[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MP85NQZJQ3D99KP0K73Q7V":3,"skill-same:01M6MP85NQZJQ3D99KP0K73Q7V":67},{"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":28,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":48,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M6MP85NQZJQ3D99KP0K73Q7V","code-review",null,"Use after completing implementation steps and before merging — reviews against plan and HOTL contracts.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fyimwoo\u002Fhotl-plugin\u002Fskills\u002Fcode-review\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37],"code review","review","code","plan","use","implementation","contracts","reviews","hotl","2026-11-10 10:12:30",false,"---\nname: code-review\ndescription: Use after completing implementation steps and before merging — reviews against plan and HOTL contracts.\n---\n\n# HOTL Code Review\n\nUser-facing entry point for getting a code review. Dispatches the full `code-reviewer` agent by default; falls back to inline review when subagents aren't available.\n\n## Process\n\n### 1. Gather Context\n\n**Resolve base branch** (fallback ladder — use the first that succeeds):\n\n1. PR base branch: `gh pr view --json baseRefName`\n2. Repo default branch: `git symbolic-ref refs\u002Fremotes\u002Forigin\u002FHEAD`\n3. `main`\n4. `master`\n\n**Resolve review scope:**\n\n- Feature branch: committed branch diff against base (`base...HEAD`), plus staged and unstaged local changes when present\n- On base branch with staged changes: staged diff\n- On base branch with unstaged changes: working tree diff\n- On clean base branch: `HEAD~1..HEAD`\n- Ambiguous (detached HEAD, no commits beyond base, no local changes): ask the user\n\n**Detect workflow file:**\n\n- First, glob for canonical workflows in `docs\u002Fplans\u002F*-workflow.md`\n- If one canonical match: use it\n- If multiple canonical matches: prefer the most recently modified canonical workflow, unless the user named one\n- If no canonical matches: glob for legacy `hotl-workflow-*.md` in project root\n- If one legacy match: use it\n- If multiple legacy matches: prefer the most recently modified legacy workflow, unless the user named one\n- If no matches: proceed without workflow context\n\n**Extract contracts** from workflow frontmatter if available (intent, constraints, success_criteria, risk_level).\n\n**Gather verification evidence:**\n\n- Primary (deterministic): `.hotl\u002Fstate\u002F*.json` and `.hotl\u002Freports\u002F*.md` — most recent artifacts if present\n- Best-effort: recent test\u002Flint output if discoverable; if unavailable, report \"not available\"\n\n### 2. Dispatch Review\n\n**If subagents are available (Claude Code, Codex):**\n\nDispatch the `code-reviewer` role as a subagent via the Agent tool. Use the structured dispatch template from `requesting-code-review`:\n\n- Review type: `direct`\n- Git range: resolved scope from step 1\n- Workflow and contracts: if available\n- Verification evidence: if available\n\n**If subagents are not available (Cline, weaker runtimes):**\n\nRun inline review in the current session using the same output contract. See \"Inline Fallback\" below.\n\n### 3. Return Findings\n\n- Present the review output (findings + verdict) to the user\n- **Do NOT** automatically invoke `receiving-code-review`\n- **Do NOT** automatically implement fixes\n- If the user asks to fix the findings (\"fix them\", \"address these\", \"implement the fixes\"): then invoke `receiving-code-review`\n\n## Verdict Model\n\nDirect reviews use the final-review verdict model:\n\n- **READY** — safe to merge\n- **READY WITH WARNINGS** — safe to merge but warnings should be addressed soon\n- **NOT READY** — blocking issues must be resolved before merge\n\n## Review Lifecycle\n\n```\ncode-review              = user-facing entry point for getting a review\nrequesting-code-review   = internal executor\u002Forchestration entry point\nreceiving-code-review    = follow-up handler for acting on findings\n```\n\n## Output Contract\n\nBoth dispatched and inline reviews must conform to `docs\u002Fcontracts\u002Fcode-review-output.md`. Every review must contain these 6 sections in order: Scope (with verification evidence), Reviewed Dimensions, Findings, What Was Not Covered, Residual Risks, Verdict.\n\n### Platform-Native Annotation Dedup\n\nWhen the platform emits platform-native annotations for localized findings (e.g., `::code-comment` in Codex, inline GitHub review comments), do not restate those findings verbatim in the Findings section. Instead, use the grouped one-liner format defined in the output contract.\n\n## Inline Fallback\n\nWhen subagents are not available, run the review inline using the same output contract. The inline review must produce identical 6-section structure — not a weaker format.