[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M754YSPNZW3CEJPDJ15ECN2M":3,"skill-same:01M754YSPNZW3CEJPDJ15ECN2M":57},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":36,"updatedAt":37,"install":38,"resources":50},"01M754YSPNZW3CEJPDJ15ECN2M","x-profile-performance",null,"Automated profiling: detect language\u002Fruntime, select appropriate profiler, execute session, generate flamegraph, identify hotspots, and suggest optimizations referencing the performance-engineering knowledge pack.","review-bench\u002Federcnj_ia-dev-environment","review-bench","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F286778065?v=4","01M7517F9NTEPDZDAXJBR30FWT","ReviewBench","01M7517FAC9F4P7TGWCNJ8VYVW",0,"MIT","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring-fintech-pci\u002F.claude\u002Fskills\u002Fx-profile-performance\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: x-profile-performance\ndescription: \"Automated profiling: detect language\u002Fruntime, select appropriate profiler, execute session, generate flamegraph, identify hotspots, and suggest optimizations referencing the performance-engineering knowledge pack.\"\nuser-invocable: true\nallowed-tools: Read, Bash, Glob, Grep, Agent\nargument-hint: \"[cpu|memory|io|all] [--duration 30s] [--output flamegraph|report|raw]\"\ncontext-budget: medium\nrequires-capabilities: []\n---\n\n## Global Output Policy\n\n- **Language**: English ONLY.\n- **Tone**: Technical, Direct, and Concise.\n- **Efficiency**: Remove all conversational fillers and greetings to save tokens.\n\n# Skill: Performance Profiling\n\n## Purpose\n\nExecute automated profiling sessions for {{PROJECT_NAME}}. Detect the project language\u002Fruntime, select the appropriate profiler, configure and run a profiling session, generate flamegraph or report output, identify hotspots, and suggest optimizations referencing the performance-engineering knowledge pack.\n\n## Triggers\n\n- `\u002Fx-profile-performance cpu` — CPU profiling with default duration\n- `\u002Fx-profile-performance memory` — memory\u002Fheap profiling\n- `\u002Fx-profile-performance io` — I\u002FO profiling (disk, network)\n- `\u002Fx-profile-performance all` — combined profiling (CPU + memory + I\u002FO)\n- `\u002Fx-profile-performance cpu --duration 60s` — CPU profiling for 60 seconds\n- `\u002Fx-profile-performance cpu --output flamegraph` — generate flamegraph SVG\n- `\u002Fx-profile-performance cpu --output report` — generate Markdown report\n- `\u002Fx-profile-performance cpu --output raw` — output native profiler format\n\n## Parameters\n\n| Parameter | Type | Required | Default | Description |\n|-----------|------|----------|---------|-------------|\n| `type` | Enum | No | `cpu` | Profiling type: `cpu`, `memory`, `io`, `all` |\n| `--duration` | Duration | No | `30s` | Recording duration |\n| `--output` | Enum | No | `flamegraph` | Output format: `flamegraph`, `report`, `raw` |\n\n## Workflow\n\n### Step 1 — Detect Language\u002FRuntime\n\nAnalyze project root for build\u002Fdependency files to identify the technology stack:\n\n| File | Language\u002FRuntime | Detection Priority |\n|------|-----------------|-------------------|\n| `pom.xml` | Java (Maven) | 1 |\n| `build.gradle` \u002F `build.gradle.kts` | Java\u002FKotlin (Gradle) | 1 |\n| `go.mod` | Go | 1 |\n| `Cargo.toml` | Rust | 1 |\n| `pyproject.toml` \u002F `requirements.txt` | Python | 1 |\n| `package.json` | Node.js\u002FTypeScript | 1 |\n| `mix.exs` | Elixir | 2 |\n| `Gemfile` | Ruby | 2 |\n\n```bash\n# Auto-detect language from project root\nls -la pom.xml build.gradle* go.mod Cargo.toml pyproject.toml package.json 2>\u002Fdev\u002Fnull\n```\n\n### Step 2 — Select Appropriate Profiler\n\nBased on detected language, select the best profiler:\n\n| Language | CPU Profiler | Memory Profiler | I\u002FO Profiler |\n|----------|-------------|-----------------|--------------|\n| **Java** | JFR (Java