[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71JS22W68TKHXVJTH721PWQ":3,"skill-same:01M71JS22W68TKHXVJTH721PWQ":89},{"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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":65,"commitSha":66,"skillDirectory":67,"forksCount":68,"repositoryHtmlUrl":69,"repositoryHomepageUrl":70,"ownerHtmlUrl":71,"ownerBlogUrl":72,"ownerDescription":73,"updatedAt":74,"install":75,"resources":88},"01M71JS22W68TKHXVJTH721PWQ","agent-self-eval",null,"Post-run self-evaluation system that scores agent output on correctness, clarity, actionability, and conciseness. Use after \u002Fteam runs, skill executions, or when explicitly asked to evaluate output quality.","coco-research\u002Fcoco","coco-research","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F68911604?v=4","01M71JRE9C4NM4NSZM4JD0BJTB","Coco Research","01M71JREA0ZMR0PMH3CKA99SN1",631,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fskills\u002Fagent-self-eval\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"self eval","agent self eval","self","eval","team","clarity","conciseness","system","feedback","Meta","run","use","windsurf","scoring","Evaluation","cline","zed","generic","when","code","2026-11-10 10:12:30",false,"---\nname: agent-self-eval\ndescription: \"Post-run self-evaluation system that scores agent output on correctness, clarity, actionability, and conciseness. Use after \u002Fteam runs, skill executions, or when explicitly asked to evaluate output quality.\"\ndomain: meta\nsupports: [claude-code, cursor, codex, generic, windsurf, zed, cline, roo-code, amazon-q]\nversion: 0.1.0\ntags: [evaluation, quality, scoring, feedback]\n---\n\n@agents\u002FPROMPT-DEFENSE.md\n\n# Agent Self-Evaluation\n\nScore your own output (or another agent's output) across four axes to identify quality gaps and feed improvements into the learning system.\n\n## When to Use\n- After completing a `\u002Fteam:*` pipeline run\n- After generating a deliverable (PRD, architecture doc, code review)\n- When user asks \"how did I do?\" or \"evaluate this output\"\n- Automatically at end of `\u002Fgsd-execute-phase` for quality tracking\n\n## Evaluation Axes\n\n| Axis | Question | Failure Signals |\n|------|----------|-----------------|\n| **Correctness** | Is the output factually accurate and technically sound? | Wrong APIs, broken references, hallucinated facts, logic errors |\n| **Clarity** | Is the explanation understandable and well-structured? | Confusing structure, undefined jargon, missing context, rambling |\n| **Actionability** | Can the user act on the output immediately? | Vague suggestions, missing steps, no verification path |\n| **Conciseness** | Did it use the minimum tokens needed? | Redundancy, over-explanation, filler content, restating the question |\n\n## Scoring Scale\n```\n5 — Exceptional: no reasonable improvement possible\n4 — Good: minor nits only, no substantive gaps\n3 — Adequate: meets request but has notable weakness on ≥1 axis\n2 — Weak: clear gap affecting usability or correctness\n1 — Poor: fundamentally misses request or contains significant errors\n```\n\n## The Evidence Rule\nEvery score below 5 MUST cite specific evidence. A score of 3 cannot just say \"could be better\" — it must say exactly what is missing or wrong. **\"Show the gap, don't just name it.\"**\n\n## Procedure\n\n### Step 1: Collect Raw Material\nGather:\n- Original user request\n- Final output\u002Fdeliverable\n- Tool outputs verifying correctness (test results, exit codes, lint)\n- User feedback received during task (corrections, \"try again\")\n\n### Step 2: Score Each Axis Independently\nRate 1-5 with mandatory evidence for scores \u003C5.\n\n### Step 3: Generate Eval Report\n```\nSELF-EVALUATION REPORT\n======================\nTask: {brief description}\nOverall: {weighted average}\u002F5\n\nCORRECTNESS: {score}\u002F5\n  Evidence: {specific finding or \"No issues found\"}\n\nCLARITY: {score}\u002F5\n  Evidence: {specific finding or \"No issues found\"}\n\nACTIONABILITY: {score}\u002F5\n  Evidence: {specific finding or \"No issues found\"}\n\nCONCISENESS: {score}\u002F5\n  Evidence: {specific finding or \"No issues found\"}\n\nIMPROVEMENT INSTINCTS:\n- {trigger} → {action} (confidence: {0.3-0.9})\n```\n\n### Step 4: Feed Learning System\nIf learning system is active (PR-27+), auto-generate instinct YAML from findings:\n```yaml\n---\nid: eval-{task-slug}-{axis-lowercase}\ntrigger: \"when {task type}\"\naction: \"{specific improvement}\"\nconfidence: 0.6\ndomain: quality\nsource: self-eval\nscope: project\n---\n```\n\n## Integration Points\n- `\u002Fteam:verify` invokes self-eval on Layer 2 output before Layer 3 review\n- `\u002Fgsd-execute-phase` runs self-eval per subagent, aggregates in SUMMARY.md\n- High-confidence eval instincts (≥0.8) auto-update team-toolkit.md quality notes\n- Low scores (≤2) on correctness trigger automatic re-execution offer\n","@agents\u002FPROMPT-DEFENSE.md\n\n# Agent Self-Evaluation\n\nScore your own output (or another agent's output) across four axes to identify quality gaps and feed improvements into the learning system.