression settings\n3. Overwrites originals (only if smaller)\n4. Reports savings per file\n5. Shows total savings summary\n\n### Script Usage\n\n```bash\n# Dry run (see what would happen)\nbun run scripts\u002Foptimize-images.ts --dry-run\n\n# Test single file\nbun run scripts\u002Foptimize-images.ts --file=path\u002Fto\u002Fimage.png\n\n# Full optimization\nbun run scripts\u002Foptimize-images.ts\n```\n\n### Expected Savings\n\nTypical results for unoptimized web images:\n\n| Image Type | Typical Savings |\n|------------|-----------------|\n| Screenshots (PNG) | 40-60% |\n| Photos (JPEG) | 20-40% |\n| Watercolors (PNG) | 30-50% |\n| Icons (PNG) | 10-30% |\n\n## Next.js Considerations\n\nNext.js provides automatic image optimization via `next\u002Fimage`. However, optimizing source images still helps:\n\n1. **Faster builds** - Smaller source images = faster processing\n2. **Fallback support** - Non-Next.js imports still benefit\n3. **Reduced storage** - Smaller repo size\n4. **CDN efficiency** - Less data to cache\u002Fserve\n\nKeep source images optimized even when using `next\u002Fimage`.\n\n## Workflow Integration\n\n### Pre-commit Hook (Optional)\n\nAdd to `.husky\u002Fpre-commit` or git hooks:\n\n```bash\n# Warn if large images are being committed\nfind public\u002Fimages -name \"*.png\" -size +500k -exec echo \"Warning: Large image: {}\" \\;\n```\n\n### CI\u002FCD Check\n\nAdd to build pipeline:\n\n```bash\n# Fail if images exceed threshold\nMAX_SIZE=79  # MB\nCURRENT=$(du -sm public\u002Fimages | cut -f1)\nif [ \"$CURRENT\" -gt \"$MAX_SIZE\" ]; then\n  echo \"Error: Images exceed ${MAX_SIZE}MB (currently ${CURRENT}MB)\"\n  exit 1\nfi\n```\n\n## Troubleshooting\n\n### Image Quality Too Low\n\nIncrease quality settings:\n- PNG: Increase `quality` to 85-90\n- JPEG: Increase `quality` to 85-90\n\n### Transparent PNGs Look Wrong\n\nEnsure `palette: true` handles transparency correctly. For complex transparency, use:\n\n```typescript\n.png({ quality: 85, palette: false })\n```\n\n### Sharp Installation Issues\n\nOn macOS, ensure libvips is available:\n\n```bash\nbrew install vips\n```\n\nOr let sharp download pre-built binaries:\n\n```bash\nnpm rebuild sharp\n```\n\n## Additional Resources\n\n### Reference Files\n\n- **`references\u002Foptimization-guide.md`** - Detailed compression algorithms and format comparison\n- **`references\u002Fsharp-api.md`** - Complete sharp API reference for images\n\n### Scripts\n\n- **`scripts\u002Foptimize-images.ts`** - Production-ready optimization script\n\n## Context Discipline\n\n**Do not read optimized images back into context.** The script outputs a summary table with file sizes, savings percentages, and totals. Ask the user to visually inspect results if quality verification is needed. Even optimized images can be large enough to fill the context window when processing many files.\n\n## Summary\n\n1. Install sharp: `bun add -d sharp`\n2. Copy optimization script to project\n3. Benchmark: `du -sh public\u002Fimages\u002F`\n4. Test: `bun run scripts\u002Foptimize-images.ts --dry-run`\n5. Optimize: `bun run scripts\u002Foptimize-images.ts`\n6. Verify: Check sizes and visual quality\n7. Commit: Include optimized images in deployment\n","# Image Optimization for Web Projects\n\nOptimize images for web performance using modern tools. This skill provides scripts and workflows for compressing PNG and JPEG images while maintaining visual quality.\n\n## When to Use This Skill\n\n- Preparing images for production web deployment\n- Reducing page load times\n- Optimizing public\u002Fimages directories\n- Batch compressing screenshots, watercolors, photos\n- Auditing image sizes before\u002Fafter optimization\n\n## Core Tool: Sharp\n\nSharp is the fastest Node.js image processing library, built on libvips. Use it for all image optimization tasks.