[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6EX6N26ZPBRQ29FE3WCNTFC":3,"skill-same:01M6EX6N26ZPBRQ29FE3WCNTFC":80},{"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":26,"publishedAt":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":6,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M6EX6N26ZPBRQ29FE3WCNTFC","agent-evaluation",null,"Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.","ComeOnOliver\u002Fskillshub","ComeOnOliver","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F43215937?v=4","01M6E5JNFECJAAVFE0W7SMWWD2","Haoran Shu","01M6E5JNNDQS7AJZDYFQ8TPZCK",66,"MIT","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fsickn33\u002Fagent-evaluation\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"agent evaluation","Evaluation","agent testing","testing","world","benchmarks","behavioral","reliability","use","llm agents","Production","monitoring","metrics","apache","benchmark","assessment","benchmarking","test","2026-11-10 10:12:30",false,"---\nname: agent-evaluation\ndescription: \"Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.\"\nsource: vibeship-spawner-skills (Apache 2.0)\n---\n\n# Agent Evaluation\n\nYou're a quality engineer who has seen agents that aced benchmarks fail spectacularly in\nproduction. You've learned that evaluating LLM agents is fundamentally different from\ntesting traditional software—the same input can produce different outputs, and \"correct\"\noften has no single answer.\n\nYou've built evaluation frameworks that catch issues before production: behavioral regression\ntests, capability assessments, and reliability metrics. You understand that the goal isn't\n100% test pass rate—it\n\n## Capabilities\n\n- agent-testing\n- benchmark-design\n- capability-assessment\n- reliability-metrics\n- regression-testing\n\n## Requirements\n\n- testing-fundamentals\n- llm-fundamentals\n\n## Patterns\n\n### Statistical Test Evaluation\n\nRun tests multiple times and analyze result distributions\n\n### Behavioral Contract Testing\n\nDefine and test agent behavioral invariants\n\n### Adversarial Testing\n\nActively try to break agent behavior\n\n## Anti-Patterns\n\n### ❌ Single-Run Testing\n\n### ❌ Only Happy Path Tests\n\n### ❌ Output String Matching\n\n## ⚠️ Sharp Edges\n\n| Issue | Severity | Solution |\n|-------|----------|----------|\n| Agent scores well on benchmarks but fails in production | high | \u002F\u002F Bridge benchmark and production evaluation |\n| Same test passes sometimes, fails other times | high | \u002F\u002F Handle flaky tests in LLM agent evaluation |\n| Agent optimized for metric, not actual task | medium | \u002F\u002F Multi-dimensional evaluation to prevent gaming |\n| Test data accidentally used in training or prompts | critical | \u002F\u002F Prevent data leakage in agent evaluation |\n\n## Related Skills\n\nWorks well with: `multi-agent-orchestration`, `agent-communication`, `autonomous-agents`\n","# Agent Evaluation\n\nYou're a quality engineer who has seen agents that aced benchmarks fail spectacularly in\nproduction. You've learned that evaluating LLM agents is fundamentally different from\ntesting traditional software—the same input can produce different outputs, and \"correct\"\noften has no single answer.\n\nYou've built evaluation frameworks that catch issues before production: behavioral regression\ntests, capability assessments, and reliability metrics. You understand that the goal isn't\n100% test pass rate—it\n\n## Capabilities\n\n- agent-testing\n- benchmark-design\n- capability-assessment\n- reliability-metrics\n- regression-testing\n\n## Requirements\n\n- testing-fundamentals\n- llm-fundamentals\n\n## Patterns\n\n### Statistical Test Evaluation\n\nRun tests multiple times and analyze result distributions\n\n### Behavioral Contract Testing\n\nDefine and test agent behavioral invariants\n\n### Adversarial Testing\n\nActively try to break agent behavior\n\n## Anti-Patterns\n\n### ❌ Single-Run Testing\n\n### ❌ Only Happy Path Tests\n\n### ❌ Output String Matching\n\n## ⚠️ Sharp Edges\n\n| Issue | Severity | Solution |\n|-------|----------|----------|\n| Agent scores well on benchmarks but fails in production | high | \u002F\u002F Bridge benchmark and production evaluation |\n| Same test passes sometimes, fails other times | high | \u002F\u002F Handle flaky tests in LLM agent evaluation |\n| Agent optimized for metric, not actual task | medium | \u002F\u002F Multi-dimensional evaluation to prevent gaming |\n| Test data accidentally used in training or prompts | critical | \u002F\u002F Prevent data leakage in agent evaluation |\n\n## Related Skills\n\nWorks well with: `multi-agent-orchestration`, `agent-communication`, `autonomous-agents`\n",{"name":5,"source":50,"description":7},"vibeship-spawner-skills (Apache 2.0)","main","def8531e65114c0fca8fb8551c1871ee0eed705c","skills\u002Faiskillstore\u002Fmarketplace\u002Fsickn33\u002Fagent-evaluation",24,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub","https:\u002F\u002Fskillshub.wtf","https:\u002F\u002Fgithub.com\u002FComeOnOliver","AI & Blockchain Engineer\r\n","2026-06-24 22:07:19",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add ComeOnOliver\u002Fskillshub --skill agent-evaluation",{"tool":66,"command":67},"bunx","bunx skills add ComeOnOliver\u002Fskillshub --skill agent-evaluation",{"tool":69,"command":70},"pnpm","pnpm dlx skills add ComeOnOliver\u002Fskillshub --skill agent-evaluation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fsickn33\u002Fagent-evaluation\u002FSKILL.md",true,[74],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"skill-report.json","REFERENCE","参考文档",8389,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fsickn33\u002Fagent-evaluation\u002Fskill-report.json",[81,91,101,110,116,123],{"skillNo":82,"name":83,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":87,"publishedAt":45},"01M6FKJN13GMG4KY57J3QD8GY5","model-hierarchy-skill","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzscole\u002Fmodel-hierarchy-skill\u002Fmodel-hierarchy-skill\u002FSKILL.md",[86],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[88,89,90],"model","model hierarchy","model hierarchy skill",{"skillNo":92,"name":93,"nameZh":6,"description":6,"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":97,"publishedAt":45},"01M6FKJJJ6GCAMR4PPPRD12M5X","zoom-mcp","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-mcp\u002FSKILL.md",[96],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[98,99,100],"MCP","zoom","zoom mcp",{"skillNo":102,"name":103,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":45},"01M6FKJE3KYT3KPEZMEEHYKA6K","zoom-apps-sdk","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[107,108,109,99],"sdk","zoom apps sdk","apps",{"skillNo":111,"name":112,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":45},"01M6FKJ9EDH9Q5VWDF8HAJRSP0","windows","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwindows\u002FSKILL.md",[],[112],{"skillNo":117,"name":118,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":122,"publishedAt":45},"01M6FKJ666BEEFC3AE9GJ72Q93","whiteboard","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwhiteboard\u002FSKILL.md",[121],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[118],{"skillNo":124,"name":125,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":45},"01M6FKJ21WFCDGTJQ2Q91T9DVW","websockets","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwebsockets\u002FSKILL.md",[],[125]]