[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6G3TYMQEWKH66WDMN3AQ1JS":3,"skill-same:01M6G3TYMQEWKH66WDMN3AQ1JS":69},{"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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":14,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6G3TYMQEWKH66WDMN3AQ1JS","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 re...","reikiplanet\u002Fdaoskills","reikiplanet","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F96377599?v=4","01M6CVWCMD740YHQDK7E9QYBW4","Reiki Planet","01M6CVWCS4KXVA2CWFVJ43EAXK",0,"MIT","https:\u002F\u002Fgithub.com\u002Freikiplanet\u002Fdaoskills\u002Fblob\u002Fmaster\u002Fskills\u002Fother\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],"agent evaluation","Evaluation","testing","benchmarking","assessment","apache","metrics","monitoring","Production","llm agents","reliability","behavioral","re","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\\u2014where even top agents achieve less than 50% on re...\"\nsource: vibeship-spawner-skills (Apache 2.0)\nrisk: unknown\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\n## When to Use\nThis skill is applicable to execute the workflow or actions described in the overview.\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\n## When to Use\nThis skill is applicable to execute the workflow or actions described in the overview.\n",{"name":5,"risk":45,"source":46,"description":7},"unknown","vibeship-spawner-skills (Apache 2.0)","master","dff58085da947e81e8418c922055644bf0082b1b","skills\u002Fother\u002Fagent-evaluation","https:\u002F\u002Fgithub.com\u002Freikiplanet\u002Fdaoskills","https:\u002F\u002Fgithub.com\u002Freikiplanet","https:\u002F\u002Fwww.reiki-planet.com","Reiki Planet Game","2026-03-29 06:02:29",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add reikiplanet\u002Fdaoskills --skill agent-evaluation",{"tool":61,"command":62},"bunx","bunx skills add reikiplanet\u002Fdaoskills --skill agent-evaluation",{"tool":64,"command":65},"pnpm","pnpm dlx skills add reikiplanet\u002Fdaoskills --skill agent-evaluation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Freikiplanet\u002Fdaoskills\u002Fblob\u002Fmaster\u002Fskills\u002Fother\u002Fagent-evaluation\u002FSKILL.md",true,[],[70,97,109,124,143,166],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":40},"01M6G614JTEQJHPT8AKK3YQ18S","web-games","Web browser game development principles. Framework selection, WebGPU, optimization, PWA.","https:\u002F\u002Fgithub.com\u002Freikiplanet\u002Fdaoskills\u002Fblob\u002Fmaster\u002Fweb-games\u002FSKILL.md",[],[77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96],"games","web games","web","grep","principles","selection","community","framework selection","edit","write","read","pwa","game","web browser","game development","Optimization","framework","browser","development","webgpu",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":40},"01M6G611H2YGV0GZFP90D38ZMJ","vr-ar","VR\u002FAR development principles. Comfort, interaction, performance requirements.","https:\u002F\u002Fgithub.com\u002Freikiplanet\u002Fdaoskills\u002Fblob\u002Fmaster\u002Fvr-ar\u002FSKILL.md",[],[104,105,95,106,107,83,85,86,87,80,108,81],"ar","vr ar","interaction","requirements","performance",{"skillNo":110,"name":111,"nameZh":6,"description":112,"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":40},"01M6G60XNMHAMV1SV0EJ1CX0AY","templates","Project scaffolding templates for new applications. Use when creating new projects from scratch. Contains 12 templates for various tech stacks.","https:\u002F\u002Fgithub.com\u002Freikiplanet\u002Fdaoskills\u002Fblob\u002Fmaster\u002Ftemplates\u002FSKILL.md",[],[111,116,117,118,119,120,83,121,87,122,123,80],"project scaffolding","From Scratch","tech","project","scaffolding","use","projects","applications",{"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":130,"publishedAt":40},"01M6G60T0GATMK3Q5H8GDC1Z8S","wcag-audit-patterns","Conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance. Use when auditing websites for accessibility, fixing WCAG violations, or implementing ac...","https:\u002F\u002Fgithub.com\u002Freikiplanet\u002Fdaoskills\u002Fblob\u002Fmaster\u002Fskills\u002Fsecurity\u002Fwcag-audit-patterns\u002FSKILL.md",[],[131,132,133,134,135,83,136,137,138,139,121,140,141,142,29],"wcag audit patterns","wcag audit","patterns","WCAG","audit","manual","with","automated testing","guidance","remediation","verification","accessibility",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":40},"01M6G60PMCHW1FRZ63F931QK3R","vulnerability-scanner","Advanced vulnerability analysis principles. OWASP 2025, Supply Chain Security, attack surface mapping, risk prioritization.","https:\u002F\u002Fgithub.com\u002Freikiplanet\u002Fdaoskills\u002Fblob\u002Fmaster\u002Fskills\u002Fsecurity\u002Fvulnerability-scanner\u002FSKILL.md",[],[150,151,152,153,154,155,156,157,83,87,80,158,81,159,160,161,162,163,164,165],"scanner","vulnerability scanner","vulnerability","prioritization","2025","mapping","chain","supply chain","Bash","analysis","risk","owasp","supply chain security","security","supply","advanced",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":172,"publishedAt":40},"01M6G60JZBB8DK0W3DSG1WNMZK","threat-modeling-expert","Expert in threat modeling methodologies, security architecture review, and risk assessment. Masters STRIDE, PASTA, attack trees, and security requirement extraction. Use for security architecture r...","https:\u002F\u002Fgithub.com\u002Freikiplanet\u002Fdaoskills\u002Fblob\u002Fmaster\u002Fskills\u002Fsecurity\u002Fthreat-modeling-expert\u002FSKILL.md",[],[173,174,175,176,177,178,179,180,163,121,181,182,183,83,184,31,185,160,186,187],"modeling","threat modeling expert","threat modeling","expert","threat","risk assessment","architecture review","architecture","security architecture review","trees","security architecture","security requirement extraction","extraction","review","stride"]