[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6K3CPSDQ1MTJS8MTS8EC0WR":3,"skill-same:01M6K3CPSDQ1MTJS8MTS8EC0WR":72},{"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":18,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":52,"install":53,"resources":65},"01M6K3CPSDQ1MTJS8MTS8EC0WR","plan-review",null,"Use only within active engineer\u002Fconduct DECIDE after coherence-check for Medium or Large work to adversarially review the final plan against the real source. Reports source-grounded findings; does not author or amend plan artifacts.","jstoup111\u002Fai-conductor","jstoup111","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1585332?v=4","01M6K374Y0VEFPVCT2KPBAN4HC","James Stoup","01M6K3751X0GFKNBD0198F50XN",7,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fjstoup111\u002Fai-conductor\u002Fblob\u002Fmain\u002Fskills\u002Fplan-review\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"plan","plan review","review","engineer","author","gating","conduct","plan artifacts","source","for","true","active","coherence","reports","only","use","check","decide","work","amend","artifacts","2026-11-10 10:12:30",false,"---\nname: plan-review\ndescription: \"Use only within active engineer\u002Fconduct DECIDE after coherence-check for Medium or Large work to adversarially review the final plan against the real source. Reports source-grounded findings; does not author or amend plan artifacts.\"\nenforcement: gating\nphase: decide\ndisable-model-invocation: true\n---\n\n## Purpose\n\nJudge the final plan against the target worktree's real source after `\u002Fcoherence-check` and before\nland. This is an adversarial, source-grounded review: deterministic candidate rows are prompts for\njudgment, never findings by themselves. Return only findings the supplied evidence supports; the\nengine owns dispatch, schema validation, artifact rendering, operator dispositions, and land\nenforcement.\n\nRun only for Medium and Large work. For Small work, do not create a review artifact or substitute\nthis review for the plan's §7b contradiction review.\n\n## Read-only review\n\nThis reviewer is read-only. It MUST NOT write or edit any worktree file, generated artifact,\noperator-decision store, configuration, or source; it MUST NOT stage or commit. Do not run tests,\nbuilds, formatters, or commands that modify project state. Inspect the supplied artifacts and source\nthrough the read-only session, then return the terminal structured result requested by the engine.\n\n## Inputs and evidence\n\nUse the supplied stories, every plan task, relevant ADR Decision sections, coherence artifact,\ncandidate rows, and the target worktree source. `ADR DECISIONS` contains the decisions changed by\nthe spec. `INDEX` lists the remaining in-scope decisions and coherence artifact by path; read each\nindexed item from its listed worktree path before relying on it. Assess the final plan rather than\nreconstructing candidate generation or routing.\n\nEvery finding needs concrete evidence. Record a feasibility finding citing the source `file:line`\nwhen a planned input differs from what production passes. Quote both passages for every\ncontradiction. An ungrounded suspicion is advisory at most: do not promote it to significant or\nblocking merely because it sounds plausible.\n\n## Candidate lenses\n\nJudge every supplied candidate under these lenses:\n\n- **test-impact:** an existing test references a path or identifier a task changes, but no task\n  updates that test.\n- **reachability:** a planned export or primitive has no production caller in source and no task\n  that supplies one.\n- **dependency-order:** a task needs a path, export, or identifier that only a task outside its\n  dependency closure introduces.\n- **feasibility:** a planned step cannot work against the actual source, including when its planned\n  input differs from the value production really passes.\n\nCandidates with insufficient evidence are not findings. Search beyond candidates for the\ncontradiction lenses below.\n\n## Contradiction sweep\n\nCheck static contradiction, oscillation, task-versus-task conflict, preserved-behavior conflict,\nand criterion-conflict. Treat ADR-versus-story as a cross-layer pair.\n\nFor every task-versus-task pair sharing a behavior, resource, state, input, output, or gate, ask:\n“if I fully satisfy A, does B still hold?” Then ask the other direction. Pairs with nothing shared\nneed no finding. Two negative answers identify an oscillation; one may identify a static\ncontradiction or another applicable conflict. A merely uncovered criterion is not a contradiction.\n\n**Layer ownership.** Story↔story pairs belong to `\u002Fconflict-check`. Cross-layer and task versus task\npairs belong to plan review at Medium and Large tier, and to the plan's §7b at Small tier.