[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74G2TMBJFXPDVX84PJABBWN":3,"skill-same:01M74G2TMBJFXPDVX84PJABBWN":46},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M74G2TMBJFXPDVX84PJABBWN","cavekit-review",null,"Adversarial senior review of the spec before any code is written. Constructs a skeptical reviewer whose authority comes from the codebase, §R research, and live best-practice — then tries to REFUTE the spec, not rubber-stamp it. Every finding cites evidence; unverifiable ones are flagged. Survivors harden §V; the run ends in an explicit go\u002Fno-go gate. Use when users invoke \u002Fck:review, say \"review the spec\", \"red-team this\", or ask \"is this plan sound\".","casualjim\u002Fpi-mimir","casualjim","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F456109?v=4","01M74FWNWVYZQ29YNASRYNTCG4","Ivan Porto Carrero","01M74FWNXE5R8481XV0Q8Q7EY0",16,"MIT","https:\u002F\u002Fgithub.com\u002Fcasualjim\u002Fpi-mimir\u002Fblob\u002Fmain\u002Fpackages\u002Fpi-cavekit\u002Fskills\u002Fcavekit-review\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: cavekit-review\ndescription: Adversarial senior review of the spec before any code is written. Constructs a skeptical reviewer whose authority comes from the codebase, §R research, and live best-practice — then tries to REFUTE the spec, not rubber-stamp it. Every finding cites evidence; unverifiable ones are flagged. Survivors harden §V; the run ends in an explicit go\u002Fno-go gate. Use when users invoke \u002Fck:review, say \"review the spec\", \"red-team this\", or ask \"is this plan sound\".\n---\n\n# cavekit-review — refute the spec before build\n\nEvery finding cites evidence — file:line or a source. No evidence → flag `[unverified]`. Default to refuted: a flaw that cannot be proved is a flaw noted, not waved through. Defers all `SPEC.md` writes to `cavekit-spec`.\n\nRead bundled `..\u002F..\u002FFORMAT.md` before interpreting §G §C §I §R §V §T.\n\n## When to review\n\n- Before `\u002Fck:build` on a high-blast-radius change (shared module, auth, data, money, public §I).\n- Spec touched §I or §V that other code depends on.\n- Right-sizing says the cost of a wrong build > the cost of one review pass.\n\nSkip for a trivial, reversible, well-understood change. Adversarial review on a typo hallucinates flaws and wastes the budget.\n\n## Phase 0 — capture\n\nRead the spec: §G §C §I §R §V §T. Hold the whole thing. Review the spec, not memory of the conversation. If `cavecrew-investigator` is available, use it for read-only compressed codebase facts (patterns, existing invariants, callers); it must not design or edit.\n\n## Phase 1 — construct the senior\n\nBuild a reviewer with real authority, not a generic critic:\n\n- Codebase — grep\u002Fread the modules this spec touches. What patterns, what invariants already hold?\n- §R — what did research establish? A spec decision that contradicts §R is a finding.\n- Live — for any best-practice claim that is uncertain, fetch it. An out-of-date assumption is a flaw.\n\nA reviewer with no evidence is just an opinion. Earn the authority first.\n\n## Phase 2 — refute\n\nAttack the spec on these axes. For each, try to find the case where it breaks:\n\n- Goal vs reality — does §G solve the actual problem, or a proxy?\n- Missing invariant — what can go wrong that no §V catches? (most findings live here)\n- Interface drift — does §I match what callers already expect? (cite the caller, file:line)\n- Constraint conflict — do two §C bullets contradict? does one fight §R?\n- Unowned edge — the input, ordering, failure, or concurrency case no §T covers.\n- Altitude — §T too vague to act on, or so granular it is just typing?