[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EFASYHDS7ACJ6M84HP9G4D":3,"skill-same:01M7EFASYHDS7ACJ6M84HP9G4D":56},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M7EFASYHDS7ACJ6M84HP9G4D","code-review",null,"Review Git changes when a ticket produces a code diff, after implementation and before landing. Use when the user asks to \"审代码\", \"审 PR\", \"review\", or \"代码审查\" against Standards and Spec axes. Orchestrates two parallel sub-agents and applies a severity gate. Does not patch; GATE BLOCKED hands off to review-report-repair.","winter6205\u002Farthurpower","winter6205","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F136674824?v=4","01M7EF9EWNYDKHX9MR3AG5QV7A","01M7EF9EXCC1CNFXQNV6PS3M8B",2,"MIT","https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fcode-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: code-review\ndescription: Review Git changes when a ticket produces a code diff, after implementation and before landing. Use when the user asks to \"审代码\", \"审 PR\", \"review\", or \"代码审查\" against Standards and Spec axes. Orchestrates two parallel sub-agents and applies a severity gate. Does not patch; GATE BLOCKED hands off to review-report-repair.\nbucket: engineering\ntype: technique\n---\n\n# Code Review\n\nThin orchestration skill: delegate Standards and Spec review to two parallel sub-agents, then apply a severity gate. Do not review code inline.\n\n## When to use\n\n- When a ticket produces a code diff and the main agent is about to land the round.\n- When the user asks to \"审代码\", \"审 PR\", \"review\", or \"代码审查\" against the per-ticket loop.\n- When a review verdict (Standards + Spec) with severity gating is required before landing.\n\n## When not to use\n\n- Docs-only or config-only changes (no code diff to review).\n- Pre-implementation plan review; use `architecture-change-reviewer` for that gate.\n- Repairing findings from this skill; that is the next slot `review-report-repair`.\n- S1-S6 measurement; use the matching S* skill or `\u002Faudit` (plugin self-changes: `arthurpower-audit-agent`).\n\n## Procedure\n\n1. **Pinned ref** — Resolve the fixed diff point: pinned commit SHA, merge-base, branch, or tag (e.g. `git diff \u003Cbase>..HEAD`). The ref must be unambiguous; capture base and HEAD explicitly.\n   完成判据: pinned ref (base + HEAD) recorded and reproducible.\n\n2. **Spec source resolved** — Resolve the spec source via the 4-level priority defined in `spec-reviewer-agent` (commit message issue ref → user-supplied path → repo `docs\u002F` or `specs\u002F` match → ask the caller). At level 4, halt the orchestrator and report the missing source instead of inventing requirements.\n   完成判据: spec source identified, or level-4 blocker reported back to main agent.\n\n3. **Standards source pinned** — Standards axis is sourced from `code-review-protocol` (§2.2 Fowler 12 smells, §4 severity levels) plus any repository coding standards. Do not duplicate the protocol in this skill; reference it.\n   完成判据: standards source = `arthurpower\u002Fskills\u002Fcode-review\u002Freferences\u002Fprotocol.md`; Fowler 12 + severity scale cited by pointer only.\n\n4. **Spawn two agents in parallel** — Dispatch in a single message via the Agent tool:\n   - `arthurpower:standards-reviewer-agent` — receives the pinned ref and standards source path; returns Standards-axis findings table with `OVERALL` line.\n   - `arthurpower:spec-reviewer-agent` — receives the pinned ref and resolved spec source; returns Spec-axis findings table with `OVERALL` line.\n     Inject the pinned ref (step 1), spec source (step 2), standards source (step 3) into each call; do not paraphrase severity definitions or the Fowler list.\n     完成判据: both agents return findings tables (including no-finding results) with the exact `OVERALL` line.\n\n5. **Aggregate side-by-side** — Merge the two findings tables into a single side-by-side report (no cross-axis reranking, no combining severities). Preserve file:line evidence and the per-axis `OVERALL` lines. Count unresolved findings per axis.\n   完成判据: side-by-side aggregation table produced, per-axis counts recorded.\n\n6. **Severity gate** — Apply the severity gate from `code-review-protocol` §4:\n   - Unresolved High (either axis) → **BLOCKED**; do **not** patch in this skill. Emit the next-slot line `NEXT: review-report-repair` and pass the aggregation table as the report (in-session is enough).\n   - Medium (without a named follow-up ticket) → advisory; do not auto-invoke repair.\n   - Low → informational only.\n     Final verdict line: `GATE: PASS` or `GATE: BLOCKED: \u003CN> High unresolved`.\n     完成判据: gate verdict emitted (PASS or BLOCKED: N High); BLOCKED includes the NEXT line; this skill does not edit product code.\n\n## Review-stage placement\n\nDocumented sequence (current slot only):\n\n- Before change: `architecture-change-reviewer` gates the plan (5-verdict).\n- After change: this skill (Standards + Spec via two parallel sub-agents).\n- This skill `GATE: BLOCKED`: next slot `review-report-repair`.\n- This skill `GATE: PASS`: this skill ends; landing claim is `verification-before-completion`.\n\nThis skill is conditional: trigger only when the ticket produced a code diff; do not run on docs\u002Fconfig-only changes.