Flight Recorder) \u002F async-profiler | JFR heap profiling | JFR I\u002FO events |\n| **Go** | pprof (CPU profile) | pprof (heap profile) | pprof (block\u002Fgoroutine) |\n| **Python** | py-spy (sampling) | memray \u002F tracemalloc | cProfile + I\u002FO tracing |\n| **Rust** | perf \u002F flamegraph-rs | DHAT \u002F heaptrack | perf I\u002FO events |\n| **Node.js** | clinic.js \u002F 0x | --inspect + Chrome DevTools | clinic.js doctor |\n| **Other** | perf (Linux) \u002F dtrace (macOS) | Valgrind massif | strace\u002Fperf |\n\n#### 2.1 — Java JFR Configuration\n\n```bash\n# Start JFR recording\njava -XX:StartFlightRecording=duration=30s,filename=profile.jfr -jar app.jar\n\n# Using async-profiler for flamegraph\n.\u002Fasprof -d 30 -f flamegraph.html \u003Cpid>\n\n# Analyze JFR recording\njfr print --events jdk.CPULoad,jdk.ThreadAllocationStatistics profile.jfr\n```\n\n#### 2.2 — Go pprof Configuration\n\n```bash\n# CPU profiling (requires net\u002Fhttp\u002Fpprof import)\ngo tool pprof http:\u002F\u002Flocalhost:6060\u002Fdebug\u002Fpprof\u002Fprofile?seconds=30\n\n# Memory profiling\ngo tool pprof http:\u002F\u002Flocalhost:6060\u002Fdebug\u002Fpprof\u002Fheap\n\n# Generate flamegraph\ngo tool pprof -http=:8080 profile.pb.gz\n```\n\n#### 2.3 — Python py-spy Configuration\n\n```bash\n# CPU profiling with py-spy\npy-spy record -o flamegraph.svg --pid \u003Cpid> --duration 30\n\n# Memory profiling with memray\nmemray run --output profile.bin script.py\nmemray flamegraph profile.bin -o flamegraph.html\n\n# Top-like real-time profiling\npy-spy top --pid \u003Cpid>\n```\n\n### Step 3 — Configure Profiling Session\n\nConfigure session parameters based on arguments:\n\n| Parameter | Default | Description |\n|-----------|---------|-------------|\n| `type` | `cpu` | Profiling type: cpu, memory, io, all |\n| `duration` | `30s` | Recording duration |\n| `sampling-rate` | Profiler default | Sampling frequency (Hz) |\n| `output` | `flamegraph` | Output format: flamegraph, report, raw |\n\n**Session configuration checklist:**\n\n- [ ] Profiler installed and accessible\n- [ ] Target application running and healthy\n- [ ] Sufficient disk space for profiling data\n- [ ] JVM flags configured (for Java: `-XX:+UnlockDiagnosticVMOptions`)\n- [ ] Profiling port accessible (for remote profiling)\n\n### Step 4 — Execute Profiling\n\nRun the selected profiler with configured parameters. Monitor for:\n\n- Profiler overhead (should be \u003C 5% for sampling profilers)\n- Disk space consumption\n- Application stability during profiling\n- Recording completion without errors\n\n### Step 5 — Generate Flamegraph\u002FReport\n\n#### 5.1 — Flamegraph Output (SVG\u002FHTML)\n\nGenerate interactive flamegraph from profiler output:\n\n- **Java JFR**: Use `jfr` tool or async-profiler to convert to flamegraph\n- **Go pprof**: Use `go tool pprof -http=:8080` for web-based flamegraph\n- **Python py-spy**: Direct SVG output with `--format flamegraph`\n- **Generic**: Use Brendan Gregg's FlameGraph scripts\n\n#### 5.2 — Markdown Report Output\n\nGenerate structured report with:\n\n```markdown\n# Profiling Report — {{PROJECT_NAME}}\n\n**Date:** YYYY-MM-DD\n**Duration:** Ns\n**Type:** cpu|memory|io\n\n## Top Hotspots\n\n| Rank | Function | Self Time | Total Time | % |\n|------|----------|-----------|------------|---|\n| 1 | com.example.Service.process() | 450ms | 1200ms | 37.5% |\n| 2 | com.example.Repo.query() | 320ms | 800ms | 26.7% |\n\n## Call Tree (Top 10)\n\n[Hierarchical call tree with timing]\n\n## Recommendations\n\n[Optimization suggestions based on hotspots]\n```\n\n#### 5.3 — Raw Output\n\nOutput the native profiler format without transformation:\n- JFR: `.jfr` file\n- pprof: `.pb.gz` file\n- py-spy: speedscope JSON\n\n### Step 6 — Identify Hotspots\n\nAnalyze profiling results to identify performance hotspots:\n\n**CPU Hotspots:**\n- Functions consuming > 10% of total CPU time\n- Recursive