\n\n## When to Use\n- After completing a `\u002Fteam:*` pipeline run\n- After generating a deliverable (PRD, architecture doc, code review)\n- When user asks \"how did I do?\" or \"evaluate this output\"\n- Automatically at end of `\u002Fgsd-execute-phase` for quality tracking\n\n## Evaluation Axes\n\n| Axis | Question | Failure Signals |\n|------|----------|-----------------|\n| **Correctness** | Is the output factually accurate and technically sound? | Wrong APIs, broken references, hallucinated facts, logic errors |\n| **Clarity** | Is the explanation understandable and well-structured? | Confusing structure, undefined jargon, missing context, rambling |\n| **Actionability** | Can the user act on the output immediately? | Vague suggestions, missing steps, no verification path |\n| **Conciseness** | Did it use the minimum tokens needed? | Redundancy, over-explanation, filler content, restating the question |\n\n## Scoring Scale\n```\n5 — Exceptional: no reasonable improvement possible\n4 — Good: minor nits only, no substantive gaps\n3 — Adequate: meets request but has notable weakness on ≥1 axis\n2 — Weak: clear gap affecting usability or correctness\n1 — Poor: fundamentally misses request or contains significant errors\n```\n\n## The Evidence Rule\nEvery score below 5 MUST cite specific evidence. A score of 3 cannot just say \"could be better\" — it must say exactly what is missing or wrong. **\"Show the gap, don't just name it.\"**\n\n## Procedure\n\n### Step 1: Collect Raw Material\nGather:\n- Original user request\n- Final output\u002Fdeliverable\n- Tool outputs verifying correctness (test results, exit codes, lint)\n- User feedback received during task (corrections, \"try again\")\n\n### Step 2: Score Each Axis Independently\nRate 1-5 with mandatory evidence for scores \u003C5.\n\n### Step 3: Generate Eval Report\n```\nSELF-EVALUATION REPORT\n======================\nTask: {brief description}\nOverall: {weighted average}\u002F5\n\nCORRECTNESS: {score}\u002F5\n  Evidence: {specific finding or \"No issues found\"}\n\nCLARITY: {score}\u002F5\n  Evidence: {specific finding or \"No issues found\"}\n\nACTIONABILITY: {score}\u002F5\n  Evidence: {specific finding or \"No issues found\"}\n\nCONCISENESS: {score}\u002F5\n  Evidence: {specific finding or \"No issues found\"}\n\nIMPROVEMENT INSTINCTS:\n- {trigger} → {action} (confidence: {0.3-0.9})\n```\n\n### Step 4: Feed Learning System\nIf learning system is active (PR-27+), auto-generate instinct YAML from findings:\n```yaml\n---\nid: eval-{task-slug}-{axis-lowercase}\ntrigger: \"when {task type}\"\naction: \"{specific improvement}\"\nconfidence: 0.6\ndomain: quality\nsource: self-eval\nscope: project\n---\n```\n\n## Integration Points\n- `\u002Fteam:verify` invokes self-eval on Layer 2 output before Layer 3 review\n- `\u002Fgsd-execute-phase` runs self-eval per subagent, aggregates in SUMMARY.md\n- High-confidence eval instincts (≥0.8) auto-update team-toolkit.md quality notes\n- Low scores (≤2) on correctness trigger automatic re-execution offer\n",{"name":5,"tags":54,"domain":57,"version":58,"supports":59,"description":7},[55,56,42,37],"evaluation","quality","meta","0.1.0",[60,61,62,46,41,45,44,63,64],"claude-code","cursor","codex","roo-code","amazon-q","main","cd89f013b617f7eea982a9bbc60e992974fda2aa","skills\u002Fagent-self-eval",15,"https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco","https:\u002F\u002Fcocoresearch.org\u002Fcoco\u002F","https:\u002F\u002Fgithub.com\u002Fcoco-research","https:\u002F\u002Fcocoresearch.org","Local-first, open-source tools for people who work with AI agents: governed memory, agents that check their own work, and data that stays on your machine.","2026-11-11 12:18:13",{"source":8,"skillName":5,"commands":76,"prompt":86,"zipAvailable":87},[77,80,83],{"tool":78,"command":79},"npx","npx skills add coco-research\u002Fcoco --skill agent-self-eval",{"tool":81,"command":82},"bunx","bunx skills add coco-research\u002Fcoco --skill agent-self-eval",{"tool":84,"command":85},"pnpm","pnpm dlx skills add coco-research\u002Fcoco --skill agent-self-eval","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fskills\u002Fagent-self-eval\u002FSKILL.md",true,[],[90,114,124,140,175,194],{"skillNo":91,"name":92,"nameZh":6,"description":93,"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":49},"01M71KEJXF9KMT0BWCMRSRFA4M","trading-super-intelligence","Trading Super Intelligence Team. Named real-world personas across 8 cells. Built local-first (LM Studio) and validator-gated. Illustrative composites; see DISCLAIMER.md.