[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HWFZKFN9TGJJ6MP3Z1BMY":3,"skill-same:01M71HWFZKFN9TGJJ6MP3Z1BMY":112},{"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":30,"publishedAt":51,"linkOnly":52,"markdownContent":53,"markdownBody":54,"frontMatter":55,"refName":71,"commitSha":72,"skillDirectory":73,"forksCount":74,"repositoryHtmlUrl":75,"repositoryHomepageUrl":6,"ownerHtmlUrl":76,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":77,"install":78,"resources":91},"01M71HWFZKFN9TGJJ6MP3Z1BMY","design-archivist",null,"Long-running design anthropologist that builds comprehensive visual databases from 500-1000 real-world examples, extracting color palettes, typography patterns, layout systems, and interaction design across any domain (portfolios, e-commerce, SaaS, adult content, technical showcases). This skill should be used when users need exhaustive design research, pattern recognition across large example sets, or systematic visual analysis for competitive positioning.","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__curiositech--design-archivist\u002FSKILL.md",[17,22,25],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":26,"categoryName":27,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50],"Archivist","design archivist","design","layout","web-design","interaction","world","across","interaction design","commerce","websearch","analysis","when","database","positioning","anthropologist","competitive positioning","expert","extracting","databases","2026-11-10 10:12:30",false,"---\nname: design-archivist\ndescription: Long-running design anthropologist that builds comprehensive visual databases from 500-1000 real-world examples, extracting color palettes, typography patterns, layout systems, and interaction\n  design across any domain (portfolios, e-commerce, SaaS, adult content, technical showcases). This skill should be used when users need exhaustive design research, pattern recognition across large example\n  sets, or systematic visual analysis for competitive positioning.\nallowed-tools: Read,Write,WebSearch,WebFetch\nmetadata:\n  category: Research & Analysis\n  pairs-with:\n  - skill: web-design-expert\n    reason: Apply researched patterns to designs\n  - skill: competitive-cartographer\n    reason: Design-focused competitive analysis\n  tags:\n  - design-research\n  - patterns\n  - analysis\n  - visual-database\n  - trends\n---\n\n# Design Archivist\n\nA design anthropologist that systematically builds visual databases through large-scale analysis of real-world examples. **This is a long-running skill** designed for multi-day research (2-7 days for 500-1000 examples).\n\n## Quick Start\n\n```\nUser: \"Research design patterns for fintech apps targeting Gen Z\"\n\nArchivist:\n1. Define scope: \"fintech landing pages, Gen Z audience (18-27)\"\n2. Set target: 500 examples over 2-3 days\n3. Identify seeds: Venmo, Cash App, Robinhood, plus competitors\n4. Begin systematic crawl with checkpoints every 10 examples\n5. After 48 hours: Deliver pattern database with:\n   - Color trends\n   - Typography patterns\n   - Layout systems\n   - White space opportunities\n```\n\n## When to Use\n\n**Use for:**\n- Exhaustive design research (300-1000 examples)\n- Pattern recognition across large example sets\n- Competitive visual analysis\n- Trend identification with data backing\n- Domain-specific design language extraction\n\n**NOT for:**\n- Quick design inspiration (use Dribbble\u002FAwwwards directly)\n- Single example analysis\n- Small samples (<50 examples)\n- Real-time trend spotting (this takes days)\n\n## Core Process\n\n### 1. Domain Initialization\n- Define target domain and audience\n- Set target count (300-1000 based on specificity)\n- Identify seed URLs or search queries\n- Establish focus areas\n\n### 2. Systematic Crawling\nFor each example:\n1. Capture visual snapshot\n2. Record metadata (URL, timestamp, context)\n3. Extract Visual DNA (colors, typography, layout, interactions)\n4. Analyze contextual signals (audience, positioning, success indicators)\n5. Apply categorical tags\n6. **Save checkpoint every 10 examples**\n\n### 3. Pattern Extraction\nAfter accumulating examples, identify:\n- **Dominant patterns** - The \"norm\" (most common approaches)\n- **Emerging patterns** - The \"future\" (gaining traction)\n- **Deprecated patterns** - The \"past\" (avoid these)\n- **Outlier patterns** - The \"experimental\" (unique approaches)\n\n## Visual DNA Extraction\n\nFor each example, extract:\n\n| Category | What to Extract |\n|----------|-----------------|\n| **Colors** | Palette, primary\u002Fsecondary\u002Faccent, dominance percentages |\n| **Typography** | Font families, weights, sizes, hierarchy |\n| **Layout** | Grid system, spacing base, structure, whitespace |\n| **Interactions** | Hover effects, transitions, scroll behaviors |\n| **Animation** | Presence level, types, timing |\n\nSee `references\u002Fdata_structures.md` for full TypeScript interfaces.