[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70NGHQVB7GDK3JHCFWE1KHG":3,"skill-same:01M70NGHQVB7GDK3JHCFWE1KHG":70},{"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":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M70NGHQVB7GDK3JHCFWE1KHG","performance-analysis",null,"Measurement approaches, profiling tools, optimization patterns, and capacity planning. Use when diagnosing performance issues, establishing baselines, identifying bottlenecks, or planning for scale. Always measure before optimizing.","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\u002Frsmdt-the-startup\u002Fplugins\u002Fteam\u002Fskills\u002Fquality\u002Fperformance-analysis\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"performance","analysis","performance analysis","issues","when","capacity planning","patterns","Tools","measurement","planning","for","Optimization","use","capacity","profiling","scale","2026-11-10 10:12:30",false,"---\nname: performance-analysis\ndescription: Measurement approaches, profiling tools, optimization patterns, and capacity planning. Use when diagnosing performance issues, establishing baselines, identifying bottlenecks, or planning for scale. Always measure before optimizing.\n---\n\n# Performance Profiling\n\n## When to Use\n\n- Establishing performance baselines before optimization\n- Diagnosing slow response times, high CPU, or memory issues\n- Identifying bottlenecks in application, database, or infrastructure\n- Planning capacity for expected load increases\n- Validating performance improvements after optimization\n- Creating performance budgets for new features\n\n## Core Methodology\n\n### The Golden Rule: Measure First\n\nNever optimize based on assumptions. Follow this order:\n\n1. **Measure** - Establish baseline metrics\n2. **Identify** - Find the actual bottleneck\n3. **Hypothesize** - Form a theory about the cause\n4. **Fix** - Implement targeted optimization\n5. **Validate** - Measure again to confirm improvement\n6. **Document** - Record findings and decisions\n\n### Profiling Hierarchy\n\nProfile at the right level to find the actual bottleneck:\n\n```\nApplication Level\n    |-- Request\u002FResponse timing\n    |-- Function\u002FMethod profiling\n    |-- Memory allocation tracking\n    |\nSystem Level\n    |-- CPU utilization per process\n    |-- Memory usage patterns\n    |-- I\u002FO wait times\n    |-- Network latency\n    |\nInfrastructure Level\n        |-- Database query performance\n        |-- Cache hit rates\n        |-- External service latency\n        |-- Resource saturation\n```\n\n## Profiling Patterns\n\n### CPU Profiling\n\nIdentify what code consumes CPU time:\n\n1. **Sampling profilers** - Low overhead, statistical accuracy\n2. **Instrumentation profilers** - Exact counts, higher overhead\n3. **Flame graphs** - Visual representation of call stacks\n\nKey metrics:\n- Self time (time in function itself)\n- Total time (self time + time in called functions)\n- Call count and frequency\n\n### Memory Profiling\n\nTrack allocation patterns and detect leaks:\n\n1. **Heap snapshots** - Point-in-time memory state\n2. **Allocation tracking** - What allocates memory and when\n3. **Garbage collection analysis** - GC frequency and duration\n\nKey metrics:\n- Heap size over time\n- Object retention\n- Allocation rate\n- GC pause times\n\n### I\u002FO Profiling\n\nMeasure disk and network operations:\n\n1. **Disk I\u002FO** - Read\u002Fwrite latency, throughput, IOPS\n2. **Network I\u002FO** - Latency, bandwidth, connection count\n3. **Database I\u002FO** - Query time, connection pool usage\n\nKey metrics:\n- Latency percentiles (p50, p95, p99)\n- Throughput (ops\u002Fsec, MB\u002Fsec)\n- Queue depth and wait times\n\n## Bottleneck Identification\n\n### The USE Method\n\nFor each resource, check:\n- **U**tilization - Percentage of time resource is busy\n- **S**aturation - Degree of queued work\n- **E**rrors - Error count for the resource\n\n### The RED Method\n\nFor services, measure:\n- **R**ate - Requests per second\n- **E**rrors - Failed requests per second\n- **D**uration - Distribution of request latencies\n\n### Common Bottleneck Patterns\n\n| Pattern | Symptoms | Typical Causes |\n|---------|----------|----------------|\n| CPU-bound | High CPU, low I\u002FO wait | Inefficient algorithms, tight loops |\n| Memory-bound | High memory, GC pressure | Memory leaks, large allocations |\n| I\u002FO-bound | Low CPU, high I\u002FO wait | Slow queries, network latency |\n| Lock contention | Low CPU, high wait time | Synchronization, connection pools |\n| N+1 queries | Many small DB queries | Missing joins, lazy loading |\n\n### Amdahl's Law\n\nOptimization impact is limited by the fraction of time affected:\n\n```\nIf 90% of time is in function A and 10% in function B:\n- Optimizing A by 50% = 45% total improvement\n- Optimizing B by 50% = 5% total improvement\n```\n\nFocus on the biggest contributors first.