[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HADM4EK3BX4WT2AX48B7E":3,"skill-same:01M71HADM4EK3BX4WT2AX48B7E":191},{"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":112,"commitSha":113,"skillDirectory":114,"forksCount":115,"repositoryHtmlUrl":116,"repositoryHomepageUrl":6,"ownerHtmlUrl":117,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":118,"install":119,"resources":132},"01M71HADM4EK3BX4WT2AX48B7E","skills-eval",null,"Evaluate and improve Claude skill quality through auditing. Use when reviewing skill quality, preparing skills for production, or auditing existing skills. Do not use when creating new skills (use modular-skills) or writing prose (use writing-clearly-and-concisely). Use this skill before shipping any skill to production.","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__athola--skills-eval\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量","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],"skills eval","eval","when","workflows","writing","token-optimization","new","quality-assessment","design","assessment","improve","skill-management","testing","programmatic","checker","inventory","performance","advanced","concisely","modules","2026-11-10 10:12:30",false,"---\nname: skills-eval\ndescription: Evaluate and improve Claude skill quality through auditing. Use when\n  reviewing skill quality, preparing skills for production, or auditing existing skills.\n  Do not use when creating new skills (use modular-skills) or writing prose (use writing-clearly-and-concisely).\n  Use this skill before shipping any skill to production.\ncategory: skill-management\ntags:\n- evaluation\n- improvement\n- skills\n- optimization\n- quality-assurance\n- tool-use\n- performance-metrics\ndependencies:\n- modular-skills\n- performance-optimization\ntools:\n- skills-auditor\n- improvement-suggester\n- compliance-checker\n- tool-performance-analyzer\n- token-usage-tracker\nprovides:\n  infrastructure:\n  - evaluation-framework\n  - quality-assurance\n  - improvement-planning\n  patterns:\n  - skill-analysis\n  - token-optimization\n  - modular-design\n  sdk_features:\n  - agent-sdk-compatibility\n  - advanced-metrics\n  - dynamic-discovery\nestimated_tokens: 1800\nusage_patterns:\n- skill-audit\n- quality-assessment\n- improvement-planning\n- skills-inventory\n- tool-performance-evaluation\n- dynamic-discovery-optimization\n- advanced-tool-use-analysis\n- programmatic-calling-efficiency\n- context-preservation-quality\n- token-efficiency-optimization\n- modular-architecture-validation\n- integration-testing\n- compliance-reporting\n- performance-benchmarking\ncomplexity: advanced\nevaluation_criteria:\n  structure_compliance: 25\n  metadata_quality: 20\n  token_efficiency: 25\n  tool_integration: 20\n  claude_sdk_compliance: 10\nmodules:\n- modules\u002Fadvanced-tool-use-analysis.md\n- modules\u002Fauthoring-checklist.md\n- modules\u002Fevaluation-criteria.md\n- modules\u002Fevaluation-framework.md\n- modules\u002Fevaluation-workflows.md\n- modules\u002Fintegration-testing.md\n- modules\u002Fintegration.md\n- modules\u002Fmulti-metric-evaluation-methodology.md\n- modules\u002Fperformance-benchmarking.md\n- modules\u002Fpressure-testing.md\n- modules\u002Fquality-metrics.md\n- modules\u002Fskill-authoring-best-practices.md\n- modules\u002Ftrigger-isolation-analysis.md\n- modules\u002Ftroubleshooting.md\n---\n# Skills Evaluation and Improvement\n\n## Table of Contents\n\n1. [Overview](#overview)\n2. [Quick Start](#quick-start)\n3. [Evaluation Workflow](#evaluation-workflow)\n4. [Evaluation and Optimization](#evaluation-and-optimization)\n5. [Resources](#resources)\n\n## Overview\n\nThis framework audits Claude skills against quality standards to improve performance and reduce token consumption. Automated tools analyze skill structure, measure context usage, and identify specific technical improvements. Run verification commands after each audit to confirm fixes work correctly.\n\nThe `skills-auditor` provides structural analysis, while the `improvement-suggester` ranks fixes by impact. Compliance is verified through the `compliance-checker`. Runtime efficiency is monitored by `tool-performance-analyzer` and `token-usage-tracker`.\n\n## Quick Start\n\n### Basic Audit\nRun a full audit of all skills or target a specific file to identify structural issues.\n```bash\n# Audit all skills\nmake audit-all\n\n# Audit specific skill\nmake audit-skill TARGET=path\u002Fto\u002Fskill\u002FSKILL.md\n```\n\n### Analysis and Optimization\nUse `skill_analyzer.py` for complexity checks and `token_estimator.py` to verify the context budget.