[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ADK4JHS7RE0REN1FHXGXK1":3,"skill-same:01M6ADK4JHS7RE0REN1FHXGXK1":85},{"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":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":60,"ownerHtmlUrl":61,"ownerBlogUrl":62,"ownerDescription":63,"updatedAt":64,"install":65,"resources":78},"01M6ADK4JHS7RE0REN1FHXGXK1","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.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33481,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\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",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"agent evaluation","Evaluation","llm agents","test agent","when","achieve","capability","spawner","top","world","behavioral","reliability","use","testing","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.\"\nmetadata:\n  source: 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,"metadata":53,"description":7},{"source":54},"vibeship-spawner-skills (Apache 2.0)","main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fagent-evaluation",3931,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-14 06:14:46",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add davila7\u002Fclaude-code-templates --skill agent-evaluation",{"tool":71,"command":72},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill agent-evaluation",{"tool":74,"command":75},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill agent-evaluation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fagent-evaluation\u002FSKILL.md",true,[79],{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"SKILL.md.tmpl","OTHER","其他",45710,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fgstack\u002Fautoplan\u002FSKILL.md.tmpl",[86,112,139,172,207,228],{"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":93,"publishedAt":48},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[92],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[94,95,96,97,98,99,100,101,39,31,102,103,104,105,106,107,108,109,110,111],"scoring","pool","wealthville pool scoring","liquidity","which","for","exit","now","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":119,"publishedAt":48},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[118],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[120,121,122,123,124,125,126,127,128,129,130,31,131,132,133,134,135,136,137,138],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":154,"publishedAt":48},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[145,148,149],{"categoryNo":146,"categoryName":147,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":150,"categoryName":151,"taxonomyType":152,"taxonomyTypeDesc":153},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[155,156,157,158,159,160,161,99,162,163,164,165,166,167,168,39,169,170,31,171],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":176,"licenseFileUrl":177,"sourceHtmlUrl":178,"categories":179,"keywords":183,"publishedAt":48},"01M6AFY6F7CC2BBZP1QD6VTNVC","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[180],{"categoryNo":181,"categoryName":182,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,99,206],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":208,"name":209,"nameZh":6,"description":210,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":176,"licenseFileUrl":211,"sourceHtmlUrl":212,"categories":213,"keywords":216,"publishedAt":48},"01M6AFWF33SFV9Z3SF4PEEE4BF","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[214,215],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":181,"categoryName":182,"taxonomyType":21,"taxonomyTypeDesc":22},[217,40,218,219,220,185,221,194,195,222,223,224,225,99,226,103,227],"webapp testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":229,"name":230,"nameZh":6,"description":231,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":176,"licenseFileUrl":232,"sourceHtmlUrl":233,"categories":234,"keywords":242,"publishedAt":48},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[235,238,239],{"categoryNo":236,"categoryName":237,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":240,"categoryName":241,"taxonomyType":152,"taxonomyTypeDesc":153},"01JBSEEDCAT000000000000036","内容创作者",[243,244,245,246,247,248,249,250,187,251,197,131,252,253,254,255,256,167,257,31,258,259,260,261,262,109,263],"discernment nudge","nudge","interpretation","help","run","reasoning","data","writing","lookup","content","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]