\n\n## Domain Quick Reference\n\n| Domain | Focus Areas | Seed Sources |\n|--------|-------------|--------------|\n| **Portfolios** | Clarity, credibility, storytelling | Awwwards, Dribbble, Behance |\n| **SaaS Landing** | Conversion, trust signals, pricing | Product Hunt, SaaS directories |\n| **E-Commerce** | Product photos, checkout, mobile | Shopify stores, major retailers |\n| **Adult Content** | Premium positioning, discretion | Adult ad networks, VR platforms |\n| **Technical Demos** | Visual drama, performance, interactivity | Shadertoy, Codrops, ArtStation |\n\nSee `references\u002Fdomain_guides.md` for detailed domain strategies.\n\n## Long-Running Infrastructure\n\n### Checkpointing Strategy\n- Save checkpoint every 10 examples\n- Include job ID, progress count, queue state, timestamp\n- Keep last 3 checkpoints as backup\n\n### Progress Reporting\nReport at intervals:\n- \"Analyzed 250\u002F1000 examples (25% complete)\"\n- \"Current rate: 100 examples\u002Fday\"\n- \"Estimated completion: 7 days\"\n- \"Top emerging pattern: glassmorphic cards (15% of recent examples)\"\n\n### Rate Limiting\n- Max 1 request per second per domain\n- Respect robots.txt\n- Implement exponential backoff on errors\n\n## Anti-Patterns\n\n### 1. Scraping Too Aggressively\n**Symptom:** Requests every 100ms, same domain hammered repeatedly\n**Fix:** 1 request\u002Fsecond max, respect robots.txt, exponential backoff\n\n### 2. No Checkpointing\n**Symptom:** Running 24 hours straight without saving\n**Fix:** Save every 10 examples with timestamp and queue state\n\n### 3. Ignoring Domain Context\n**Symptom:** Applying e-commerce patterns to portfolio sites\n**Fix:** Research domain-specific best practices first\n\n### 4. Analysis Paralysis\n**Symptom:** 30 minutes per example across 1000 examples\n**Fix:** Batch process in groups of 10, deep-dive only on outliers\n\n### 5. Insufficient Diversity\n**Symptom:** Only analyzing top-tier examples\n**Fix:** Include leaders, mid-tier, and independents; geographic diversity\n\n### 6. Ignoring Historical Context\n**Symptom:** Treating all patterns as current\n**Fix:** Use Wayback Machine, note when patterns emerged, track evolution\n\n## Output Format\n\nGenerate comprehensive research packages with:\n- **Meta**: Domain, count, date range, depth\n- **Examples**: Full visual database\n- **Patterns**: Dominant, emerging, deprecated, outlier\n- **Insights**: Color\u002Ftypography\u002Flayout\u002Finteraction trends\n- **Recommendations**: Safe choices, differentiators, patterns to avoid\n\n## Cost and Scale\n\nFor 1000-example analysis:\n| Item | Cost |\n|------|------|\n| Screenshots | ~$20 (Playwright cloud @ $0.02\u002Feach) |\n| LLM Analysis | ~$15 (100 batches × $0.15) |\n| Storage | ~$0.01 (200MB) |\n| **Total** | **~$35** |\n| **Runtime** | 48-72 hours |\n\nInform users of scope and cost before beginning.\n\n## Reference Files\n\n| File | Contents |\n|------|----------|\n| `references\u002Fdata_structures.md` | TypeScript interfaces for VisualDNA, ContextAnalysis, Checkpoint |\n| `references\u002Fdomain_guides.md` | Detailed domain-specific strategies and focus areas |\n\n---\n\n**Covers:** Design Research | Pattern Recognition | Visual Analysis | Competitive Intelligence\n\n**Use with:** web-design-expert (apply findings) | competitive-cartographer (market context)\n","# Design Archivist\n\nA design anthropologist that systematically builds visual databases through large-scale analysis of real-world examples. **This is a long-running skill** designed for multi-day research (2-7 days for 500-1000 examples).\n\n## Quick Start\n\n```\nUser: \"Research design patterns for fintech apps targeting Gen Z\"\n\nArchivist:\n1. Define scope: \"fintech landing pages, Gen Z audience (18-27)\"\n2. Set target: 500 examples over 2-3 days\n3. Identify seeds: Venmo, Cash App, Robinhood, plus competitors\n4. Begin systematic crawl with checkpoints every 10 examples\n5. After 48 hours: Deliver pattern database with:\n   - Color trends\n   - Typography patterns\n   - Layout systems\n   - White space opportunities\n```\n\n## When to Use\n\n**Use for:**\n- Exhaustive design research (300-1000 examples)\n- Pattern recognition across large example sets\n- Competitive visual analysis\n- Trend identification with data backing\n- Domain-specific design language extraction\n\n**NOT for:**\n- Quick design inspiration (use Dribbble\u002FAwwwards directly)\n- Single example analysis\n- Small samples (<50 examples)\n- Real-time trend spotting (this