\n```bash\nmake analyze-skill TARGET=path\u002Fto\u002Fskill\u002FSKILL.md\nmake estimate-tokens TARGET=path\u002Fto\u002Fskill\u002FSKILL.md\n```\n\n### Improvements\nGenerate a prioritized plan and verify standards compliance using `improvement_suggester.py` and `compliance_checker.py`.\n```bash\nmake improve-skill TARGET=path\u002Fto\u002Fskill\u002FSKILL.md\nmake check-compliance TARGET=path\u002Fto\u002Fskill\u002FSKILL.md\n```\n\n## Evaluation Workflow\n\nStart with `make audit-all` to inventory skills and identify high-priority targets. For each skill requiring attention, run analysis with `analyze-skill` to map complexity. Generate an improvement plan, apply fixes, and run `check-compliance` to verify the skill meets project standards. Finalize by checking the token budget for efficiency.\n\n## Evaluation and Optimization\n\nQuality assessments use the `skills-auditor` and `improvement-suggester` to generate detailed reports. Performance analysis focuses on token efficiency through the `token-usage-tracker` and tool performance via `tool-performance-analyzer`. For standards compliance, the `compliance-checker` automates common fixes for structural issues.\n\n### Scoring and Prioritization\n\nWe evaluate skills across five dimensions: structure compliance, content quality, token efficiency, activation reliability, and tool integration. Scores above 90 represent production-ready skills, while scores below 50 indicate critical issues requiring immediate attention.\n\nImprovements are prioritized by impact. Critical issues include security vulnerabilities or broken functionality. High-priority items cover structural flaws that hinder discoverability. Medium and low priorities focus on best practices and minor optimizations.\n\n### Structural Patterns\n\n**Deprecated**: `skills\u002Fshared\u002Fmodules\u002F` directories. Shared modules must be relocated into the consuming skill's own `modules\u002F` directory. The evaluator flags any remaining `skills\u002Fshared\u002F` as a structural warning.\n\n**Current**: Each skill owns its modules at `skills\u002F\u003Cskill-name>\u002Fmodules\u002F`. Cross-skill references use relative paths (e.g., `..\u002Fskill-authoring\u002Fmodules\u002Fanti-rationalization.md`).\n\n## Resources\n\n### Shared Modules: Cross-Skill Patterns\n- **Anti-Rationalization Patterns**: See [anti-rationalization.md](..\u002Fskill-authoring\u002Fmodules\u002Fanti-rationalization.md)\n- **Enforcement Language**: See [enforcement-language.md](..\u002Fshared-patterns\u002Fmodules\u002Fworkflow-patterns.md)\n- **Trigger Patterns**: See [trigger-patterns.md](modules\u002Fevaluation-criteria.md)\n\n### Skill-Specific Modules\n- **Trigger Isolation Analysis**: See `modules\u002Ftrigger-isolation-analysis.md`\n- **Skill Authoring Best Practices**: See `modules\u002Fskill-authoring-best-practices.md`\n- **Authoring Checklist**: See `modules\u002Fauthoring-checklist.md`\n- **Evaluation Workflows**: See `modules\u002Fevaluation-workflows.md`\n- **Quality Metrics**: See `modules\u002Fquality-metrics.md`\n- **Advanced Tool Use Analysis**: See `modules\u002Fadvanced-tool-use-analysis.md`\n- **Evaluation Framework**: See `modules\u002Fevaluation-framework.md`\n- **Integration Patterns**: See `modules\u002Fintegration.md`\n- **Troubleshooting**: See `modules\u002Ftroubleshooting.md`\n- **Pressure Testing**: See `modules\u002Fpressure-testing.md`\n- **Integration Testing**: See `modules\u002Fintegration-testing.md`\n- **Multi-Metric Evaluation**: See `modules\u002Fmulti-metric-evaluation-methodology.md`\n- **Performance Benchmarking**: See `modules\u002Fperformance-benchmarking.md`\n\n### Tools and Automation\n- **Tools**: Executable analysis utilities in `scripts\u002F` directory.\n- **Automation**: Setup and validation scripts in `scripts\u002Fautomation\u002F`.\n","# Skills Evaluation and Improvement\n\n## Table of Contents\n\n1. [Overview](#overview)\n2. [Quick Start](#quick-start)\n3. [Evaluation Workflow](#evaluation-workflow)\n4. [Evaluation and Optimization](#evaluation-and-optimization)\n5. [Resources](#resources)\n\n## Overview\n\nThis framework audits Claude skills against quality standards to improve performance and reduce token consumption. Automated tools analyze skill structure, measure context usage, and identify specific technical improvements. Run verification commands after each audit to confirm fixes work correctly.