\n\n## Acceptance Criteria\n\n- [ ] The pinned diff ref (base + HEAD) is explicit and reproducible.\n- [ ] Spec source resolved via the 4-level priority, or level-4 blocker reported back.\n- [ ] Standards source references `code-review-protocol` §2.2 and §4 by pointer only (no duplicated Fowler list).\n- [ ] Both `standards-reviewer-agent` and `spec-reviewer-agent` were dispatched in parallel and returned findings tables with `OVERALL` lines.\n- [ ] Findings from both axes are presented side-by-side without cross-axis reranking.\n- [ ] Every finding includes severity, file:line, axis, problem, and remediation.\n- [ ] Severity gate verdict is emitted (`GATE: PASS` or `GATE: BLOCKED: N High`). BLOCKED includes `NEXT: review-report-repair` and does not patch.\n\n## Verification\n\nSkill type: technique\nBar level: minimum\n\n- Confirm the frontmatter omits `disable-model-invocation`, keeping the skill model-invoked.\n- Confirm `bucket: engineering` is preserved.\n- Confirm the description states a conditional trigger (\"when a ticket produces a code diff\") and no longer references the upstream CLI wrapper.\n- Confirm no inline CLI command, executable build, or binary path appears in the body.\n- Confirm the Fowler 12 smell list is referenced by pointer (protocol §2.2), not duplicated in body.\n- Confirm this skill does not implement fixes (repair is `review-report-repair`).\n","# Code Review\n\nThin orchestration skill: delegate Standards and Spec review to two parallel sub-agents, then apply a severity gate. Do not review code inline.\n\n## When to use\n\n- When a ticket produces a code diff and the main agent is about to land the round.\n- When the user asks to \"审代码\", \"审 PR\", \"review\", or \"代码审查\" against the per-ticket loop.\n- When a review verdict (Standards + Spec) with severity gating is required before landing.\n\n## When not to use\n\n- Docs-only or config-only changes (no code diff to review).\n- Pre-implementation plan review; use `architecture-change-reviewer` for that gate.\n- Repairing findings from this skill; that is the next slot `review-report-repair`.\n- S1-S6 measurement; use the matching S* skill or `\u002Faudit` (plugin self-changes: `arthurpower-audit-agent`).\n\n## Procedure\n\n1. **Pinned ref** — Resolve the fixed diff point: pinned commit SHA, merge-base, branch, or tag (e.g. `git diff \u003Cbase>..HEAD`). The ref must be unambiguous; capture base and HEAD explicitly.\n   完成判据: pinned ref (base + HEAD) recorded and reproducible.\n\n2. **Spec source resolved** — Resolve the spec source via the 4-level priority defined in `spec-reviewer-agent` (commit message issue ref → user-supplied path → repo `docs\u002F` or `specs\u002F` match → ask the caller). At level 4, halt the orchestrator and report the missing source instead of inventing requirements.\n   完成判据: spec source identified, or level-4 blocker reported back to main agent.\n\n3. **Standards source pinned** — Standards axis is sourced from `code-review-protocol` (§2.2 Fowler 12 smells, §4 severity levels) plus any repository coding standards. Do not duplicate the protocol in this skill; reference it.\n   完成判据: standards source = `arthurpower\u002Fskills\u002Fcode-review\u002Freferences\u002Fprotocol.md`; Fowler 12 + severity scale cited by pointer only.\n\n4. **Spawn two agents in parallel** — Dispatch in a single message via the Agent tool:\n   - `arthurpower:standards-reviewer-agent` — receives the pinned ref and standards source path; returns Standards-axis findings table with `OVERALL` line.\n   - `arthurpower:spec-reviewer-agent` — receives the pinned ref and resolved spec source; returns Spec-axis findings table with `OVERALL` line.\n     Inject the pinned ref (step 1), spec source (step 2), standards source (step 3) into each call; do not paraphrase severity definitions or the Fowler list.\n     完成判据: both agents return findings tables (including no-finding results) with the exact `OVERALL` line.\n\n5. **Aggregate side-by-side** — Merge the two findings tables into a single side-by-side report (no cross-axis reranking, no combining severities). Preserve file:line evidence and the per-axis `OVERALL` lines. Count unresolved findings per axis.\n   完成判据: side-by-side aggregation table produced, per-axis counts recorded.\n\n6. **Severity gate** — Apply the severity gate from `code-review-protocol` §4:\n   - Unresolved High (either axis) → **BLOCKED**; do **not** patch in this skill. Emit the next-slot line `NEXT: review-report-repair` and pass the aggregation table as the report (in-session is enough).\n   - Medium (without a named follow-up ticket) → advisory; do not auto-invoke repair.\n   - Low → informational only.\n     Final verdict line: `GATE: PASS` or `GATE: BLOCKED: \u003CN> High unresolved`.\n     完成判据: gate verdict emitted (PASS or BLOCKED: N High); BLOCKED includes the NEXT line; this skill does not edit product code.\n\n## Review-stage placement\n\nDocumented sequence (current slot only):\n\n- Before change: `architecture-change-reviewer` gates the plan (5-verdict).\n- After change: this skill (Standards + Spec via two parallel sub-agents).