\n\n## Phase 3 — classify\n\nEach finding: `evidence → claim → severity`.\n\n- BLOCK — build on this spec ships a real defect. Must fix first.\n- HARDEN — add\u002Fsharpen a §V so the build cannot regress it.\n- NOTE — worth knowing, not blocking.\n\nNo evidence? Down-rank to NOTE and tag `[unverified]`. ⊥ inflate a hunch to BLOCK.\n\n## Phase 4 — harden §V and gate\n\n- Each HARDEN finding → a draft §V line (testable, cites the §I\u002Fbehavior it guards). Hand to `cavekit-spec` to write.\n- End on an explicit gate using `ask_user_question` only for the GO\u002FNO-GO decision after showing the verdict in normal text:\n\n```text\n## review verdict\nBLOCK: 1 — §I.api shape ≠ caller src\u002Fclient.ts:40. fix §I before build.\nHARDEN: 2 — drafted V8 (idempotent refund), V9 (tx around dual write).\nNOTE: 1 — §T4 vague, split before \u002Fck:build.\ngate: NO-GO until BLOCK cleared. then \u002Fck:build §T after cavekit-spec writes V8,V9.\n```\n\nGO or NO-GO, never a shrug. Review is the checkpoint that stops a confident wrong build.\n\n## Boundaries\n\n- ⊥ write `SPEC.md`. Draft §V and hand to `cavekit-spec`.\n- ⊥ pass a finding with no evidence as fact. Flag `[unverified]`.\n- ⊥ review trivia. Right-size or skip.\n- ⊥ rewrite the user's intent. Harden the spec, do not replace its goal.\n- Reference sibling skills by `cavekit-\u003Cverb>` names (e.g. `cavekit-spec`, `cavekit-build`), never upstream `skills\u002F\u003Cverb>\u002FSKILL.md` paths.\n","# cavekit-review — refute the spec before build\n\nEvery finding cites evidence — file:line or a source. No evidence → flag `[unverified]`. Default to refuted: a flaw that cannot be proved is a flaw noted, not waved through. Defers all `SPEC.md` writes to `cavekit-spec`.\n\nRead bundled `..\u002F..\u002FFORMAT.md` before interpreting §G §C §I §R §V §T.\n\n## When to review\n\n- Before `\u002Fck:build` on a high-blast-radius change (shared module, auth, data, money, public §I).\n- Spec touched §I or §V that other code depends on.\n- Right-sizing says the cost of a wrong build > the cost of one review pass.\n\nSkip for a trivial, reversible, well-understood change. Adversarial review on a typo hallucinates flaws and wastes the budget.\n\n## Phase 0 — capture\n\nRead the spec: §G §C §I §R §V §T. Hold the whole thing. Review the spec, not memory of the conversation. If `cavecrew-investigator` is available, use it for read-only compressed codebase facts (patterns, existing invariants, callers); it must not design or edit.\n\n## Phase 1 — construct the senior\n\nBuild a reviewer with real authority, not a generic critic:\n\n- Codebase — grep\u002Fread the modules this spec touches. What patterns, what invariants already hold?\n- §R — what did research establish? A spec decision that contradicts §R is a finding.\n- Live — for any best-practice claim that is uncertain, fetch it. An out-of-date assumption is a flaw.\n\nA reviewer with no evidence is just an opinion. Earn the authority first.\n\n## Phase 2 — refute\n\nAttack the spec on these axes. For each, try to find the case where it breaks:\n\n- Goal vs reality — does §G solve the actual problem, or a proxy?\n- Missing invariant — what can go wrong that no §V catches? (most findings live here)\n- Interface drift — does §I match what callers already expect? (cite the caller, file:line)\n- Constraint conflict — do two §C bullets contradict? does one fight §R?\n- Unowned edge — the input, ordering, failure, or concurrency case no §T covers.\n- Altitude — §T too vague to act on, or so granular it is just typing?\n\n## Phase 3 — classify\n\nEach finding: `evidence → claim → severity`.\n\n- BLOCK — build on this spec ships a real defect. Must fix first.\n- HARDEN — add\u002Fsharpen a §V so the build cannot regress it.