\n\nThe `skills-auditor` provides structural analysis, while the `improvement-suggester` ranks fixes by impact. Compliance is verified through the `compliance-checker`. Runtime efficiency is monitored by `tool-performance-analyzer` and `token-usage-tracker`.\n\n## Quick Start\n\n### Basic Audit\nRun a full audit of all skills or target a specific file to identify structural issues.\n```bash\n# Audit all skills\nmake audit-all\n\n# Audit specific skill\nmake audit-skill TARGET=path\u002Fto\u002Fskill\u002FSKILL.md\n```\n\n### Analysis and Optimization\nUse `skill_analyzer.py` for complexity checks and `token_estimator.py` to verify the context budget.\n```bash\nmake analyze-skill TARGET=path\u002Fto\u002Fskill\u002FSKILL.md\nmake estimate-tokens TARGET=path\u002Fto\u002Fskill\u002FSKILL.md\n```\n\n### Improvements\nGenerate a prioritized plan and verify standards compliance using `improvement_suggester.py` and `compliance_checker.py`.\n```bash\nmake improve-skill TARGET=path\u002Fto\u002Fskill\u002FSKILL.md\nmake check-compliance TARGET=path\u002Fto\u002Fskill\u002FSKILL.md\n```\n\n## Evaluation Workflow\n\nStart with `make audit-all` to inventory skills and identify high-priority targets. For each skill requiring attention, run analysis with `analyze-skill` to map complexity. Generate an improvement plan, apply fixes, and run `check-compliance` to verify the skill meets project standards. Finalize by checking the token budget for efficiency.\n\n## Evaluation and Optimization\n\nQuality assessments use the `skills-auditor` and `improvement-suggester` to generate detailed reports. Performance analysis focuses on token efficiency through the `token-usage-tracker` and tool performance via `tool-performance-analyzer`. For standards compliance, the `compliance-checker` automates common fixes for structural issues.\n\n### Scoring and Prioritization\n\nWe evaluate skills across five dimensions: structure compliance, content quality, token efficiency, activation reliability, and tool integration. Scores above 90 represent production-ready skills, while scores below 50 indicate critical issues requiring immediate attention.\n\nImprovements are prioritized by impact. Critical issues include security vulnerabilities or broken functionality. High-priority items cover structural flaws that hinder discoverability. Medium and low priorities focus on best practices and minor optimizations.\n\n### Structural Patterns\n\n**Deprecated**: `skills\u002Fshared\u002Fmodules\u002F` directories. Shared modules must be relocated into the consuming skill's own `modules\u002F` directory. The evaluator flags any remaining `skills\u002Fshared\u002F` as a structural warning.\n\n**Current**: Each skill owns its modules at `skills\u002F\u003Cskill-name>\u002Fmodules\u002F`. Cross-skill references use relative paths (e.g., `..\u002Fskill-authoring\u002Fmodules\u002Fanti-rationalization.md`).\n\n## Resources\n\n### Shared Modules: Cross-Skill Patterns\n- **Anti-Rationalization Patterns**: See [anti-rationalization.md](..\u002Fskill-authoring\u002Fmodules\u002Fanti-rationalization.md)\n- **Enforcement Language**: See [enforcement-language.md](..\u002Fshared-patterns\u002Fmodules\u002Fworkflow-patterns.md)\n- **Trigger Patterns**: See [trigger-patterns.md](modules\u002Fevaluation-criteria.md)\n\n### Skill-Specific Modules\n- **Trigger Isolation Analysis**: See `modules\u002Ftrigger-isolation-analysis.md`\n- **Skill Authoring Best Practices**: See `modules\u002Fskill-authoring-best-practices.md`\n- **Authoring Checklist**: See `modules\u002Fauthoring-checklist.md`\n- **Evaluation Workflows**: See `modules\u002Fevaluation-workflows.md`\n- **Quality Metrics**: See `modules\u002Fquality-metrics.md`\n- **Advanced Tool Use Analysis**: See `modules\u002Fadvanced-tool-use-analysis.md`\n- **Evaluation Framework**: See `modules\u002Fevaluation-framework.md`\n- **Integration Patterns**: See `modules\u002Fintegration.md`\n- **Troubleshooting**: See `modules\u002Ftroubleshooting.md`\n- **Pressure Testing**: See `modules\u002Fpressure-testing.md`\n- **Integration Testing**: See `modules\u002Fintegration-testing.md`\n- **Multi-Metric Evaluation**: See `modules\u002Fmulti-metric-evaluation-methodology.md`\n- **Performance Benchmarking**: See `modules\u002Fperformance-benchmarking.md`\n\n### Tools and Automation\n- **Tools**: Executable analysis utilities in `scripts\u002F` directory.\n- **Automation**: Setup and validation scripts in `scripts\u002Fautomation\u002F`.