call patterns with deep stack depth\n- Lock contention points (high wait time)\n\n**Memory Hotspots:**\n- Objects with highest allocation rate\n- Memory leak candidates (growing heap over time)\n- Large object allocations (> 1MB per allocation)\n\n**I\u002FO Hotspots:**\n- Blocking I\u002FO operations on hot paths\n- Excessive network round-trips\n- Unbuffered file operations\n\n### Step 7 — Suggest Optimizations\n\nReference the performance-engineering knowledge pack for contextualized optimization suggestions:\n\n| Hotspot Type | Common Optimizations |\n|-------------|---------------------|\n| CPU-bound loops | Algorithm optimization, caching, parallelization |\n| Memory allocation | Object pooling, value types, lazy initialization |\n| I\u002FO blocking | Async I\u002FO, connection pooling, batching |\n| Lock contention | Lock-free data structures, read-write locks, partitioning |\n| GC pressure | Reduce allocation rate, tune GC parameters, off-heap storage |\n| Serialization | Binary formats (protobuf), zero-copy, pre-computed serialization |\n\n## Error Handling\n\n| Scenario | Action |\n|----------|--------|\n| Language not detected | List supported languages, ask user to specify |\n| Profiler not installed | Provide installation instructions for detected stack |\n| Application not running | Instruct user to start the application first |\n| Permission denied | Suggest running with appropriate privileges (sudo\u002Fptrace) |\n| Recording failed | Check disk space, profiler compatibility, retry once |\n| Empty profiling data | Verify application is under load during profiling |\n\n## Integration Notes\n\n| Skill | Relationship | Context |\n|-------|-------------|---------|\n| x-run-perf-tests | complements | Performance tests generate load; profiling captures behavior |\n| x-troubleshoot-operations | calls | Troubleshooting may invoke profiling for performance issues |\n| x-review-codebase | called-by | Performance review specialist may reference profiling results |\n\n## Knowledge Pack References\n\n| Knowledge Pack | Usage |\n|----------------|-------|\n| performance-engineering | Optimization patterns, profiler selection, hotspot classification |\n","## Global Output Policy\n\n- **Language**: English ONLY.\n- **Tone**: Technical, Direct, and Concise.\n- **Efficiency**: Remove all conversational fillers and greetings to save tokens.\n\n# Skill: Performance Profiling\n\n## Purpose\n\nExecute automated profiling sessions for {{PROJECT_NAME}}. Detect the project language\u002Fruntime, select the appropriate profiler, configure and run a profiling session, generate flamegraph or report output, identify hotspots, and suggest optimizations referencing the performance-engineering knowledge pack.\n\n## Triggers\n\n- `\u002Fx-profile-performance cpu` — CPU profiling with default duration\n- `\u002Fx-profile-performance memory` — memory\u002Fheap profiling\n- `\u002Fx-profile-performance io` — I\u002FO profiling (disk, network)\n- `\u002Fx-profile-performance all` — combined profiling (CPU + memory + I\u002FO)\n- `\u002Fx-profile-performance cpu --duration 60s` — CPU profiling for 60 seconds\n- `\u002Fx-profile-performance cpu --output flamegraph` — generate flamegraph SVG\n- `\u002Fx-profile-performance cpu --output report` — generate Markdown report\n- `\u002Fx-profile-performance cpu --output raw` — output native profiler format\n\n## Parameters\n\n| Parameter | Type | Required | Default | Description |\n|-----------|------|----------|---------|-------------|\n| `type` | Enum | No | `cpu` | Profiling type: `cpu`, `memory`, `io`, `all` |\n| `--duration` | Duration | No | `30s` | Recording duration |\n| `--output` | Enum | No | `flamegraph` | Output format: `flamegraph`, `report`, `raw` |\n\n## Workflow\n\n### Step 1 — Detect Language\u002FRuntime\n\nAnalyze project root for build\u002Fdependency files to identify the technology stack:\n\n| File | Language\u002FRuntime | Detection Priority |\n|------|-----------------|-------------------|\n| `pom.xml` | Java (Maven) | 1 |\n| `build.gradle` \u002F `build.gradle.kts` | Java\u002FKotlin (Gradle) | 1 |\n| `go.mod` | Go | 1 |\n| `Cargo.toml` | Rust | 1 |\n| `pyproject.toml` \u002F `requirements.txt` | Python | 1 |\n| `package.json` | Node.js\u002FTypeScript | 1 |\n| `mix.exs` | Elixir | 2 |\n| `Gemfile` | Ruby | 2 |\n\n```bash\n# Auto-detect language from project root\nls -la pom.xml build.gradle* go.mod Cargo.toml pyproject.toml package.json 2>\u002Fdev\u002Fnull\n```\n\n### Step 2 — Select Appropriate Profiler\n\nBased on detected language, select the best profiler:\n\n| Language | CPU Profiler | Memory Profiler | I\u002FO Profiler |\n|----------|-------------|-----------------|--------------|\n| **Java** | JFR (Java Flight Recorder) \u002F async-profiler | JFR heap profiling | JFR I\u002FO events |\n| **Go** | pprof (CPU profile) | pprof (heap profile) | pprof (block\u002Fgoroutine) |\n| **Python** | py-spy (sampling) | memray \u002F tracemalloc | cProfile + I\u002FO tracing |\n| **Rust** | perf \u002F flamegraph-rs | DHAT \u002F heaptrack | perf I\u002FO events |\n| **Node.js** | clinic.js \u002F 0x | --inspect + Chrome DevTools | clinic.js doctor |\n| **Other** | perf (Linux) \u002F dtrace (macOS) | Valgrind massif | strace\u002Fperf |\n\n#### 2.1 — Java JFR Configuration\n\n```bash\n# Start JFR recording\njava -XX:StartFlightRecording=duration=30s,filename=profile.jfr -jar app.jar\n\n# Using async-profiler for flamegraph\n.\u002Fasprof -d 30 -f flamegraph.html \u003Cpid>\n\n# Analyze JFR recording\njfr print --events jdk.CPULoad,jdk.ThreadAllocationStatistics profile.jfr\n```\n\n#### 2.2 — Go pprof Configuration\n\n```bash\n# CPU profiling (requires net\u002Fhttp\u002Fpprof import)\ngo tool pprof http:\u002F\u002Flocalhost:6060\u002Fdebug\u002Fpprof\u002Fprofile?seconds=30\n\n# Memory profiling\ngo tool pprof http:\u002F\u002Flocalhost:6060\u002Fdebug\u002Fpprof\u002Fheap\n\n# Generate flamegraph\ngo tool pprof -http=:8080 profile.pb.gz\n```\n\n#### 2.3 — Python py-spy Configuration\n\n```bash\n# CPU profiling with py-spy\npy-spy record -o flamegraph.svg --pid \u003Cpid> --duration 30\n\n# Memory profiling with memray\nmemray run --output profile.bin script.py\nmemray flamegraph profile.bin -o flamegraph.html\n\n# Top-like real-time profiling\npy-spy top --pid \u003Cpid>\n```\n\n### Step 3 — Configure Profiling Session\n\nConfigure session parameters based on arguments:\n\n| Parameter | Default | Description |\n|-----------|---------|-------------|\n| `type` | `cpu` | Profiling type: cpu, memory, io, all |\n| `duration` | `30s` | Recording duration |\n| `sampling-rate` | Profiler default | Sampling frequency (Hz) |\n| `output` | `flamegraph` | Output format: flamegraph, report, raw |\n\n**Session configuration checklist:**\n\n- [ ] Profiler installed and accessible\n- [ ] Target application running and healthy\n- [ ] Sufficient disk space for profiling data\n- [ ] JVM flags configured (for Java: `-XX:+UnlockDiagnosticVMOptions`)\n- [ ] Profiling port accessible (for remote profiling)\n\n### Step 4 — Execute Profiling\n\nRun the selected profiler with configured parameters. Monitor for:\n\n- Profiler overhead (should be \u003C 5% for sampling profilers)\n- Disk space consumption\n- Application stability during profiling\n- Recording completion without errors\n\n### Step 5 — Generate Flamegraph\u002FReport\n\n#### 5.1 — Flamegraph Output (SVG\u002FHTML)\n\nGenerate interactive flamegraph from profiler output:\n\n- **Java JFR**: Use `jfr` tool or async-profiler to convert to flamegraph\n- **Go pprof**: Use `go tool pprof -http=:8080` for web-based flamegraph\n- **Python py-spy**: Direct SVG output with `--format flamegraph`\n- **Generic**: Use Brendan Gregg's FlameGraph scripts\n\n#### 5.2 — Markdown Report Output\n\nGenerate structured report with:\n\n```markdown\n# Profiling