takes days)\n\n## Core Process\n\n### 1. Domain Initialization\n- Define target domain and audience\n- Set target count (300-1000 based on specificity)\n- Identify seed URLs or search queries\n- Establish focus areas\n\n### 2. Systematic Crawling\nFor each example:\n1. Capture visual snapshot\n2. Record metadata (URL, timestamp, context)\n3. Extract Visual DNA (colors, typography, layout, interactions)\n4. Analyze contextual signals (audience, positioning, success indicators)\n5. Apply categorical tags\n6. **Save checkpoint every 10 examples**\n\n### 3. Pattern Extraction\nAfter accumulating examples, identify:\n- **Dominant patterns** - The \"norm\" (most common approaches)\n- **Emerging patterns** - The \"future\" (gaining traction)\n- **Deprecated patterns** - The \"past\" (avoid these)\n- **Outlier patterns** - The \"experimental\" (unique approaches)\n\n## Visual DNA Extraction\n\nFor each example, extract:\n\n| Category | What to Extract |\n|----------|-----------------|\n| **Colors** | Palette, primary\u002Fsecondary\u002Faccent, dominance percentages |\n| **Typography** | Font families, weights, sizes, hierarchy |\n| **Layout** | Grid system, spacing base, structure, whitespace |\n| **Interactions** | Hover effects, transitions, scroll behaviors |\n| **Animation** | Presence level, types, timing |\n\nSee `references\u002Fdata_structures.md` for full TypeScript interfaces.\n\n## Domain Quick Reference\n\n| Domain | Focus Areas | Seed Sources |\n|--------|-------------|--------------|\n| **Portfolios** | Clarity, credibility, storytelling | Awwwards, Dribbble, Behance |\n| **SaaS Landing** | Conversion, trust signals, pricing | Product Hunt, SaaS directories |\n| **E-Commerce** | Product photos, checkout, mobile | Shopify stores, major retailers |\n| **Adult Content** | Premium positioning, discretion | Adult ad networks, VR platforms |\n| **Technical Demos** | Visual drama, performance, interactivity | Shadertoy, Codrops, ArtStation |\n\nSee `references\u002Fdomain_guides.md` for detailed domain strategies.\n\n## Long-Running Infrastructure\n\n### Checkpointing Strategy\n- Save checkpoint every 10 examples\n- Include job ID, progress count, queue state, timestamp\n- Keep last 3 checkpoints as backup\n\n### Progress Reporting\nReport at intervals:\n- \"Analyzed 250\u002F1000 examples (25% complete)\"\n- \"Current rate: 100 examples\u002Fday\"\n- \"Estimated completion: 7 days\"\n- \"Top emerging pattern: glassmorphic cards (15% of recent examples)\"\n\n### Rate Limiting\n- Max 1 request per second per domain\n- Respect robots.txt\n- Implement exponential backoff on errors\n\n## Anti-Patterns\n\n### 1. Scraping Too Aggressively\n**Symptom:** Requests every 100ms, same domain hammered repeatedly\n**Fix:** 1 request\u002Fsecond max, respect robots.txt, exponential backoff\n\n### 2. No Checkpointing\n**Symptom:** Running 24 hours straight without saving\n**Fix:** Save every 10 examples with timestamp and queue state\n\n### 3. Ignoring Domain Context\n**Symptom:** Applying e-commerce patterns to portfolio sites\n**Fix:** Research domain-specific best practices first\n\n### 4. Analysis Paralysis\n**Symptom:** 30 minutes per example across 1000 examples\n**Fix:** Batch process in groups of 10, deep-dive only on outliers\n\n### 5. Insufficient Diversity\n**Symptom:** Only analyzing top-tier examples\n**Fix:** Include leaders, mid-tier, and independents; geographic diversity\n\n### 6. Ignoring Historical Context\n**Symptom:** Treating all patterns as current\n**Fix:** Use Wayback Machine, note when patterns emerged, track evolution\n\n## Output Format\n\nGenerate comprehensive research packages with:\n- **Meta**: Domain, count, date range, depth\n- **Examples**: Full visual database\n- **Patterns**: Dominant, emerging, deprecated, outlier\n- **Insights**: Color\u002Ftypography\u002Flayout\u002Finteraction trends\n- **Recommendations**: Safe choices, differentiators, patterns to avoid\n\n## Cost and Scale\n\nFor 1000-example analysis:\n| Item | Cost |\n|------|------|\n| Screenshots | ~$20 (Playwright cloud @ $0.02\u002Feach) |\n| LLM Analysis | ~$15 (100 batches × $0.15) |\n| Storage | ~$0.01 (200MB) |\n| **Total** | **~$35** |\n| **Runtime** | 48-72 hours |\n\nInform users of scope and cost before beginning.