[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JGVJ7H21GFHTJ57RBWC6C1":3,"skill-same:01M6JGVJ7H21GFHTJ57RBWC6C1":68},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M6JGVJ7H21GFHTJ57RBWC6C1","review-remediate",null,"Use for the review-then-fix-everything loop on a package or diff — deliver a grounded review report immediately (no scoping questions, no plan-approval), then remediate every finding as tracked numbered items, gating each batch on typecheck\u002Flint\u002Ftest\u002Fbuild plus an independent Codex pass until clean. Trigger on \"review and fix \u003Cpackage>\", \"remediate the review\", \"review-fix-verify\", or when the user wants a deep review followed by autonomous remediation. Distinct from gstack `review` (pre-landing PR review) and `code-review` (diff only) — this reviews from scratch AND fixes to green.","ancyloce\u002Fanvilkit-studio","ancyloce","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F103255835?v=4","01M6JGS0GSF9KTQE3VS6HA5FZ2","Ancyloce","01M6JGS0NK83XM8EJYT39C39CD",2,"MIT","https:\u002F\u002Fgithub.com\u002Fancyloce\u002Fanvilkit-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Freview-remediate\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"review remediate","review","clean","review report","fixes","for","reviews","trigger","as","deep","green","only","diff","use","landing","fix","autonomous","package","pr","pr review","2026-11-10 10:12:30",false,"---\nname: review-remediate\ndescription: Use for the review-then-fix-everything loop on a package or diff — deliver a grounded review report immediately (no scoping questions, no plan-approval), then remediate every finding as tracked numbered items, gating each batch on typecheck\u002Flint\u002Ftest\u002Fbuild plus an independent Codex pass until clean. Trigger on \"review and fix \u003Cpackage>\", \"remediate the review\", \"review-fix-verify\", or when the user wants a deep review followed by autonomous remediation. Distinct from gstack `review` (pre-landing PR review) and `code-review` (diff only) — this reviews from scratch AND fixes to green.\nversion: \"1.0.0\"\n---\n\n# Review → Remediate → Verify\n\nThe user's highest-value loop, codified. Run it end-to-end without stopping to ask how to proceed.\n\n## 1. Review (deliver immediately)\n\n- Produce the review report as your FIRST action — no scoping questions, no `ExitPlanMode`. State scope assumptions inline.\n- Read the target package\u002Fdiff in full; ground every finding in `file:line` evidence.\n- Classify by severity and number each finding so it is trackable: **P0** (correctness \u002F security \u002F release-blocker), **P1** (should-fix), **P2** (nice-to-have) → `P0-1`, `P1-2`, …\n- Write the report to `docs\u002Fcode-review\u002F\u003Ctarget>-review-\u003CUTC-timestamp>.md` (the `docs\u002F` tree is git-ignored working space).\n\n## 2. Track\n\n- Create one task per P0\u002FP1 finding (`TaskCreate`); flip to `in_progress` \u002F `completed` as you go.\n\n## 3. Remediate (batched, priority order)\n\n- Fix P0 first, then P1. Prefer a root-cause fix plus a regression test over a band-aid.\n- After editing source that ships from `dist\u002F`, rebuild the affected bundle before continuing — source-only edits do not reach consumers.\n\n## 4. Gate each batch\n\n- Run the full gate for touched packages: `pnpm typecheck`, `pnpm lint`, `pnpm test`, `pnpm build` (or the package's `check:all`).\n- Separate pre-existing \u002F unrelated failures (report them) from regressions you introduced (fix them). The repo has several documented pre-existing flakes — verify against clean `HEAD` before blaming your change.\n\n## 5. Independent verify (Codex)\n\n- Run an independent Codex pass over the changes (`\u002Fcodex:review`, or a scoped read-only `codex exec` — avoid `--uncommitted`, which times out here).\n- Fix everything it legitimately flags; re-run the gate. Iterate until Codex is clean AND all gates pass with zero new test failures.\n- If Codex is unavailable (usage limit \u002F timeout), say so explicitly and lean on the gates.