\n- This skill `GATE: BLOCKED`: next slot `review-report-repair`.\n- This skill `GATE: PASS`: this skill ends; landing claim is `verification-before-completion`.\n\nThis skill is conditional: trigger only when the ticket produced a code diff; do not run on docs\u002Fconfig-only changes.\n\n## Acceptance Criteria\n\n- [ ] The pinned diff ref (base + HEAD) is explicit and reproducible.\n- [ ] Spec source resolved via the 4-level priority, or level-4 blocker reported back.\n- [ ] Standards source references `code-review-protocol` §2.2 and §4 by pointer only (no duplicated Fowler list).\n- [ ] Both `standards-reviewer-agent` and `spec-reviewer-agent` were dispatched in parallel and returned findings tables with `OVERALL` lines.\n- [ ] Findings from both axes are presented side-by-side without cross-axis reranking.\n- [ ] Every finding includes severity, file:line, axis, problem, and remediation.\n- [ ] Severity gate verdict is emitted (`GATE: PASS` or `GATE: BLOCKED: N High`). BLOCKED includes `NEXT: review-report-repair` and does not patch.\n\n## Verification\n\nSkill type: technique\nBar level: minimum\n\n- Confirm the frontmatter omits `disable-model-invocation`, keeping the skill model-invoked.\n- Confirm `bucket: engineering` is preserved.\n- Confirm the description states a conditional trigger (\"when a ticket produces a code diff\") and no longer references the upstream CLI wrapper.\n- Confirm no inline CLI command, executable build, or binary path appears in the body.\n- Confirm the Fowler 12 smell list is referenced by pointer (protocol §2.2), not duplicated in body.\n- Confirm this skill does not implement fixes (repair is `review-report-repair`).\n",{"name":5,"type":23,"bucket":24,"description":7},"technique","engineering","master","1a067ffc9024631d22ca8bf2b47ad81369f28056","arthurpower\u002Fskills\u002Fcode-review",0,"https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower","https:\u002F\u002Fgithub.com\u002Fwinter6205","2026-10-28 23:46:38",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add winter6205\u002Farthurpower --skill code-review",{"tool":38,"command":39},"bunx","bunx skills add winter6205\u002Farthurpower --skill code-review",{"tool":41,"command":42},"pnpm","pnpm dlx skills add winter6205\u002Farthurpower --skill code-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fcode-review\u002FSKILL.md",true,[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fprotocol.md","REFERENCE","参考文档",5859,"https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fcode-review\u002Freferences\u002Fprotocol.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fspec-as-test.md",1062,"https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fcode-review\u002Freferences\u002Fspec-as-test.md",[57,64,71,78,85,92],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":18},"01M7EFDX3VT33HSHDA17T9N9JJ","writing-plans","Use when turning a buildable spec into ordered tracer bullets after architecture-change-reviewer. Covers vertical slicing, dependency order, and headroom for the implementer. Triggers on 写计划, 拆任务, 任务分解, 制定方案, 跨文件改动, 计划.","https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M7EFDQV6SGJWDK634DWPFR35","wayfinder","Use when a chunk of work is more than one agent session can hold — plan it as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M7EFDM9Y55GKYFGY96088BYB","verification-before-completion","This skill should be used when claiming \"完成\" \u002F \"done\" \u002F \"fixed\" \u002F \"passing\" \u002F \"ready to ship\", before trusting a subagent success report, or when checking \"对照计划\" \u002F \"对照 spec\" — whether this run's delivery matches its basis.","https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M7EFDFCY4V0JMQHSEE34A2JS","using-agent-skills","Use when starting a new session, switching tasks, or unsure which arthurpower skill applies. Routes incoming work to the matching skill via flowchart before invoking. Activates on phrases like \"which skill should I use\", \"skill check\", \"pre-task skill check\", \"how to start\", \"router\", \"skill routing\", or when multiple competing skills could apply. Does not auto-invoke user-invoked authoring skills (skill-authoring, self-evolving-rules).","https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fusing-agent-skills\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M7EFDB70ATNQASXP4BKDYGA6","test-driven-development","Use when implementing logic, fixing a bug, or changing behavior — write the failing test first (RED), then minimal code (GREEN), then refactor. Triggers on \"write the failing test first\", \"Prove-It\", or a bug that needs a reproduction test before the fix.","https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":18},"01M7EFD6NPWFG5WSXT0DF07XH1","systematic-debugging","Use when debugging a test failure, build break, unexpected runtime error, flaky test, or hanging process. Triggers on phrases like \"fix this bug\", \"getting an error\", \"failing test\", \"flaky\", \"hanging\", \"halfway through debugging\", \"this used to work\", \"intermittent failure\", \"stack trace shows X\", or any case where behavior does not match expectations. Prevents shotgun debugging.","https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]