[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73BYH3CG2JASC2CCD6GXC4J":3,"skill-same:01M73BYH3CG2JASC2CCD6GXC4J":70},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":14,"categories":15,"keywords":16,"publishedAt":17,"linkOnly":18,"markdownContent":19,"markdownBody":20,"frontMatter":21,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":12,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M73BYH3CG2JASC2CCD6GXC4J","worker-benchmarks",null,"ngdletrung\u002FJKAI-Zenith","ngdletrung","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F88302940?v=4","01M73BJVV5QJ87R3MC4BXJMWDN","01M73BJVWAAM03TM18QHKRDAMH",0,"MIT","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FCORE\u002Fworker-benchmarks\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nid: worker-benchmarks\nname_vn: worker-benchmarks\nversion: 1.0.0\nauthor: Zenith Legacy\ndomain: UNKNOWN\nintent_pairs: []\naliases_vn: []\nschema: {}\npriority: NORMAL\nrelated_skills: []\n\n---\n\n# worker-benchmarks (worker-benchmarks)\n\n## 🌟 TỔNG QUAN\n---\nname: worker-benchmarks\ndescription: Run comprehensive worker system benchmarks and performance analysis\nversion: 1.0.0\ninvocable: true\nauthor: agentic-flow\ncapabilities:\n  - performance_testing\n  - metrics_collection\n  - optimization_recommendations\n---\n\n# Worker Benchmarks Skill\n\nRun comprehensive performance benchmarks for the agentic-flow worker system.\n\n## Quick Start\n\n```bash\n# Run full benchmark suite\nnpx agentic-flow workers benchmark\n\n# Run specific benchmark\nnpx agentic-flow workers benchmark --type trigger-detection\nnpx agentic-flow workers benchmark --type registry\nnpx agentic-flow workers benchmark --type agent-selection\nnpx agentic-flow workers benchmark --type concurrent\n```\n\n## Benchmark Types\n\n### 1. Trigger Detection (`trigger-detection`)\nTests keyword detection speed across 12 worker triggers.\n- **Target**: p95 \u003C 5ms\n- **Iterations**: 1000\n- **Metrics**: latency, throughput, histogram\n\n### 2. Worker Registry (`registry`)\nTests CRUD operations on worker entries.\n- **Target**: p95 \u003C 10ms\n- **Iterations**: 500 creates, gets, updates\n- **Metrics**: per-operation latency breakdown\n\n### 3. Agent Selection (`agent-selection`)\nTests performance-based agent selection.\n- **Target**: p95 \u003C 1ms\n- **Iterations**: 1000\n- **Metrics**: selection confidence, agent scores\n\n### 4. Model Cache (`cache`)\nTests model caching performance.\n- **Target**: p95 \u003C 0.5ms\n- **Metrics**: hit rate, cache size, eviction stats\n\n### 5. Concurrent Workers (`concurrent`)\nTests parallel worker creation and updates.\n- **Target**: \u003C 1000ms for 10 workers\n- **Metrics**: per-worker latency, memory usage\n\n### 6. Memory Key Generation (`memory-keys`)\nTests memory pattern key generation.\n- **Target**: p95 \u003C 0.1ms\n- **Iterations**: 5000\n- **Metrics**: unique patterns, throughput\n\n## Output Format\n\n```\n═══════════════════════════════════════════════════════════\n📈 BENCHMARK RESULTS\n═══════════════════════════════════════════════════════════\n\n✅ Trigger Detection\n   Operation: detect\n   Count: 1,000\n   Avg: 0.045ms | p95: 0.120ms (target: 5ms)\n   Throughput: 22,222 ops$s\n   Memory Δ: 0.12MB\n\n✅ Worker Registry\n   Operation: crud\n   Count: 1,500\n   Avg: 1.234ms | p95: 3.456ms (target: 10ms)\n   Throughput: 810 ops$s\n   Memory Δ: 2.34MB\n\n───────────────────────────────────────────────────────────\n📊 SUMMARY\n───────────────────────────────────────────────────────────\nTotal Tests: 6\nPassed: 6 | Failed: 0\nAvg Latency: 0.567ms\nTotal Duration: 2345ms\nPeak Memory: 8.90MB\n═══════════════════════════════════════════════════════════\n```\n\n## Integration with Settings\n\nBenchmark thresholds are configured in `.claude$settings.json`:\n\n```json\n{\n  \"performance\": {\n    \"benchmarkThresholds\": {\n      \"triggerDetection\": { \"p95Ms\": 5 },\n      \"workerRegistry\": { \"p95Ms\": 10 },\n      \"agentSelection\": { \"p95Ms\": 1 },\n      \"memoryKeyGeneration\": { \"p95Ms\": 0.1 },\n      \"concurrentWorkers\": { \"totalMs\": 1000 }\n    }\n  }\n}\n```\n\n## Programmatic Usage\n\n```typescript\nimport { workerBenchmarks, runBenchmarks } from 'agentic-flow$workers$worker-benchmarks';\n\n\u002F\u002F Run full suite\nconst suite = await runBenchmarks();\nconsole.log(suite.summary);\n\n\u002F\u002F Run individual benchmarks\nconst triggerResult = await workerBenchmarks.benchmarkTriggerDetection(1000);\nconst registryResult = await workerBenchmarks.benchmarkRegistryOperations(500);\n```\n\n## Performance Optimization Tips\n\n1. **Model Cache**: Enable with `CLAUDE_FLOW_MODEL_CACHE_MB=512`\n2. **Parallel Workers**: Enable with `CLAUDE_FLOW_WORKER_PARALLEL=true`\n3. **Warning Suppression**: Enable with `CLAUDE_FLOW_SUPPRESS_WARNINGS=true`\n4. **SQLite WAL Mode**: Automatic for better concurrent performance\n\n\n## 🛠️ PHÁC ĐỒ VẬN HÀNH (OPERATIONAL PROTOCOL)\n### 🔍 Phase 1: Investigation (Thẩm định)\n- Xác minh tham số đầu vào dựa trên Schema.\n- Kiểm tra bối cảnh hệ thống liên quan.\n\n### 🚀 Phase 2: Action (Thực thi)\n- Triệu hồi logic thực thi trong `logic.py`.\n- Trả về kết quả và chắt lọc kinh nghiệm.\n\n---\n## ⚠️ SAI LẦM THƯỜNG GẶP (COMMON PITFALLS)\n- Chưa ghi nhận.\n\n---\n*TRUNG THÀNH - CHÍNH XÁC - TỐI THƯỢNG* 💎🦾\n","# worker-benchmarks (worker-benchmarks)\n\n## 🌟 TỔNG QUAN\n---\nname: worker-benchmarks\ndescription: Run comprehensive worker system benchmarks and performance analysis\nversion: 1.0.0\ninvocable: true\nauthor: agentic-flow\ncapabilities:\n  - performance_testing\n  - metrics_collection\n  - optimization_recommendations\n---\n\n# Worker Benchmarks Skill\n\nRun comprehensive performance benchmarks for the agentic-flow worker system.\n\n## Quick Start\n\n```bash\n# Run full benchmark suite\nnpx agentic-flow workers benchmark\n\n# Run specific benchmark\nnpx agentic-flow workers benchmark --type trigger-detection\nnpx agentic-flow workers benchmark --type registry\nnpx agentic-flow workers benchmark --type agent-selection\nnpx agentic-flow workers benchmark --type concurrent\n```\n\n## Benchmark Types\n\n### 1. Trigger Detection (`trigger-detection`)\nTests keyword detection speed across 12 worker triggers.\n- **Target**: p95 \u003C 5ms\n- **Iterations**: 1000\n- **Metrics**: latency, throughput, histogram\n\n### 2. Worker Registry (`registry`)\nTests CRUD operations on worker entries.\n- **Target**: p95 \u003C 10ms\n- **Iterations**: 500 creates, gets, updates\n- **Metrics**: per-operation latency breakdown\n\n### 3. Agent Selection (`agent-selection`)\nTests performance-based agent selection.\n- **Target**: p95 \u003C 1ms\n- **Iterations**: 1000\n- **Metrics**: selection confidence, agent scores\n\n### 4. Model Cache (`cache`)\nTests model caching performance.\n- **Target**: p95 \u003C 0.5ms\n- **Metrics**: hit rate, cache size, eviction stats\n\n### 5. Concurrent Workers (`concurrent`)\nTests parallel worker creation and updates.\n- **Target**: \u003C 1000ms for 10 workers\n- **Metrics**: per-worker latency, memory usage\n\n### 6. Memory Key Generation (`memory-keys`)\nTests memory pattern key generation.\n- **Target**: p95 \u003C 0.1ms\n- **Iterations**: 5000\n- **Metrics**: unique patterns, throughput\n\n## Output Format\n\n```\n═══════════════════════════════════════════════════════════\n📈 BENCHMARK RESULTS\n═══════════════════════════════════════════════════════════\n\n✅ Trigger Detection\n   Operation: detect\n   Count: 1,000\n   Avg: 0.045ms | p95: 0.120ms (target: 5ms)\n   Throughput: 22,222 ops$s\n   Memory Δ: 0.12MB\n\n✅ Worker Registry\n   Operation: crud\n   Count: 1,500\n   Avg: 1.234ms | p95: 3.456ms (target: 10ms)\n   Throughput: 810 ops$s\n   Memory Δ: 2.34MB\n\n───────────────────────────────────────────────────────────\n📊 SUMMARY\n───────────────────────────────────────────────────────────\nTotal Tests: 6\nPassed: 6 | Failed: 0\nAvg Latency: 0.567ms\nTotal Duration: 2345ms\nPeak Memory: 8.90MB\n═══════════════════════════════════════════════════════════\n```\n\n## Integration with Settings\n\nBenchmark thresholds are configured in `.claude$settings.json`:\n\n```json\n{\n  \"performance\": {\n    \"benchmarkThresholds\": {\n      \"triggerDetection\": { \"p95Ms\": 5 },\n      \"workerRegistry\": { \"p95Ms\": 10 },\n      \"agentSelection\": { \"p95Ms\": 1 },\n      \"memoryKeyGeneration\": { \"p95Ms\": 0.1 },\n      \"concurrentWorkers\": { \"totalMs\": 