\n\n## Verification\n\nBefore returning, verify the task-versus-task sweep considered both directions for every pair with a\nshared subject. Verify every reported finding has the required source-grounded evidence, and that\neach claimed contradiction quotes both opposing passages. Return no finding for a candidate or pair\nthat the evidence does not support.\n","## Purpose\n\nJudge the final plan against the target worktree's real source after `\u002Fcoherence-check` and before\nland. This is an adversarial, source-grounded review: deterministic candidate rows are prompts for\njudgment, never findings by themselves. Return only findings the supplied evidence supports; the\nengine owns dispatch, schema validation, artifact rendering, operator dispositions, and land\nenforcement.\n\nRun only for Medium and Large work. For Small work, do not create a review artifact or substitute\nthis review for the plan's §7b contradiction review.\n\n## Read-only review\n\nThis reviewer is read-only. It MUST NOT write or edit any worktree file, generated artifact,\noperator-decision store, configuration, or source; it MUST NOT stage or commit. Do not run tests,\nbuilds, formatters, or commands that modify project state. Inspect the supplied artifacts and source\nthrough the read-only session, then return the terminal structured result requested by the engine.\n\n## Inputs and evidence\n\nUse the supplied stories, every plan task, relevant ADR Decision sections, coherence artifact,\ncandidate rows, and the target worktree source. `ADR DECISIONS` contains the decisions changed by\nthe spec. `INDEX` lists the remaining in-scope decisions and coherence artifact by path; read each\nindexed item from its listed worktree path before relying on it. Assess the final plan rather than\nreconstructing candidate generation or routing.\n\nEvery finding needs concrete evidence. Record a feasibility finding citing the source `file:line`\nwhen a planned input differs from what production passes. Quote both passages for every\ncontradiction. An ungrounded suspicion is advisory at most: do not promote it to significant or\nblocking merely because it sounds plausible.\n\n## Candidate lenses\n\nJudge every supplied candidate under these lenses:\n\n- **test-impact:** an existing test references a path or identifier a task changes, but no task\n  updates that test.\n- **reachability:** a planned export or primitive has no production caller in source and no task\n  that supplies one.\n- **dependency-order:** a task needs a path, export, or identifier that only a task outside its\n  dependency closure introduces.\n- **feasibility:** a planned step cannot work against the actual source, including when its planned\n  input differs from the value production really passes.\n\nCandidates with insufficient evidence are not findings. Search beyond candidates for the\ncontradiction lenses below.\n\n## Contradiction sweep\n\nCheck static contradiction, oscillation, task-versus-task conflict, preserved-behavior conflict,\nand criterion-conflict. Treat ADR-versus-story as a cross-layer pair.\n\nFor every task-versus-task pair sharing a behavior, resource, state, input, output, or gate, ask:\n“if I fully satisfy A, does B still hold?” Then ask the other direction. Pairs with nothing shared\nneed no finding. Two negative answers identify an oscillation; one may identify a static\ncontradiction or another applicable conflict. A merely uncovered criterion is not a contradiction.\n\n**Layer ownership.** Story↔story pairs belong to `\u002Fconflict-check`. Cross-layer and task versus task\npairs belong to plan review at Medium and Large tier, and to the plan's §7b at Small tier.\n\n## Verification\n\nBefore returning, verify the task-versus-task sweep considered both directions for every pair with a\nshared subject. Verify every reported finding has the required source-grounded evidence, and that\neach claimed contradiction quotes both opposing passages. Return no finding for a candidate or pair\nthat the evidence does not support.