\n\n## 6. Report\n\n- Summarize: findings closed (by id), gate results, Codex verdict, and any pre-existing failures documented separately. Stop only when every gate is green.\n\nLeave commits to the user — this repo: never commit.\n","# Review → Remediate → Verify\n\nThe user's highest-value loop, codified. Run it end-to-end without stopping to ask how to proceed.\n\n## 1. Review (deliver immediately)\n\n- Produce the review report as your FIRST action — no scoping questions, no `ExitPlanMode`. State scope assumptions inline.\n- Read the target package\u002Fdiff in full; ground every finding in `file:line` evidence.\n- Classify by severity and number each finding so it is trackable: **P0** (correctness \u002F security \u002F release-blocker), **P1** (should-fix), **P2** (nice-to-have) → `P0-1`, `P1-2`, …\n- Write the report to `docs\u002Fcode-review\u002F\u003Ctarget>-review-\u003CUTC-timestamp>.md` (the `docs\u002F` tree is git-ignored working space).\n\n## 2. Track\n\n- Create one task per P0\u002FP1 finding (`TaskCreate`); flip to `in_progress` \u002F `completed` as you go.\n\n## 3. Remediate (batched, priority order)\n\n- Fix P0 first, then P1. Prefer a root-cause fix plus a regression test over a band-aid.\n- After editing source that ships from `dist\u002F`, rebuild the affected bundle before continuing — source-only edits do not reach consumers.\n\n## 4. Gate each batch\n\n- Run the full gate for touched packages: `pnpm typecheck`, `pnpm lint`, `pnpm test`, `pnpm build` (or the package's `check:all`).\n- Separate pre-existing \u002F unrelated failures (report them) from regressions you introduced (fix them). The repo has several documented pre-existing flakes — verify against clean `HEAD` before blaming your change.\n\n## 5. Independent verify (Codex)\n\n- Run an independent Codex pass over the changes (`\u002Fcodex:review`, or a scoped read-only `codex exec` — avoid `--uncommitted`, which times out here).\n- Fix everything it legitimately flags; re-run the gate. Iterate until Codex is clean AND all gates pass with zero new test failures.\n- If Codex is unavailable (usage limit \u002F timeout), say so explicitly and lean on the gates.\n\n## 6. Report\n\n- Summarize: findings closed (by id), gate results, Codex verdict, and any pre-existing failures documented separately. Stop only when every gate is green.\n\nLeave commits to the user — this repo: never commit.\n",{"name":5,"version":44,"description":7},"1.0.0","main","e4eeaefbd56226a251b228f1beb87a293ab3140a",".claude\u002Fskills\u002Freview-remediate",1,"https:\u002F\u002Fgithub.com\u002Fancyloce\u002Fanvilkit-studio","http:\u002F\u002Fanvilkit.aiiua.com\u002F","https:\u002F\u002Fgithub.com\u002Fancyloce","🧙‍♂️  Front-end mage with a secret back-end talent. \r\n🔮  Fluent in React, Vue, Go, and Rust.\r\n📚  Book addict and  🎵  music lover. Let's create some  ✨ magic","2026-11-01 10:38:50",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add ancyloce\u002Fanvilkit-studio --skill review-remediate",{"tool":60,"command":61},"bunx","bunx skills add ancyloce\u002Fanvilkit-studio --skill review-remediate",{"tool":63,"command":64},"pnpm","pnpm dlx skills add ancyloce\u002Fanvilkit-studio --skill review-remediate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fancyloce\u002Fanvilkit-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Freview-remediate\u002FSKILL.md",true,[],[69,99,120,143,149,160],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":80,"publishedAt":39},"01M6JGVQAQWDRDT2CAQ2VH7D9V","react-doctor","Use when finishing a feature, fixing a bug, before committing React code, or when the user types `\u002Fdoctor`, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.","https:\u002F\u002Fgithub.com\u002Fancyloce\u002Fanvilkit-studio\u002Fblob\u002Fmain\u002Fpackages\u002Fruntime\u002Fcore\u002F.claude\u002Fskills\u002Freact-doctor\u002FSKILL.md",[75],{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",[81,82,83,84,85,86,87,88,89,90,91,32,92,93,21,94,95,96,97,98],"react","doctor","react doctor","workflow","architecture","lint","code","playbook","regression","bundle size","check","regression