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Ftrading\u002FSKILL.md",[96],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[98,99,100,101,102,103,104,105,106,33,107,108,109,110,111,112,113],"super","trading super intelligence","intelligence","trading","validator","personas","local","composites","studio","across","world","first","gated","2026","lm studio","local-first",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":121,"publishedAt":49},"01M71KEFWS3CMAP7DF1P0FWTDE","strategy-super-intelligence","Strategy Super Intelligence Team. Named real-world personas across 7 cells. Built local-first (LM Studio) and validator-gated. Illustrative composites; see DISCLAIMER.md.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Fstrategy\u002FSKILL.md",[120],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[122,98,123,100,102,103,104,105,106,33,107,108,109,110,111,112,113],"strategy","strategy super intelligence",{"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":134,"publishedAt":49},"01M71KED56ZEPK2QE84QSQPMT0","risk-compliance-super-intelligence","Risk & Compliance (GRC) Super Intelligence Team. Named real-world personas across 7 cells. Built local-first (LM Studio) and validator-gated. Illustrative composites; see DISCLAIMER.md.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Frisk-compliance\u002FSKILL.md",[130,131],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":132,"categoryName":133,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000037","律师与法务",[135,98,136,137,138,100,102,103,104,105,139,106,33,107,108,109,110,111,112,113],"risk","risk compliance super intelligence","compliance","risk compliance","grc",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":159,"publishedAt":49},"01M71KE9A2FWSC74VA96W1EZSN","product-design-super-intelligence","Your product + design brain trust and decision partner. Named personas across 8 cells spanning product strategy, discovery\u002Fresearch, growth\u002Fmetrics, design foundations\u002Fusability, design leadership\u002Fcraft, UX\u002Fcontent, design systems, and a…","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Fproduct-design\u002FSKILL.md",[146,149,152,153,156],{"categoryNo":147,"categoryName":148,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":150,"categoryName":151,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":154,"categoryName":155,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000031","产品经理",{"categoryNo":157,"categoryName":158,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000032","设计师",[160,161,100,162,98,163,164,165,166,167,168,33,107,169,170,111,171,172,173,174],"design","product","product design","product design super intelligence","foundations","product-design","decision","design systems","usability","leadership","ux","brain","craft","metrics","trust",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":183,"publishedAt":49},"01M71KE6H9FPSD9TECYFBPXZ8Y","legal-ip-super-intelligence","Your legal, IP, and regulatory brain trust. 31 named personas across 7 cells covering patent strategy, tech licensing, regulatory litigation, AI governance, open-source compliance, privacy law, and antitrust.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Flegal-ip\u002FSKILL.md",[181,182],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":132,"categoryName":133,"taxonomyType":26,"taxonomyTypeDesc":27},[184,98,185,100,186,187,174,188,103,189,190,191,122,33,107,192,137,193,111,171],"ip","legal ip super intelligence","legal","sep","tech","litigation","ai governance","open","open-source","governance",{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":201,"publishedAt":49},"01M71KE36QRY610V6YVB9JWRND","healthcare-life-sciences-super-intelligence","Your healthcare and life sciences brain trust. 25 named personas across 7 cells covering drug discovery, medtech, biotech strategy, health policy, genomics, clinical trials, and healthcare economics.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Fhealthcare-life-sciences\u002FSKILL.md",[200],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[202,98,203,204,100,187,174,205,206,103,207,208,122,33,107,209,210,211,212,111],"healthcare","healthcare life sciences super intelligence","life","economics","discovery","policy","clinical","clinical trials","health","trials","genomics"]