\n",{"name":5,"phase":36,"description":7,"enforcement":24,"disable-model-invocation":45},true,"main","136b34ec6792f53d0beba330dfa2dffad6c93484","skills\u002Fplan-review",2,"https:\u002F\u002Fgithub.com\u002Fjstoup111\u002Fai-conductor","https:\u002F\u002Fgithub.com\u002Fjstoup111","2026-11-11 08:28:50",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":45},[55,58,61],{"tool":56,"command":57},"npx","npx skills add jstoup111\u002Fai-conductor --skill plan-review",{"tool":59,"command":60},"bunx","bunx skills add jstoup111\u002Fai-conductor --skill plan-review",{"tool":62,"command":63},"pnpm","pnpm dlx skills add jstoup111\u002Fai-conductor --skill plan-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjstoup111\u002Fai-conductor\u002Fblob\u002Fmain\u002Fskills\u002Fplan-review\u002FSKILL.md",[66],{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"agents\u002Fopenai.yaml","REFERENCE","参考文档",43,"https:\u002F\u002Fgithub.com\u002Fjstoup111\u002Fai-conductor\u002Fblob\u002Fmain\u002Fskills\u002Fplan-review\u002Fagents\u002Fopenai.yaml",[73,90,129,150,169,183],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":40},"01M70YKSA2H7Q9WSRD1ECEGY20","build-review-dependency-hygiene","Judge whether a feature diff adds unnecessary, insufficiently pinned, or license-incompatible dependencies.","https:\u002F\u002Fgithub.com\u002Fjstoup111\u002Fai-conductor\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-review-dependency-hygiene\u002FSKILL.md",[],[80,81,82,83,84,21,85,86,87,88,29,89,24],"build","dependency hygiene","dependency","hygiene","build review dependency hygiene","feature","diff","dependencies","license","judge",{"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":109,"publishedAt":40},"01M6K3EQQ6ADH3G2RMYK6XE26E","writing-system-tests","Use BEFORE implementing any feature that has stories in .docs\u002Fstories\u002F — generates failing acceptance specs from acceptance criteria as the RED phase of TDD. Generates HTTP\u002Frequest-level acceptance tests for headless\u002FAPI projects, end-to-end UI tests for projects with a frontend, using the project's own test framework and directory conventions.","https:\u002F\u002Fgithub.com\u002Fjstoup111\u002Fai-conductor\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-system-tests\u002FSKILL.md",[96,101,104],{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",{"categoryNo":102,"categoryName":103,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,24,127,128],"writing","system","tests","writing system tests","projects","headless","project","end","implementing","frontend","acceptance","api","claims","directory","ui","framework","failing","phase","request",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":40},"01M6K3EHR0QQ1QY1S9RC6D1WTD","verify-claims","Use only when an active workflow is about to rely on a nontrivial factual claim or assumption for a spec, plan, ADR, finding, or code decision. Do not invoke for casual questions, status reports, restatements, or trivially verifiable mechanics.","https:\u002F\u002Fgithub.com\u002Fjstoup111\u002Fai-conductor\u002Fblob\u002Fmain\u002Fskills\u002Fverify-claims\u002FSKILL.md",[],[136,122,137,138,139,28,140,141,29,142,33,34,143,144,32,19,30,145,146,147,148,24,149],"verify claims","verify","do","adr","decision","claim","mechanics","workflow","code","questions","about","spec","invoke","when",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":156,"publishedAt":40},"01M6K3ED4NF5DJA2Y35MH2JCRC","tdd","Use when implementing any feature or bugfix. Five-step cycle: RED → DOMAIN → GREEN → DOMAIN → COMMIT. Enforces test-first development with domain integrity review at every phase boundary.","https:\u002F\u002Fgithub.com\u002Fjstoup111\u002Fai-conductor\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002FSKILL.md",[],[152,157,158,159,118,160,21,161,162,163,164,85,165,29,34,166,167,168,149,127],"green","cycle","structural","commit","at","bugfix","integrity","domain","development","with","test","test-first",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":175,"publishedAt":40},"01M6K3E6PEXBXYY2K8TSRTN1JT","stories","Use only within active engineer\u002Fconduct DECIDE after architecture approval, when a committed `.docs\u002Fstories` acceptance artifact is required. Do not invoke for general user-story examples, requirements discussion, or direct implementation requests.","https:\u002F\u002Fgithub.com\u002Fjstoup111\u002Fai-conductor\u002Fblob\u002Fmain\u002Fskills\u002Fstories\u002FSKILL.md",[],[171,25,138,28,36,22,176,29,33,34,120,177,178,179,122,180,137,181,30,182,148,24,149],"general","requirements","architecture","examples","artifact","requests","implementation",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":189,"publishedAt":40},"01M6K3E1HE7267YKFJQ3YFCGW5","stack-land","Use when an operator needs to land reviewed manual changes on the correct closed child of a stacked feature. Operator-invoked only: inspect ownership, propose the safe child with evidence, and require confirmation before opening the landing.","https:\u002F\u002Fgithub.com\u002Fjstoup111\u002Fai-conductor\u002Fblob\u002Fmain\u002Fskills\u002Fstack-land\u002FSKILL.md",[],[190,191,192,166,122,193,194,195,137,85,196,197,198,199,200,29,201,33,34,202,149,203],"stack","land","stack land","evidence","child","changes","inspect","manual","correct","landing","safe","operator","confirmation","advisory"]