\n- NOTE — worth knowing, not blocking.\n\nNo evidence? Down-rank to NOTE and tag `[unverified]`. ⊥ inflate a hunch to BLOCK.\n\n## Phase 4 — harden §V and gate\n\n- Each HARDEN finding → a draft §V line (testable, cites the §I\u002Fbehavior it guards). Hand to `cavekit-spec` to write.\n- End on an explicit gate using `ask_user_question` only for the GO\u002FNO-GO decision after showing the verdict in normal text:\n\n```text\n## review verdict\nBLOCK: 1 — §I.api shape ≠ caller src\u002Fclient.ts:40. fix §I before build.\nHARDEN: 2 — drafted V8 (idempotent refund), V9 (tx around dual write).\nNOTE: 1 — §T4 vague, split before \u002Fck:build.\ngate: NO-GO until BLOCK cleared. then \u002Fck:build §T after cavekit-spec writes V8,V9.\n```\n\nGO or NO-GO, never a shrug. Review is the checkpoint that stops a confident wrong build.\n\n## Boundaries\n\n- ⊥ write `SPEC.md`. Draft §V and hand to `cavekit-spec`.\n- ⊥ pass a finding with no evidence as fact. Flag `[unverified]`.\n- ⊥ review trivia. Right-size or skip.\n- ⊥ rewrite the user's intent. Harden the spec, do not replace its goal.\n- Reference sibling skills by `cavekit-\u003Cverb>` names (e.g. `cavekit-spec`, `cavekit-build`), never upstream `skills\u002F\u003Cverb>\u002FSKILL.md` paths.\n",{"name":5,"description":7},"main","86a206d111fba4ffc9c47c363486479262e63513","packages\u002Fpi-cavekit\u002Fskills\u002Fcavekit-review",9,"https:\u002F\u002Fgithub.com\u002Fcasualjim\u002Fpi-mimir","https:\u002F\u002Fgithub.com\u002Fcasualjim","http:\u002F\u002Fflanders.co.nz","2026-11-10 15:32:15",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add casualjim\u002Fpi-mimir --skill cavekit-review",{"tool":38,"command":39},"bunx","bunx skills add casualjim\u002Fpi-mimir --skill cavekit-review",{"tool":41,"command":42},"pnpm","pnpm dlx skills add casualjim\u002Fpi-mimir --skill cavekit-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcasualjim\u002Fpi-mimir\u002Fblob\u002Fmain\u002Fpackages\u002Fpi-cavekit\u002Fskills\u002Fcavekit-review\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M74GK3CG2X0988XMHBKNC0HG","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Fcasualjim\u002Fpi-mimir\u002Fblob\u002Fmain\u002Fpackages\u002Fpi-pstack\u002Fskills\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M74GK2A4034JSAN8BCGBEPVB","unslop","Cut AI tells from any writing.","https:\u002F\u002Fgithub.com\u002Fcasualjim\u002Fpi-mimir\u002Fblob\u002Fmain\u002Fpackages\u002Fpi-pstack\u002Fskills\u002Funslop\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M74GK13302GXTR58TM47BQY1","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002Fcasualjim\u002Fpi-mimir\u002Fblob\u002Fmain\u002Fpackages\u002Fpi-pstack\u002Fskills\u002Ftypescript-best-practices\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M74GJYB1DJCA4AQH22MWYM9J","technical-writing","Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for \u002Fskill:technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.","https:\u002F\u002Fgithub.com\u002Fcasualjim\u002Fpi-mimir\u002Fblob\u002Fmain\u002Fpackages\u002Fpi-pstack\u002Fskills\u002Ftechnical-writing\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M74GJW7794XM60AKH76941T0","teach","Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.","https:\u002F\u002Fgithub.com\u002Fcasualjim\u002Fpi-mimir\u002Fblob\u002Fmain\u002Fpackages\u002Fpi-pstack\u002Fskills\u002Fteach\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M74GJPQN3RW4FN7G78W2NFR1","tdd","Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.","https:\u002F\u002Fgithub.com\u002Fcasualjim\u002Fpi-mimir\u002Fblob\u002Fmain\u002Fpackages\u002Fpi-pstack\u002Fskills\u002Ftdd\u002FSKILL.md",[],[]]