\n\n## Capacity Planning\n\n### Baseline Establishment\n\nMeasure current capacity under production load:\n\n1. **Peak load metrics** - Maximum concurrent users, requests\u002Fsec\n2. **Resource headroom** - How close to limits at peak\n3. **Scaling patterns** - Linear, sub-linear, or super-linear\n\n### Load Testing Approach\n\n1. **Establish baseline** - Current performance at normal load\n2. **Ramp testing** - Gradually increase load to find limits\n3. **Stress testing** - Push beyond limits to understand failure modes\n4. **Soak testing** - Sustained load to find memory leaks, degradation\n\n### Capacity Metrics\n\n| Metric | What It Tells You |\n|--------|-------------------|\n| Throughput at saturation | Maximum system capacity |\n| Latency at 80% load | Performance before degradation |\n| Error rate under stress | Failure patterns |\n| Recovery time | How quickly system returns to normal |\n\n### Growth Planning\n\n```\nRequired Capacity = (Current Load x Growth Factor) + Safety Margin\n\nExample:\n- Current: 1000 req\u002Fsec\n- Expected growth: 50% per year\n- Safety margin: 30%\n\nYear 1 need = (1000 x 1.5) x 1.3 = 1950 req\u002Fsec\n```\n\n## Optimization Patterns\n\n### Quick Wins\n\n1. **Enable caching** - Application, CDN, database query cache\n2. **Add indexes** - For slow queries identified in profiling\n3. **Compression** - Gzip\u002FBrotli for responses\n4. **Connection pooling** - Reduce connection overhead\n5. **Batch operations** - Reduce round-trips\n\n### Algorithmic Improvements\n\n1. **Reduce complexity** - O(n^2) to O(n log n)\n2. **Lazy evaluation** - Defer work until needed\n3. **Memoization** - Cache computed results\n4. **Pagination** - Limit data processed at once\n\n### Architectural Changes\n\n1. **Horizontal scaling** - Add more instances\n2. **Async processing** - Queue background work\n3. **Read replicas** - Distribute read load\n4. **Caching layers** - Redis, Memcached\n5. **CDN** - Edge caching for static content\n\n## Best Practices\n\n- Profile in production-like environments; development can have different characteristics\n- Use percentiles (p95, p99) not averages for latency\n- Monitor continuously, not just during incidents\n- Set performance budgets and enforce them in CI\n- Document baseline metrics before making changes\n- Keep profiling overhead low in production\n- Correlate metrics across layers (application, database, infrastructure)\n- Understand the difference between latency and throughput\n\n## Anti-Patterns\n\n- Optimizing without measurement\n- Using averages for latency metrics\n- Profiling only in development\n- Ignoring tail latencies (p99, p999)\n- Premature optimization of non-bottleneck code\n- Over-engineering for hypothetical scale\n- Caching without invalidation strategy\n\n## References\n\n- [Profiling Tools Reference](references\u002Fprofiling-tools.md) - Tools by language and platform\n","# Performance Profiling\n\n## When to Use\n\n- Establishing performance baselines before optimization\n- Diagnosing slow response times, high CPU, or memory issues\n- Identifying bottlenecks in application, database, or infrastructure\n- Planning capacity for expected load increases\n- Validating performance improvements after optimization\n- Creating performance budgets for new features\n\n## Core Methodology\n\n### The Golden Rule: Measure First\n\nNever optimize based on assumptions. Follow this order:\n\n1. **Measure** - Establish baseline metrics\n2. **Identify** - Find the actual bottleneck\n3. **Hypothesize** - Form a theory about the cause\n4. **Fix** - Implement targeted optimization\n5. **Validate** - Measure again to confirm improvement\n6. **Document** - Record findings and decisions\n\n### Profiling Hierarchy\n\nProfile at the right level to find the actual bottleneck:\n\n```\nApplication Level\n    |-- Request\u002FResponse timing\n    |-- Function\u002FMethod profiling\n    |-- Memory allocation tracking\n    |\nSystem Level\n    |-- CPU utilization per process\n    |-- Memory usage patterns\n    |-- I\u002FO wait times\n    |-- Network latency\n    |\nInfrastructure Level\n        |-- Database query performance\n        |-- Cache hit rates\n        |-- External service latency\n        |-- Resource saturation\n```\n\n## Profiling Patterns\n\n### CPU Profiling\n\nIdentify