[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DCAW3A9NNEC90TRPRVGKJV":3,"skill-same:01M6DCAW3A9NNEC90TRPRVGKJV":50},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":25,"linkOnly":26,"markdownContent":27,"markdownBody":28,"frontMatter":29,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":13,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M6DCAW3A9NNEC90TRPRVGKJV","agent-as-judge",null,"Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fplatform\u002Frouting\u002Ffixtures\u002Fhome\u002F.agents\u002Fskills\u002Fagent-as-judge\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24],"as","agent as judge","2026-11-10 10:12:30",false,"---\nname: agent-as-judge\ndescription: Advisory, evidence-citing Agent-as-a-Judge. Use when you want a second opinion on whether a completion meets its Definition of Done AFTER the deterministic verification cluster (typed receipts, fail-first red-proof, execution-consensus, golden-journey oracle) has run — it decomposes the DoD into falsifiable YES\u002FNO items, cites a ledger-event or evidence-hash per item (chain-of-custody), execute-to-confirms every would-be-blocking finding, and scores against the ICD-203 nine analytic standards. Its opinion NEVER gates or grants \"done\" (COUNCIL C3): only a re-run executable receipt could ever block and that path is deferred indefinitely, so it is 100% ADVISORY and ships in SHADOW mode (observe + log, never blocks, never nags). Imports passk-stats (F5) for kappa\u002Fe-value calibration vs the owner's Codex-reflect corrections; stays advisory while kappa \u003C 0.6 and auto-demotes on decay. NOT a done-gate, NOT terminal authority; a same-vendor judge shares the fixer's blind spots so prefer a cross-vendor Codex second judge on contested calls. Do NOT use to BLOCK a merge\u002Fcompletion, and do NOT use it in place of the deterministic gates.\n---\n\n# Agent-as-a-Judge (advisory, evidence-citing)\n\nA tool-using LLM judge that annotates the **subjective residue** of a Definition of Done — the\nitems the deterministic gates cannot decide (\"is the artifact actually correct?\", \"does this\nmatch intent?\"). It is **advisory this wave**: its opinion never gates, and it ships in SHADOW\nmode. The subagent contract lives in `agents\u002Fagent-as-judge.md`; this skill is the operator guide\nplus the reference implementation the judge runs.\n\n**Evidence:** MASTER-DECISION-QUEUE A5 (`gem-hunt-2026-07-12`); COUNCIL-VERDICT C3\n(*\"opinion never gates, only a cited executed receipt can block — deferred indefinitely\"*).\nResearch: Agent-as-a-Judge (arXiv 2410.10934); ICD-203 Analytic Standards; EvalGen (2404.12272);\nJudgeBench (LLM judges ~chance) — the empirical basis for the advisory-until-calibrated stance.\n\n## Where it sits in the pipeline (read this first)\n\n```\n   deterministic cluster (carries ALL blocking weight, no calibration needed)\n   ┌─────────────┬──────────────┬────────────────────┬─────────────────────┐\n   │ A1 typed    │ A3 fail-first│ A4 execution-      │ C4 golden-journey   │\n   │ receipts    │ red-proof    │ consensus          │ oracle (keystone)   │\n   └─────────────┴──────────────┴────────────────────┴─────────────────────┘\n                                   │  green?\n                                   ▼\n              ┌─────────────────────────────────────────────┐\n              │  Agent-as-a-Judge  (THIS)  — runs AFTER      │\n              │  ADVISORY · SHADOW · annotates SUBJECTIVE DoD │\n\n### When to use\n### When NOT to use\n### The contract in one screen\n### Protocol (four steps)\n### Calibration harness (passk-stats \u002F F5)\n### Shadow-mode logging (COUNCIL C5)\n### Reference implementation\n### Honest limits\n","# Agent-as-a-Judge (advisory, evidence-citing)\n\nA tool-using LLM judge that annotates the **subjective residue** of a Definition of Done — the\nitems the deterministic gates cannot decide (\"is the artifact actually correct?\", \"does this\nmatch intent?\"). It is **advisory this wave**: its opinion never gates, and it ships in SHADOW\nmode. The subagent contract lives in `agents\u002Fagent-as-judge.md`; this skill is the operator guide\nplus the reference implementation the judge runs.\n\n**Evidence:** MASTER-DECISION-QUEUE A5 (`gem-hunt-2026-07-12`); COUNCIL-VERDICT C3\n(*\"opinion never gates, only a cited executed receipt can block — deferred indefinitely\"*).\nResearch: Agent-as-a-Judge (arXiv 2410.10934); ICD-203 Analytic Standards; EvalGen (2404.12272);\nJudgeBench (LLM judges ~chance) — the empirical basis for the advisory-until-calibrated stance.\n\n## Where it sits in the pipeline (read this first)\n\n```\n   deterministic cluster (carries ALL blocking weight, no calibration needed)\n   ┌─────────────┬──────────────┬────────────────────┬─────────────────────┐\n   │ A1 typed    │ A3 fail-first│ A4 execution-      │ C4 golden-journey   │\n   │ receipts    │ red-proof    │ consensus          │ oracle (keystone)   │\n   └─────────────┴──────────────┴────────────────────┴─────────────────────┘\n                                   │  green?\n                                   ▼\n              ┌─────────────────────────────────────────────┐\n              │  Agent-as-a-Judge  (THIS)  — runs AFTER      │\n              │  ADVISORY · SHADOW · annotates SUBJECTIVE DoD │\n\n### When to use\n### When NOT to use\n### The contract in one screen\n### Protocol (four steps)\n### Calibration harness (passk-stats \u002F F5)\n### Shadow-mode logging (COUNCIL C5)\n### Reference implementation\n### Honest limits\n",{},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","platform\u002Frouting\u002Ffixtures\u002Fhome\u002F.agents\u002Fskills\u002Fagent-as-judge","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":7,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill agent-as-judge",{"tool":42,"command":43},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill agent-as-judge",{"tool":45,"command":46},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill agent-as-judge","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fplatform\u002Frouting\u002Ffixtures\u002Fhome\u002F.agents\u002Fskills\u002Fagent-as-judge\u002FSKILL.md",true,[],[51,73,100,127,141,157],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":25},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[58,59,60,61,62,63,64,65,66,67,68,69,70,71,72],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","use","context","repo","injection","execution","file",{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":80,"publishedAt":25},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[79],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[81,82,83,84,85,86,87,88,89,90,91,92,93,94,67,95,96,97,98,99],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":112,"publishedAt":25},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[106,109],{"categoryNo":107,"categoryName":108,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":110,"categoryName":111,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",[113,114,115,116,117,118,119,120,121,122,82,123,124,125,126],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":25},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[129,134,135,136,137,138,139,140],"setup","report","project","installation","project setup","issues","state",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":148,"publishedAt":25},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[147],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[143,149,63,150,151,152,67,153,154,155,156],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":158,"name":134,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":25},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[134,136,97,163,138,164],"files","interactive"]