check","up","scan","local","feature","types","size",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":39},"01M6JGVDZD39P3Q97XGQPTTKQN","review-fixes","Close out an EXISTING code-review findings report — one subagent per finding, each with a regression test — then regenerate EN\u002Fzh\u002Fja\u002Fko docs, run all gates, and verify no stale or unexported symbols remain. Trigger on \"\u002Freview-fixes\", \"fix all N review findings\", \"close the review findings\", or when the user hands over a findings report to remediate. Distinct from review-remediate, which produces the review itself first — this skill starts from a report that already exists.","https:\u002F\u002Fgithub.com\u002Fancyloce\u002Fanvilkit-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Freview-fixes\u002FSKILL.md",[],[20,23,106,107,87,108,109,110,111,89,34,112,113,114,115,26,116,117,118,119],"review fixes","test","code-review","first","verify","subagent","regression test","en","zh","gates","with","review findings","which","Existing",{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":39},"01M6JGV8J3ZRFGCXR2W3Q9ZWYK","release-prep","Pre-release verification + go\u002Fno-go checklist for publishing @anvilkit packages. Detects the release surface (main workspace fixed-group vs components submodule), runs changeset status and the check:all release gates, enforces this repo's publish gotchas (version.ts drift, ui peer ranges, never-publish canvas-templates, bundle\u002Fapi-snapshot), then hands the exact publish command to the user. Use when asked to \"prep a release\", \"check release readiness\", \"\u002Frelease-prep\", or before cutting a version. Does NOT commit or publish.","https:\u002F\u002Fgithub.com\u002Fancyloce\u002Fanvilkit-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frelease-prep\u002FSKILL.md",[],[127,128,129,130,131,132,133,134,135,136,32,137,138,139,140,45,141,115,142,24],"release","prep","release prep","canvas","components","commit","api","Bash","changeset","repo","version","never","publishing","peer","drift","true",{"skillNo":144,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":148,"publishedAt":39},"01M6JGV33MBTTHMZ1SNJZHAA6H","https:\u002F\u002Fgithub.com\u002Fancyloce\u002Fanvilkit-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Freact-doctor\u002FSKILL.md",[147],{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},[81,82,83,84,85,86,87,88,89,90,91,32,92,93,21,94,95,96,97,98],{"skillNo":150,"name":151,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":157,"publishedAt":39},"01M6JGV1KQAFYH6ZQ864ZBCVVH","pre-refactor","https:\u002F\u002Fgithub.com\u002Fancyloce\u002Fanvilkit-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fpre-refactor\u002FSKILL.md",[154],{"categoryNo":155,"categoryName":156,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000007","代码审查",[158,159],"refactor","pre refactor",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":174,"publishedAt":39},"01M6JGTX3NW0PFBVP05G0VCEQB","phase-execute","Autonomous phase runner for numbered plans (docs\u002Fplans\u002F*, docs\u002Fprd\u002F*):\nscoped gates per task, full gate only at phase boundaries, checkpoint to\n.claude\u002Fstate\u002Fphase-run.json after every task so a run resumes at the\nexact next task, edit-guard.mjs against concurrent writers, explicit E2E\nservers, flaky quarantine, deliverables report at phase end. Use for\n\"execute phase X of \u003Cplan>\", \"drive the next phase\", \"phase-execute\n\u003Cplan>\", \"resume the phase\", or \"dry-run phase X\".","https:\u002F\u002Fgithub.com\u002Fancyloce\u002Fanvilkit-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fphase-execute\u002FSKILL.md",[166,169],{"categoryNo":167,"categoryName":168,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":170,"categoryName":171,"taxonomyType":172,"taxonomyTypeDesc":173},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[175,176,177,134,178,179,180,181,182,183,35,30,184,185,186,187,188,189,190,24],"execute","phase execute","run","plan","advance","run phase","read","write","edit","runner","milestone","next","full","end","dry","at"]