what code consumes CPU time:\n\n1. **Sampling profilers** - Low overhead, statistical accuracy\n2. **Instrumentation profilers** - Exact counts, higher overhead\n3. **Flame graphs** - Visual representation of call stacks\n\nKey metrics:\n- Self time (time in function itself)\n- Total time (self time + time in called functions)\n- Call count and frequency\n\n### Memory Profiling\n\nTrack allocation patterns and detect leaks:\n\n1. **Heap snapshots** - Point-in-time memory state\n2. **Allocation tracking** - What allocates memory and when\n3. **Garbage collection analysis** - GC frequency and duration\n\nKey metrics:\n- Heap size over time\n- Object retention\n- Allocation rate\n- GC pause times\n\n### I\u002FO Profiling\n\nMeasure disk and network operations:\n\n1. **Disk I\u002FO** - Read\u002Fwrite latency, throughput, IOPS\n2. **Network I\u002FO** - Latency, bandwidth, connection count\n3. **Database I\u002FO** - Query time, connection pool usage\n\nKey metrics:\n- Latency percentiles (p50, p95, p99)\n- Throughput (ops\u002Fsec, MB\u002Fsec)\n- Queue depth and wait times\n\n## Bottleneck Identification\n\n### The USE Method\n\nFor each resource, check:\n- **U**tilization - Percentage of time resource is busy\n- **S**aturation - Degree of queued work\n- **E**rrors - Error count for the resource\n\n### The RED Method\n\nFor services, measure:\n- **R**ate - Requests per second\n- **E**rrors - Failed requests per second\n- **D**uration - Distribution of request latencies\n\n### Common Bottleneck Patterns\n\n| Pattern | Symptoms | Typical Causes |\n|---------|----------|----------------|\n| CPU-bound | High CPU, low I\u002FO wait | Inefficient algorithms, tight loops |\n| Memory-bound | High memory, GC pressure | Memory leaks, large allocations |\n| I\u002FO-bound | Low CPU, high I\u002FO wait | Slow queries, network latency |\n| Lock contention | Low CPU, high wait time | Synchronization, connection pools |\n| N+1 queries | Many small DB queries | Missing joins, lazy loading |\n\n### Amdahl's Law\n\nOptimization impact is limited by the fraction of time affected:\n\n```\nIf 90% of time is in function A and 10% in function B:\n- Optimizing A by 50% = 45% total improvement\n- Optimizing B by 50% = 5% total improvement\n```\n\nFocus on the biggest contributors first.\n\n## Capacity Planning\n\n### Baseline Establishment\n\nMeasure current capacity under production load:\n\n1. **Peak load metrics** - Maximum concurrent users, requests\u002Fsec\n2. **Resource headroom** - How close to limits at peak\n3. **Scaling patterns** - Linear, sub-linear, or super-linear\n\n### Load Testing Approach\n\n1. **Establish baseline** - Current performance at normal load\n2. **Ramp testing** - Gradually increase load to find limits\n3. **Stress testing** - Push beyond limits to understand failure modes\n4. **Soak testing** - Sustained load to find memory leaks, degradation\n\n### Capacity Metrics\n\n| Metric | What It Tells You |\n|--------|-------------------|\n| Throughput at saturation | Maximum system capacity |\n| Latency at 80% load | Performance before degradation |\n| Error rate under stress | Failure patterns |\n| Recovery time | How quickly system returns to normal |\n\n### Growth Planning\n\n```\nRequired Capacity = (Current Load x Growth Factor) + Safety Margin\n\nExample:\n- Current: 1000 req\u002Fsec\n- Expected growth: 50% per year\n- Safety margin: 30%\n\nYear 1 need = (1000 x 1.5) x 1.3 = 1950 req\u002Fsec\n```\n\n## Optimization Patterns\n\n### Quick Wins\n\n1. **Enable caching** - Application, CDN, database query cache\n2. **Add indexes** - For slow queries identified in profiling\n3. **Compression** - Gzip\u002FBrotli for responses\n4. **Connection pooling** - Reduce connection overhead\n5. **Batch operations** - Reduce round-trips\n\n### Algorithmic Improvements\n\n1. **Reduce complexity** - O(n^2) to O(n log n)\n2. **Lazy evaluation** - Defer work until needed\n3. **Memoization** - Cache computed results\n4. **Pagination** - Limit data processed at once\n\n### Architectural Changes\n\n1. **Horizontal scaling** - Add more instances\n2. **Async processing** - Queue background work\n3. **Read replicas** - Distribute read load\n4. **Caching layers** - Redis, Memcached\n5. **CDN** - Edge caching for static content\n\n## Best Practices\n\n- Profile in production-like environments; development can have different characteristics\n- Use percentiles (p95, p99) not averages for latency\n- Monitor continuously, not just during incidents\n- Set performance budgets and enforce them in CI\n- Document baseline metrics before making changes\n- Keep profiling overhead