\n\n## Reference Files\n\n| File | Contents |\n|------|----------|\n| `references\u002Fdata_structures.md` | TypeScript interfaces for VisualDNA, ContextAnalysis, Checkpoint |\n| `references\u002Fdomain_guides.md` | Detailed domain-specific strategies and focus areas |\n\n---\n\n**Covers:** Design Research | Pattern Recognition | Visual Analysis | Competitive Intelligence\n\n**Use with:** web-design-expert (apply findings) | competitive-cartographer (market context)\n",{"name":5,"metadata":56,"description":7,"allowed-tools":70},{"tags":57,"category":62,"pairs-with":63},[58,59,42,60,61],"design-research","patterns","visual-database","trends","Research & Analysis",[64,67],{"skill":65,"reason":66},"web-design-expert","Apply researched patterns to designs",{"skill":68,"reason":69},"competitive-cartographer","Design-focused competitive analysis","Read,Write,WebSearch,WebFetch","main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--design-archivist",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":79,"prompt":89,"zipAvailable":90},[80,83,86],{"tool":81,"command":82},"npx","npx skills add JSGforever\u002Fskillguard --skill design-archivist",{"tool":84,"command":85},"bunx","bunx skills add JSGforever\u002Fskillguard --skill design-archivist",{"tool":87,"command":88},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill design-archivist","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--design-archivist\u002FSKILL.md",true,[92,98,102,106],{"path":93,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":96,"sourceHtmlUrl":97},"CHANGELOG.md","REFERENCE","参考文档",1243,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--design-archivist\u002FCHANGELOG.md",{"path":99,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fdata_structures.md",4095,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--design-archivist\u002Freferences\u002Fdata_structures.md",{"path":103,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":104,"sourceHtmlUrl":105},"references\u002Fdomain_guides.md",6004,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--design-archivist\u002Freferences\u002Fdomain_guides.md",{"path":107,"resourceType":108,"resourceTypeDesc":109,"sizeBytes":110,"sourceHtmlUrl":111},"scripts\u002Fvalidate_archive.sh","SCRIPT","脚本",2522,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--design-archivist\u002Fscripts\u002Fvalidate_archive.sh",[113,142,156,183,204,225],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":122,"publishedAt":51},"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",[119],{"categoryNo":120,"categoryName":121,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[123,124,125,126,127,128,129,130,131,132,133,134,43,135,136,137,138,139,140,141],"scanner","skillguard codex scanner","skillguard","codex","chain","skill security","security-review","review report","structural","secret","prompt injection","security scanner","review","malicious","permissions","exposure","audit","scripts","safe",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":146,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":152,"publishedAt":51},"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",[149],{"categoryNo":150,"categoryName":151,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000033","数据分析师",[153,154,155],"data","data exfiltrator","files",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":51},"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",[],[163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182],"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":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":192,"publishedAt":51},"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",[189],{"categoryNo":190,"categoryName":191,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[172,193,180,181,194,195,196,197,48,198,163,199,200,176,178,201,179,182,202,203],"react performance optimizer","react performance","performance optimizer","app","nextjs","re","render","2025","code","router","strategies",{"skillNo":205,"name":206,"nameZh":6,"description":207,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":208,"categories":209,"keywords":211,"publishedAt":51},"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",[210],{"categoryNo":190,"categoryName":191,"taxonomyType":20,"taxonomyTypeDesc":21},[212,182,213,214,215,216,172,163,217,218,219,178,179,180,220,181,221,222,223,224],"llm streaming response handler","handler","error","processing","retry","chat ui","error recovery","critical","batch","display","text","server","read",{"skillNo":226,"name":227,"nameZh":6,"description":228,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":229,"categories":230,"keywords":238,"publishedAt":51},"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",[231,234,237],{"categoryNo":232,"categoryName":233,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":235,"categoryName":236,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":120,"categoryName":121,"taxonomyType":20,"taxonomyTypeDesc":21},[239,240,241,242,243,244,245,170,48,246,247,248,179,203,249,224,250,251,252,253],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","pipeline","testing","ci","workflows","run","release","write","edit","git"]