\n\n### Dimensions\n\n**Plan alignment** (when workflow provided):\n- All steps in the workflow file completed\n- success_criteria from frontmatter met\n- No unplanned scope added (YAGNI)\n\nWhen no workflow: state \"Plan alignment: skipped (no workflow provided)\"\n\n**Code quality and design:**\n- Tests exist and pass for all new behavior\n- No code duplication introduced (DRY)\n- Error handling at system boundaries only\n- Reference `docs\u002Fchecklists\u002Farchitecture-and-design.md` for SOLID and architecture smell heuristics. If the checklist file is not available, continue with best-effort review.\n\n**Security and reliability:**\n- Reference `docs\u002Fchecklists\u002Fsecurity-and-reliability.md` for expanded security heuristics.\n- Check for injection, auth gaps, race conditions, secret leakage, unsafe patterns.\n- If the checklist file is not available, continue with best-effort review.\n\n**Performance and boundary conditions:**\n- Reference `docs\u002Fchecklists\u002Fperformance-and-boundary-conditions.md` for performance and boundary condition heuristics.\n- Check for N+1 queries, unbounded memory, off-by-one, null handling, swallowed exceptions.\n- If the checklist file is not available, continue with best-effort review.\n\n**Removal and simplification:**\n- Reference `docs\u002Fchecklists\u002Fremoval-and-simplification.md` for dead code and simplification heuristics.\n- Flag unused exports, dead branches, feature-flagged-off code. Classify as safe-delete-now or defer-with-plan.\n- If the checklist file is not available, continue with best-effort review.\n\n**HOTL governance:**\n- risk_level: high steps had human gate approval\n- No sensitive data (secrets, PII) in code, logs, or comments\n- Security-sensitive paths (auth, encryption) have human review documented\n\n### Findings Format\n\nEvery finding must include:\n\n```\n- [SEVERITY]: file\u002Fpath:line — description\n  Why: [why this matters]\n  Fix: [expected remediation direction]\n```\n\nFor localized issues: file:line is required. For scope-level findings: provide the narrowest evidence available.\n\n### Severity Levels\n\n- **BLOCK:** Must fix before merge (failing tests, security issues, missing gates on high-risk steps)\n- **WARN:** Should fix soon (code quality, missing docs for public APIs)\n- **NOTE:** Consider in future (style, minor improvements)\n\nBLOCK issues must be resolved before claiming done.\n\n### Clean Review\n\nPer the output contract, when a dimension has no findings it must still state what was checked, what was not covered, and residual risks. Additionally, the review must always include sections 4 (What Was Not Covered) and 5 (Residual Risks) even when no individual dimension has findings.\n","# HOTL Code Review\n\nUser-facing entry point for getting a code review. Dispatches the full `code-reviewer` agent by default; falls back to inline review when subagents aren't available.\n\n## Process\n\n### 1. Gather Context\n\n**Resolve base branch** (fallback ladder — use the first that succeeds):\n\n1. PR base branch: `gh pr view --json baseRefName`\n2. Repo default branch: `git symbolic-ref refs\u002Fremotes\u002Forigin\u002FHEAD`\n3. `main`\n4. `master`\n\n**Resolve review scope:**\n\n- Feature branch: committed branch diff against base (`base...HEAD`), plus staged and unstaged local changes when present\n- On base branch with staged changes: staged diff\n- On base branch with unstaged changes: working tree diff\n- On clean base branch: `HEAD~1..HEAD`\n- Ambiguous (detached HEAD, no commits beyond base, no local changes): ask the user\n\n**Detect workflow file:**\n\n- First, glob for canonical workflows in `docs\u002Fplans\u002F*-workflow.md`\n- If one canonical match: use it\n- If multiple canonical matches: prefer the most recently modified canonical workflow, unless the user named one\n- If no canonical matches: glob for legacy `hotl-workflow-*.md` in project root\n- If one legacy match: use it\n- If multiple legacy matches: prefer the most recently modified legacy workflow, unless the user named one\n- If no matches: proceed without workflow context\n\n**Extract contracts** from workflow frontmatter if available (intent, constraints, success_criteria, risk_level).\n\n**Gather verification evidence:**\n\n- Primary (deterministic): `.hotl\u002Fstate\u002F*.json` and `.hotl\u002Freports\u002F*.md` — most recent artifacts if present\n- Best-effort: recent test\u002Flint output if discoverable; if unavailable, report \"not available\"\n\n### 2. Dispatch Review\n\n**If subagents are available (Claude Code, Codex):**\n\nDispatch the `code-reviewer` role as a subagent via the Agent tool. Use the structured dispatch template from `requesting-code-review`:\n\n- Review type: `direct`\n- Git range: resolved scope from step 1\n- Workflow and contracts: if available\n- Verification evidence: if available\n\n**If subagents are not available (Cline, weaker runtimes):**\n\nRun inline review in the current session using the same output contract. See \"Inline Fallback\" below.