\n\n### Install Sharp\n\n```bash\nbun add -d sharp\n# or\nnpm install -D sharp\n```\n\n## Quick Start Workflow\n\n### 1. Benchmark Current State\n\nBefore optimization, measure baseline metrics:\n\n```bash\n# Total size and count\ndu -sh public\u002Fimages\u002F\nfind public\u002Fimages -type f \\( -name \"*.png\" -o -name \"*.jpg\" -o -name \"*.jpeg\" \\) | wc -l\n\n# Size by format\nfind public\u002Fimages -name \"*.png\" -exec du -ch {} + | tail -1\nfind public\u002Fimages \\( -name \"*.jpg\" -o -name \"*.jpeg\" \\) -exec du -ch {} + | tail -1\n\n# Top 20 largest files\nfind public\u002Fimages -type f \\( -name \"*.png\" -o -name \"*.jpg\" \\) -exec ls -la {} \\; | \\\n  awk '{print $5, $9}' | sort -rn | head -20 | \\\n  awk '{printf \"%6.1fMB  %s\\n\", $1\u002F1048576, $2}'\n```\n\n### 2. Test on Single Image\n\nAlways test optimization settings on one image first:\n\n```bash\nbun run scripts\u002Foptimize-images.ts --file=public\u002Fimages\u002Flargest-image.png --dry-run\n```\n\n### 3. Run Full Optimization\n\nAfter verifying settings work well:\n\n```bash\nbun run scripts\u002Foptimize-images.ts\n```\n\n### 4. Verify Results\n\n```bash\n# Compare before\u002Fafter\ndu -sh public\u002Fimages\u002F\n\n# Visually inspect optimized images\n# Run production build\nbun run build\n```\n\n## Optimization Settings\n\n### PNG Optimization\n\nSharp's PNG encoder with palette mode for maximum compression:\n\n```typescript\nsharp(filePath)\n  .png({\n    quality: 80,           \u002F\u002F 1-100, lower = smaller\n    compressionLevel: 9,   \u002F\u002F 0-9, higher = more compression\n    adaptiveFiltering: true,\n    palette: true,         \u002F\u002F Use palette for smaller files\n  })\n  .toBuffer();\n```\n\n**Recommended settings:**\n- Screenshots: quality 80, compression 9\n- Photos: quality 85, compression 9\n- Icons\u002Flogos: quality 90, compression 9 (preserve crispness)\n\n### JPEG Optimization\n\nSharp with mozjpeg for superior compression:\n\n```typescript\nsharp(filePath)\n  .jpeg({\n    quality: 80,    \u002F\u002F 1-100, lower = smaller\n    mozjpeg: true,  \u002F\u002F Use mozjpeg encoder\n  })\n  .toBuffer();\n```\n\n**Recommended settings:**\n- Photos: quality 75-80\n- Screenshots: quality 80-85\n- Hero images: quality 85\n\n## The Optimization Script\n\nCopy `scripts\u002Foptimize-images.ts` to the project's scripts directory. The script:\n\n1. Recursively finds all PNG\u002FJPEG images\n2. Applies compression settings\n3. Overwrites originals (only if smaller)\n4. Reports savings per file\n5. Shows total savings summary\n\n### Script Usage\n\n```bash\n# Dry run (see what would happen)\nbun run scripts\u002Foptimize-images.ts --dry-run\n\n# Test single file\nbun run scripts\u002Foptimize-images.ts --file=path\u002Fto\u002Fimage.png\n\n# Full optimization\nbun run scripts\u002Foptimize-images.ts\n```\n\n### Expected Savings\n\nTypical results for unoptimized web images:\n\n| Image Type | Typical Savings |\n|------------|-----------------|\n| Screenshots (PNG) | 40-60% |\n| Photos (JPEG) | 20-40% |\n| Watercolors (PNG) | 30-50% |\n| Icons (PNG) | 10-30% |\n\n## Next.js Considerations\n\nNext.js provides automatic image optimization via `next\u002Fimage`. However, optimizing source images still helps:\n\n1. **Faster builds** - Smaller source images = faster processing\n2. **Fallback support** - Non-Next.js imports still benefit\n3. **Reduced storage** - Smaller repo size\n4. **CDN efficiency** - Less data to cache\u002Fserve\n\nKeep source images optimized even when using `next\u002Fimage`.