\n",{"name":5,"tags":51,"tools":59,"modules":65,"category":37,"provides":80,"complexity":43,"description":7,"dependencies":91,"usage_patterns":94,"estimated_tokens":107,"evaluation_criteria":108},[52,53,54,55,56,57,58],"evaluation","improvement","skills","optimization","quality-assurance","tool-use","performance-metrics",[60,61,62,63,64],"skills-auditor","improvement-suggester","compliance-checker","tool-performance-analyzer","token-usage-tracker",[66,67,68,69,70,71,72,73,74,75,76,77,78,79],"modules\u002Fadvanced-tool-use-analysis.md","modules\u002Fauthoring-checklist.md","modules\u002Fevaluation-criteria.md","modules\u002Fevaluation-framework.md","modules\u002Fevaluation-workflows.md","modules\u002Fintegration-testing.md","modules\u002Fintegration.md","modules\u002Fmulti-metric-evaluation-methodology.md","modules\u002Fperformance-benchmarking.md","modules\u002Fpressure-testing.md","modules\u002Fquality-metrics.md","modules\u002Fskill-authoring-best-practices.md","modules\u002Ftrigger-isolation-analysis.md","modules\u002Ftroubleshooting.md",{"patterns":81,"sdk_features":84,"infrastructure":88},[82,31,83],"skill-analysis","modular-design",[85,86,87],"agent-sdk-compatibility","advanced-metrics","dynamic-discovery",[89,56,90],"evaluation-framework","improvement-planning",[92,93],"modular-skills","performance-optimization",[95,33,90,96,97,98,99,100,101,102,103,104,105,106],"skill-audit","skills-inventory","tool-performance-evaluation","dynamic-discovery-optimization","advanced-tool-use-analysis","programmatic-calling-efficiency","context-preservation-quality","token-efficiency-optimization","modular-architecture-validation","integration-testing","compliance-reporting","performance-benchmarking",1800,{"metadata_quality":109,"token_efficiency":110,"tool_integration":109,"structure_compliance":110,"claude_sdk_compliance":111},20,25,10,"main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__athola--skills-eval",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":120,"prompt":130,"zipAvailable":131},[121,124,127],{"tool":122,"command":123},"npx","npx skills add JSGforever\u002Fskillguard --skill skills-eval",{"tool":125,"command":126},"bunx","bunx skills add JSGforever\u002Fskillguard --skill skills-eval",{"tool":128,"command":129},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill skills-eval","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__athola--skills-eval\u002FSKILL.md",true,[133,138,141,144,147,150,153,156,159,162,165,168,171,174,177,181,187],{"path":66,"resourceType":134,"resourceTypeDesc":135,"sizeBytes":136,"sourceHtmlUrl":137},"REFERENCE","参考文档",3361,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__athola--skills-eval\u002Fmodules\u002Fadvanced-tool-use-analysis.md",{"path":67,"resourceType":134,"resourceTypeDesc":135,"sizeBytes":139,"sourceHtmlUrl":140},2041,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__athola--skills-eval\u002Fmodules\u002Fauthoring-checklist.md",{"path":68,"resourceType":134,"resourceTypeDesc":135,"sizeBytes":142,"sourceHtmlUrl":143},12010,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__athola--skills-eval\u002Fmodules\u002Fevaluation-criteria.md",{"path":69,"resourceType":134,"resourceTypeDesc":135,"sizeBytes":145,"sourceHtmlUrl":146},3102,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__athola--skills-eval\u002Fmodules\u002Fevaluation-framework.md",{"path":70,"resourceType":134,"resourceTypeDesc":135,"sizeBytes":148,"sourceHtmlUrl":149},2110,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__athola--skills-eval\u002Fmodules\u002Fevaluation-workflows.md",{"path":71,"resourceType":134,"resourceTypeDesc":135,"sizeBytes":151,"sourceHtmlUrl":152},9919,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__athola--skills-eval\u002Fmodules\u002Fintegration-testing.md",{"path":72,"resourceType":134,"resourceTypeDesc":135,"sizeBytes":154,"sourceHtmlUrl":155},3365,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__athola--skills-eval\u002Fmodules\u002Fintegration.md",{"path":73,"resourceType":134,"resourceTypeDesc":135,"sizeBytes":157,"sourceHtmlUrl":158},1451,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__athola--skills-eval\u002Fmodules\u002Fmulti-metric-evaluation-methodology.md",{"path":74,"resourceType":134,"resourceTypeDesc":135,"sizeBytes":160,"sourceHtmlUrl":161},16313,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__athola--skills-eval\u002Fmodules\u002Fperformance-benchmarking.md",{"path":75,"resourceType":134,"resourceTypeDesc":135,"sizeBytes":163,"sourceHtmlUrl":164},16031,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__athola--skills-eval\u002