Report — {{PROJECT_NAME}}\n\n**Date:** YYYY-MM-DD\n**Duration:** Ns\n**Type:** cpu|memory|io\n\n## Top Hotspots\n\n| Rank | Function | Self Time | Total Time | % |\n|------|----------|-----------|------------|---|\n| 1 | com.example.Service.process() | 450ms | 1200ms | 37.5% |\n| 2 | com.example.Repo.query() | 320ms | 800ms | 26.7% |\n\n## Call Tree (Top 10)\n\n[Hierarchical call tree with timing]\n\n## Recommendations\n\n[Optimization suggestions based on hotspots]\n```\n\n#### 5.3 — Raw Output\n\nOutput the native profiler format without transformation:\n- JFR: `.jfr` file\n- pprof: `.pb.gz` file\n- py-spy: speedscope JSON\n\n### Step 6 — Identify Hotspots\n\nAnalyze profiling results to identify performance hotspots:\n\n**CPU Hotspots:**\n- Functions consuming > 10% of total CPU time\n- Recursive call patterns with deep stack depth\n- Lock contention points (high wait time)\n\n**Memory Hotspots:**\n- Objects with highest allocation rate\n- Memory leak candidates (growing heap over time)\n- Large object allocations (> 1MB per allocation)\n\n**I\u002FO Hotspots:**\n- Blocking I\u002FO operations on hot paths\n- Excessive network round-trips\n- Unbuffered file operations\n\n### Step 7 — Suggest Optimizations\n\nReference the performance-engineering knowledge pack for contextualized optimization suggestions:\n\n| Hotspot Type | Common Optimizations |\n|-------------|---------------------|\n| CPU-bound loops | Algorithm optimization, caching, parallelization |\n| Memory allocation | Object pooling, value types, lazy initialization |\n| I\u002FO blocking | Async I\u002FO, connection pooling, batching |\n| Lock contention | Lock-free data structures, read-write locks, partitioning |\n| GC pressure | Reduce allocation rate, tune GC parameters, off-heap storage |\n| Serialization | Binary formats (protobuf), zero-copy, pre-computed serialization |\n\n## Error Handling\n\n| Scenario | Action |\n|----------|--------|\n| Language not detected | List supported languages, ask user to specify |\n| Profiler not installed | Provide installation instructions for detected stack |\n| Application not running | Instruct user to start the application first |\n| Permission denied | Suggest running with appropriate privileges (sudo\u002Fptrace) |\n| Recording failed | Check disk space, profiler compatibility, retry once |\n| Empty profiling data | Verify application is under load during profiling |\n\n## Integration Notes\n\n| Skill | Relationship | Context |\n|-------|-------------|---------|\n| x-run-perf-tests | complements | Performance tests generate load; profiling captures behavior |\n| x-troubleshoot-operations | calls | Troubleshooting may invoke profiling for performance issues |\n| x-review-codebase | called-by | Performance review specialist may reference profiling results |\n\n## Knowledge Pack References\n\n| Knowledge Pack | Usage |\n|----------------|-------|\n| performance-engineering | Optimization patterns, profiler selection, hotspot classification |\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25,"context-budget":26,"user-invocable":27,"requires-capabilities":28},"Read, Bash, Glob, Grep, Agent","[cpu|memory|io|all] [--duration 30s] [--output flamegraph|report|raw]","medium",true,[],"main","952a630c6f38d193a349d86fa18db1de8843e837","src\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring-fintech-pci\u002F.claude\u002Fskills\u002Fx-profile-performance",1,"https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment","https:\u002F\u002Fgithub.com\u002Freview-bench","https:\u002F\u002Freview-bench.ai","An open benchmark for AI code review.","2026-10-27 06:56:37",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":27},[40,43,46],{"tool":41,"command":42},"npx","npx skills add review-bench\u002Federcnj_ia-dev-environment --skill x-profile-performance",{"tool":44,"command":45},"bunx","bunx skills add review-bench\u002Federcnj_ia-dev-environment --skill x-profile-performance",{"tool":47,"command":48},"pnpm","pnpm dlx skills add review-bench\u002Federcnj_ia-dev-environment --skill x-profile-performance","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring-fintech-pci\u002F.claude\u002Fskills\u002Fx-profile-performance\u002FSKILL.md",[51],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"README.md","REFERENCE","参考文档",1966,"https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring-fintech-pci\u002F.claude\u002Fskills\u002Fx-profile-performance\u002FREADME.md",[58,65,72,79,86,93],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M757M8J48TQ1Y3X25GSJBXAS","x-parallel-eval","Detects and classifies file-collision risks between work units (tasks, stories, or epic phases) before parallel execution. Reads ## File Footprint blocks produced by x-task-plan \u002F x-story-plan, applies the parallelism-heuristics knowledge pack (hard \u002F regen \u002F soft categories + hotspot overrides), and emits a collision matrix + serialization recommendation in Markdown (default) or JSON.","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fx-parallel-eval\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M757M57XMR9546S69466HDWT","parallelism-heuristics","Canonical catalog of file-collision heuristics for parallel task, story, and epic execution. Defines the File Footprint block format, the three Conflict Categories (hard \u002F regen \u002F soft), a hotspot list of high-contention paths, and the degrade-with-warning policy. Consumed by x-task-plan, x-story-plan, x-epic-map, x-parallel-eval, and x-dev-*-implement.","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fparallelism-heuristics\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M757M11SZ8P1VCQABT08QVYA","x-watch-pr-ci","Polls a PR's CI checks and Copilot review status, blocking until checks complete or timeout. Returns one of 8 stable exit codes (SUCCESS=0, CI_PENDING_PROCEED=10, CI_FAILED=20, TIMEOUT=30, PR_ALREADY_MERGED=40, NO_CI_CONFIGURED=50, PR_CLOSED=60, PR_NOT_FOUND=70). Writes a versioned state-file for session resume.","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring\u002Fplatform-claude-code\u002F.claude\u002Fskills\u002Fx-watch-pr-ci\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M757KW53K8KFPGADFB4PH949","x-validate-docs","Documentation freshness gate: validates 6 dimensions (readme, api-specs, grpc-proto, adr, skill-docs, system-architecture) against code changes in a PR. Stack-aware — only validates targets declared\u002Fauto-detected from ProjectConfig.documentation.targets. Returns exit non-zero on staleness; produces structured report.","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring\u002Fplatform-claude-code\u002F.claude\u002Fskills\u002Fx-validate-docs\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M757KQZHSA10MKC0CR571D60","x-update-system-architecture","Incrementally updates docs\u002Farchitecture\u002Fsystem.md after an epic completes. Appends new entries to the Decision Log (§11) using x-internal-write-report --append (dedup by ## ID: marker) and surgically inserts component\u002Fintegration changes into sections 1-10 via Edit. Idempotent: re-running with the same epic produces a byte-identical system.md.","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring\u002Fplatform-claude-code\u002F.claude\u002Fskills\u002Fx-update-system-architecture\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M757KKBT5Q1SVF8DMJBVF46M","x-update-architecture","Incrementally updates the service architecture document with changes from architecture plans. Adds new components, integrations, flows, and ADR references without rewriting existing content. Use after implementation to keep architecture documentation current.","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring\u002Fplatform-claude-code\u002F.claude\u002Fskills\u002Fx-update-architecture\u002FSKILL.md",[],[]]