\n\n## Workflow Integration\n\n### Pre-commit Hook (Optional)\n\nAdd to `.husky\u002Fpre-commit` or git hooks:\n\n```bash\n# Warn if large images are being committed\nfind public\u002Fimages -name \"*.png\" -size +500k -exec echo \"Warning: Large image: {}\" \\;\n```\n\n### CI\u002FCD Check\n\nAdd to build pipeline:\n\n```bash\n# Fail if images exceed threshold\nMAX_SIZE=79  # MB\nCURRENT=$(du -sm public\u002Fimages | cut -f1)\nif [ \"$CURRENT\" -gt \"$MAX_SIZE\" ]; then\n  echo \"Error: Images exceed ${MAX_SIZE}MB (currently ${CURRENT}MB)\"\n  exit 1\nfi\n```\n\n## Troubleshooting\n\n### Image Quality Too Low\n\nIncrease quality settings:\n- PNG: Increase `quality` to 85-90\n- JPEG: Increase `quality` to 85-90\n\n### Transparent PNGs Look Wrong\n\nEnsure `palette: true` handles transparency correctly. For complex transparency, use:\n\n```typescript\n.png({ quality: 85, palette: false })\n```\n\n### Sharp Installation Issues\n\nOn macOS, ensure libvips is available:\n\n```bash\nbrew install vips\n```\n\nOr let sharp download pre-built binaries:\n\n```bash\nnpm rebuild sharp\n```\n\n## Additional Resources\n\n### Reference Files\n\n- **`references\u002Foptimization-guide.md`** - Detailed compression algorithms and format comparison\n- **`references\u002Fsharp-api.md`** - Complete sharp API reference for images\n\n### Scripts\n\n- **`scripts\u002Foptimize-images.ts`** - Production-ready optimization script\n\n## Context Discipline\n\n**Do not read optimized images back into context.** The script outputs a summary table with file sizes, savings percentages, and totals. Ask the user to visually inspect results if quality verification is needed. Even optimized images can be large enough to fill the context window when processing many files.\n\n## Summary\n\n1. Install sharp: `bun add -d sharp`\n2. Copy optimization script to project\n3. Benchmark: `du -sh public\u002Fimages\u002F`\n4. Test: `bun run scripts\u002Foptimize-images.ts --dry-run`\n5. Optimize: `bun run scripts\u002Foptimize-images.ts`\n6. Verify: Check sizes and visual quality\n7. Commit: Include optimized images in deployment\n",{"name":5,"version":51,"description":7},"1.0.0","main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__b-open-io--optimize-images",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add JSGforever\u002Fskillguard --skill optimize-images",{"tool":65,"command":66},"bunx","bunx skills add JSGforever\u002Fskillguard --skill optimize-images",{"tool":68,"command":69},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill optimize-images","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__b-open-io--optimize-images\u002FSKILL.md",true,[73,79],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Foptimization-guide.md","REFERENCE","参考文档",7011,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__b-open-io--optimize-images\u002Freferences\u002Foptimization-guide.md",{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"scripts\u002Foptimize-images.ts","SCRIPT","脚本",7937,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__b-open-io--optimize-images\u002Fscripts\u002Foptimize-images.ts",[86,112,128,155,177,197],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":93,"publishedAt":46},"01M71HY2SNXBA9Q00WZDTZQ31Z","skillguard-codex-scanner","Hybrid deterministic+LLM agent-skill security scanner. Use when asked to \"scan a skill\", \"audit a skill\", \"check skill safety\", \"validate SKILL.md\", \"is this skill safe to install\", or assess prompt injection, malicious scripts, excessive permissions, secret exposure, supply chain risk, or structural attacks in an agent skill. Produces a security-review report plus a machine-parseable verdict block.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fsrc\u002Fskillguard\u002Fstatic_scanner\u002Fskillguard-codex-scanner\u002FSKILL.md",[92],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[94,95,96,97,98,99,100,101,102,103,104,105,42,106,107,108,109,110,35,111],"scanner","skillguard codex scanner","skillguard","codex","chain","skill security","security-review","review report","structural","secret","prompt injection","security scanner","review","malicious","permissions","exposure","audit","safe",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":116,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":124,"publishedAt":46},"01M71HY0SPKTT3S27BC2HPAC5M","data-exfiltrator","Analyzes data