low in production\n- Correlate metrics across layers (application, database, infrastructure)\n- Understand the difference between latency and throughput\n\n## Anti-Patterns\n\n- Optimizing without measurement\n- Using averages for latency metrics\n- Profiling only in development\n- Ignoring tail latencies (p99, p999)\n- Premature optimization of non-bottleneck code\n- Over-engineering for hypothetical scale\n- Caching without invalidation strategy\n\n## References\n\n- [Profiling Tools Reference](references\u002Fprofiling-tools.md) - Tools by language and platform\n",{"name":5,"description":7},"main","7850740bd837adb32f0a109ab2af82482196c6f2","skills\u002Frsmdt-the-startup\u002Fplugins\u002Fteam\u002Fskills\u002Fquality\u002Fperformance-analysis",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":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add shengdabai\u002FTony-Claude-Code-Skills --skill performance-analysis",{"tool":56,"command":57},"bunx","bunx skills add shengdabai\u002FTony-Claude-Code-Skills --skill performance-analysis",{"tool":59,"command":60},"pnpm","pnpm dlx skills add shengdabai\u002FTony-Claude-Code-Skills --skill performance-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Frsmdt-the-startup\u002Fplugins\u002Fteam\u002Fskills\u002Fquality\u002Fperformance-analysis\u002FSKILL.md",true,[64],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fprofiling-tools.md","REFERENCE","参考文档",9988,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Frsmdt-the-startup\u002Fplugins\u002Fteam\u002Fskills\u002Fquality\u002Fperformance-analysis\u002Freferences\u002Fprofiling-tools.md",[71,90,124,149,171,191],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":82,"publishedAt":35},"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",[77],{"categoryNo":78,"categoryName":79,"taxonomyType":80,"taxonomyTypeDesc":81},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",[83,84,85,86,87,88,89],"methodology","xiaolai","xiaolai methodology","朋友","投资","writing","收入",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":104,"publishedAt":35},"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",[96,99],{"categoryNo":97,"categoryName":98,"taxonomyType":80,"taxonomyTypeDesc":81},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":100,"categoryName":101,"taxonomyType":102,"taxonomyTypeDesc":103},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[92,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123],"knowledge","wiki","explore","walkthrough","project","get","knowledge base","run","generate","intent","cli","map","documentation","project wiki","disk","architecture","code","unknown","generated",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":134,"publishedAt":35},"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",[130,131],{"categoryNo":97,"categoryName":98,"taxonomyType":80,"taxonomyTypeDesc":81},{"categoryNo":132,"categoryName":133,"taxonomyType":102,"taxonomyTypeDesc":103},"01JBSEEDCAT000000000000036","内容创作者",[126,135,136,137,138,139,140,141,113,142,143,144,23,31,145,146,147,148],"user","content","视频","creator","generate video","videos","launch","video content","create","upload","auto","types","Video","创作",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":156,"publishedAt":35},"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",[155],{"categoryNo":97,"categoryName":98,"taxonomyType":80,"taxonomyTypeDesc":81},[157,158,126,159,160,147,161,162,163,164,165,166,167,168,111,169,23,31,105,170],"sync","script","youtube script sync","recording","shorts","first","base","person","update","active","child","optimize","idempotent","long",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":181,"publishedAt":35},"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",[177,178,179,180],{"categoryNo":78,"categoryName":79,"taxonomyType":80,"taxonomyTypeDesc":81},{"categoryNo":97,"categoryName":98,"taxonomyType":80,"taxonomyTypeDesc":81},{"categoryNo":100,"categoryName":101,"taxonomyType":102,"taxonomyTypeDesc":103},{"categoryNo":132,"categoryName":133,"taxonomyType":102,"taxonomyTypeDesc":103},[182,88,183,184,185,186,121,23,31,187,188,189,190],"writing skills","how","teach","write skill","write","claude code skills","files","how to","trigger",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":199,"publishedAt":35},"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",[197,198],{"categoryNo":78,"categoryName":79,"taxonomyType":80,"taxonomyTypeDesc":81},{"categoryNo":132,"categoryName":133,"taxonomyType":102,"taxonomyTypeDesc":103},[200,88,201,109,202,188,23,183,186,31,189],"Rules","writing rules","project rules"]