1000 }\n    }\n  }\n}\n```\n\n## Programmatic Usage\n\n```typescript\nimport { workerBenchmarks, runBenchmarks } from 'agentic-flow$workers$worker-benchmarks';\n\n\u002F\u002F Run full suite\nconst suite = await runBenchmarks();\nconsole.log(suite.summary);\n\n\u002F\u002F Run individual benchmarks\nconst triggerResult = await workerBenchmarks.benchmarkTriggerDetection(1000);\nconst registryResult = await workerBenchmarks.benchmarkRegistryOperations(500);\n```\n\n## Performance Optimization Tips\n\n1. **Model Cache**: Enable with `CLAUDE_FLOW_MODEL_CACHE_MB=512`\n2. **Parallel Workers**: Enable with `CLAUDE_FLOW_WORKER_PARALLEL=true`\n3. **Warning Suppression**: Enable with `CLAUDE_FLOW_SUPPRESS_WARNINGS=true`\n4. **SQLite WAL Mode**: Automatic for better concurrent performance\n\n\n## 🛠️ PHÁC ĐỒ VẬN HÀNH (OPERATIONAL PROTOCOL)\n### 🔍 Phase 1: Investigation (Thẩm định)\n- Xác minh tham số đầu vào dựa trên Schema.\n- Kiểm tra bối cảnh hệ thống liên quan.\n\n### 🚀 Phase 2: Action (Thực thi)\n- Triệu hồi logic thực thi trong `logic.py`.\n- Trả về kết quả và chắt lọc kinh nghiệm.\n\n---\n## ⚠️ SAI LẦM THƯỜNG GẶP (COMMON PITFALLS)\n- Chưa ghi nhận.\n\n---\n*TRUNG THÀNH - CHÍNH XÁC - TỐI THƯỢNG* 💎🦾\n",{"id":5,"author":22,"domain":23,"schema":24,"name_vn":5,"version":25,"priority":26,"aliases_vn":27,"intent_pairs":28,"related_skills":29},"Zenith Legacy","UNKNOWN",{},"1.0.0","NORMAL",[],[],[],"main","571327a911ec45873180fd5628525b6d4504ed79","intelligence\u002Fskills\u002FCORE\u002Fworker-benchmarks","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith","https:\u002F\u002Fgithub.com\u002Fngdletrung","2026-11-08 11:23:33",{"source":7,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add ngdletrung\u002FJKAI-Zenith --skill worker-benchmarks",{"tool":42,"command":43},"bunx","bunx skills add ngdletrung\u002FJKAI-Zenith --skill worker-benchmarks",{"tool":45,"command":46},"pnpm","pnpm dlx skills add ngdletrung\u002FJKAI-Zenith --skill worker-benchmarks","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FCORE\u002Fworker-benchmarks\u002FSKILL.md",true,[50,56,62,66],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"__init__.py","SCRIPT","脚本",66,"https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FCORE\u002Fworker-benchmarks\u002F__init__.py",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"dossier.md","REFERENCE","参考文档",2212,"https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FCORE\u002Fworker-benchmarks\u002Fdossier.md",{"path":63,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":64,"sourceHtmlUrl":65},"logic.py",401,"https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FCORE\u002Fworker-benchmarks\u002Flogic.py",{"path":67,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":68,"sourceHtmlUrl":69},"manifest.json",1051,"https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FCORE\u002Fworker-benchmarks\u002Fmanifest.json",[71,78,84,91,97,103],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":17},"01M73C2NC1W5P3A0V3GQAJ0SJB","standard_plugin","Hướng dẫn kích hoạt và vận hành cho kỹ năng standard_plugin.","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002Ftemplates\u002Fstandard_plugin\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":17},"01M73C2KAN3Q7D5XEBKB3KZW1B","_STANDARD","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002F_STANDARD\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":17},"01M73C2HV7KDJQTA6ACCR10HZB","test_dynamic_audit","Thao tác kiểm toán động","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FTEST\u002Ftest_dynamic_audit\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":17},"01M73C2FRG0JHZ6W155V1KCHRP","security-audit","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FSECURITY\u002Fsecurity-audit\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":17},"01M73C2EMWYHFTAR9RSZ41TBGP","security-and-hardening","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FSECURITY\u002Fsecurity-and-hardening\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":17},"01M73C2CV0BQ59NAEWXKBQ370Z","performance-optimization","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FSECURITY\u002Fperformance-optimization\u002FSKILL.md",[],[]]