files","MIT","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Fsmoke-one-skill\u002Fasset1__cisco-ai-defense--data-exfiltrator\u002FSKILL.md",[119],{"categoryNo":120,"categoryName":121,"taxonomyType":122,"taxonomyTypeDesc":123},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[125,126,127],"data","data exfiltrator","files",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":46},"01M71HXVS9EMN44BGDW215FZ72","real-time-collaboration-engine","Build real-time collaborative editing with WebSockets, OT\u002FCRDT conflict resolution, and presence awareness. Implements cursor tracking, optimistic updates, and offline sync. Use for collaborative editors, whiteboards, video editing. Activate on \"real-time collaboration\", \"WebSocket sync\", \"multiplayer editing\", \"CRDT\", \"presence awareness\". NOT for simple chat, request-response APIs, or single-user apps.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--real-time-collaboration-engine\u002FSKILL.md",[],[135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154],"time","real time collaboration engine","real time collaboration","collaboration","engine","real time","Video","reliability","video editing","performance","conflict resolution","presence","access","apps","updates","Bash","activate","optimizer","react","streaming",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":164,"publishedAt":46},"01M71HXP6CTY4KFN0QVMMN0V7J","react-performance-optimizer","Optimize React apps for 60fps performance. Implements memoization, virtualization, code splitting, bundle optimization. Use for slow renders, large lists, bundle bloat. Activate on \"React performance\", \"slow render\", \"useMemo\", \"bundle size\", \"virtualization\". NOT for backend optimization, non-React frameworks, or premature optimization.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--react-performance-optimizer\u002FSKILL.md",[161],{"categoryNo":162,"categoryName":163,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[144,165,152,153,166,167,168,169,170,171,135,172,173,148,150,174,151,154,175,176],"react performance optimizer","react performance","performance optimizer","app","nextjs","expert","re","render","2025","code","router","strategies",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":184,"publishedAt":46},"01M71HXH7QXSQB4QTDZ7SP7YXQ","llm-streaming-response-handler","Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI\u002FAnthropic\u002FClaude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on \"LLM streaming\", \"SSE\", \"token stream\", \"chat UI\", \"real-time AI\". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--llm-streaming-response-handler\u002FSKILL.md",[183],{"categoryNo":162,"categoryName":163,"taxonomyType":20,"taxonomyTypeDesc":21},[185,154,186,187,188,189,144,135,190,191,192,150,151,152,39,153,193,194,195,196],"llm streaming response handler","handler","error","processing","retry","chat ui","error recovery","critical","display","text","server","read",{"skillNo":198,"name":199,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":210,"publishedAt":46},"01M71HXCB0E1YRKYW1Y8T0Y106","github-actions-pipeline-builder","Build production CI\u002FCD pipelines with GitHub Actions. Implements matrix builds, caching, deployments, testing, security scanning. Use for automated testing, deployments, release workflows. Activate on \"GitHub Actions\", \"CI\u002FCD\", \"workflow\", \"deployment pipeline\", \"automated testing\". NOT for Jenkins\u002FCircleCI, manual deployments, or non-GitHub repositories.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--github-actions-pipeline-builder\u002FSKILL.md",[203,206,209],{"categoryNo":204,"categoryName":205,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":207,"categoryName":208,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[211,212,213,214,215,216,217,142,170,218,219,43,151,176,220,196,221,222,223,224],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","pipeline","testing","ci","run","release","write","edit","git"]