Fmodules\u002Fpressure-testing.md",{"path":76,"resourceType":134,"resourceTypeDesc":135,"sizeBytes":166,"sourceHtmlUrl":167},5216,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__athola--skills-eval\u002Fmodules\u002Fquality-metrics.md",{"path":77,"resourceType":134,"resourceTypeDesc":135,"sizeBytes":169,"sourceHtmlUrl":170},1566,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__athola--skills-eval\u002Fmodules\u002Fskill-authoring-best-practices.md",{"path":78,"resourceType":134,"resourceTypeDesc":135,"sizeBytes":172,"sourceHtmlUrl":173},5049,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__athola--skills-eval\u002Fmodules\u002Ftrigger-isolation-analysis.md",{"path":79,"resourceType":134,"resourceTypeDesc":135,"sizeBytes":175,"sourceHtmlUrl":176},7669,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__athola--skills-eval\u002Fmodules\u002Ftroubleshooting.md",{"path":178,"resourceType":134,"resourceTypeDesc":135,"sizeBytes":179,"sourceHtmlUrl":180},"README.md",769,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__athola--skills-eval\u002FREADME.md",{"path":182,"resourceType":183,"resourceTypeDesc":184,"sizeBytes":185,"sourceHtmlUrl":186},"scripts\u002Fautomation\u002Fdeploy.sh","SCRIPT","脚本",1730,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__athola--skills-eval\u002Fscripts\u002Fautomation\u002Fdeploy.sh",{"path":188,"resourceType":183,"resourceTypeDesc":184,"sizeBytes":189,"sourceHtmlUrl":190},"scripts\u002FREADME.md",7693,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__athola--skills-eval\u002Fscripts\u002FREADME.md",[192,219,235,261,283,304],{"skillNo":193,"name":194,"nameZh":6,"description":195,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":196,"categories":197,"keywords":199,"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",[198],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[200,201,202,203,204,205,206,207,208,209,210,211,28,212,213,214,215,216,217,218],"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":220,"name":221,"nameZh":6,"description":222,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":223,"licenseFileUrl":6,"sourceHtmlUrl":224,"categories":225,"keywords":231,"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",[226],{"categoryNo":227,"categoryName":228,"taxonomyType":229,"taxonomyTypeDesc":230},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[232,233,234],"data","data exfiltrator","files",{"skillNo":236,"name":237,"nameZh":6,"description":238,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":239,"categories":240,"keywords":241,"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",[],[242,243,244,245,246,247,248,249,250,42,251,252,253,254,255,256,257,258,259,260],"time","real time collaboration engine","real time collaboration","collaboration","engine","real time","Video","reliability","video editing","conflict resolution","presence","access","apps","updates","Bash","activate","optimizer","react","streaming",{"skillNo":262,"name":263,"nameZh":6,"description":264,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":265,"categories":266,"keywords":270,"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",[267],{"categoryNo":268,"categoryName":269,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[42,271,258,259,272,273,274,275,276,277,242,278,279,254,256,280,257,260,281,282],"react performance optimizer","react performance","performance optimizer","app","nextjs","expert","re","render","2025","code","router","strategies",{"skillNo":284,"name":285,"nameZh":6,"description":286,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":287,"categories":288,"keywords":290,"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",[289],{"categoryNo":268,"categoryName":269,"taxonomyType":20,"taxonomyTypeDesc":21},[291,260,292,293,294,295,42,242,296,297,298,256,257,258,299,259,300,301,302,303],"llm streaming response handler","handler","error","processing","retry","chat ui","error recovery","critical","batch","display","text","server","read",{"skillNo":305,"name":306,"nameZh":6,"description":307,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":308,"categories":309,"keywords":315,"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",[310,311,314],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":312,"categoryName":313,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[316,317,318,319,320,321,322,249,276,38,323,29,257,282,324,303,325,326,327,328],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","pipeline","ci","run","release","write","edit","git"]