\n\n### 3. Return Findings\n\n- Present the review output (findings + verdict) to the user\n- **Do NOT** automatically invoke `receiving-code-review`\n- **Do NOT** automatically implement fixes\n- If the user asks to fix the findings (\"fix them\", \"address these\", \"implement the fixes\"): then invoke `receiving-code-review`\n\n## Verdict Model\n\nDirect reviews use the final-review verdict model:\n\n- **READY** — safe to merge\n- **READY WITH WARNINGS** — safe to merge but warnings should be addressed soon\n- **NOT READY** — blocking issues must be resolved before merge\n\n## Review Lifecycle\n\n```\ncode-review              = user-facing entry point for getting a review\nrequesting-code-review   = internal executor\u002Forchestration entry point\nreceiving-code-review    = follow-up handler for acting on findings\n```\n\n## Output Contract\n\nBoth dispatched and inline reviews must conform to `docs\u002Fcontracts\u002Fcode-review-output.md`. Every review must contain these 6 sections in order: Scope (with verification evidence), Reviewed Dimensions, Findings, What Was Not Covered, Residual Risks, Verdict.\n\n### Platform-Native Annotation Dedup\n\nWhen the platform emits platform-native annotations for localized findings (e.g., `::code-comment` in Codex, inline GitHub review comments), do not restate those findings verbatim in the Findings section. Instead, use the grouped one-liner format defined in the output contract.\n\n## Inline Fallback\n\nWhen subagents are not available, run the review inline using the same output contract. The inline review must produce identical 6-section structure — not a weaker format.\n\n### Dimensions\n\n**Plan alignment** (when workflow provided):\n- All steps in the workflow file completed\n- success_criteria from frontmatter met\n- No unplanned scope added (YAGNI)\n\nWhen no workflow: state \"Plan alignment: skipped (no workflow provided)\"\n\n**Code quality and design:**\n- Tests exist and pass for all new behavior\n- No code duplication introduced (DRY)\n- Error handling at system boundaries only\n- Reference `docs\u002Fchecklists\u002Farchitecture-and-design.md` for SOLID and architecture smell heuristics. If the checklist file is not available, continue with best-effort review.\n\n**Security and reliability:**\n- Reference `docs\u002Fchecklists\u002Fsecurity-and-reliability.md` for expanded security heuristics.\n- Check for injection, auth gaps, race conditions, secret leakage, unsafe patterns.\n- If the checklist file is not available, continue with best-effort review.\n\n**Performance and boundary conditions:**\n- Reference `docs\u002Fchecklists\u002Fperformance-and-boundary-conditions.md` for performance and boundary condition heuristics.\n- Check for N+1 queries, unbounded memory, off-by-one, null handling, swallowed exceptions.\n- If the checklist file is not available, continue with best-effort review.\n\n**Removal and simplification:**\n- Reference `docs\u002Fchecklists\u002Fremoval-and-simplification.md` for dead code and simplification heuristics.\n- Flag unused exports, dead branches, feature-flagged-off code. Classify as safe-delete-now or defer-with-plan.\n- If the checklist file is not available, continue with best-effort review.\n\n**HOTL governance:**\n- risk_level: high steps had human gate approval\n- No sensitive data (secrets, PII) in code, logs, or comments\n- Security-sensitive paths (auth, encryption) have human review documented\n\n### Findings Format\n\nEvery finding must include:\n\n```\n- [SEVERITY]: file\u002Fpath:line — description\n  Why: [why this matters]\n  Fix: [expected remediation direction]\n```\n\nFor localized issues: file:line is required. For scope-level findings: provide the narrowest evidence available.\n\n### Severity Levels\n\n- **BLOCK:** Must fix before merge (failing tests, security issues, missing gates on high-risk steps)\n- **WARN:** Should fix soon (code quality, missing docs for public APIs)\n- **NOTE:** Consider in future (style, minor improvements)\n\nBLOCK issues must be resolved before claiming done.\n\n### Clean Review\n\nPer the output contract, when a dimension has no findings it must still state what was checked, what was not covered, and residual risks. Additionally, the review must always include sections 4 (What Was Not Covered) and 5 (Residual Risks) even when no individual dimension has findings.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fyimwoo\u002Fhotl-plugin\u002Fskills\u002Fcode-review",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill code-review",{"tool":59,"command":60},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill code-review",{"tool":62,"command":63},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill code-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fyimwoo\u002Fhotl-plugin\u002Fskills\u002Fcode-review\u002FSKILL.md",true,[],[68,78,86,94,102,110],{"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":72,"licenseFileUrl":73,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":77},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":82,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":77},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":77},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":98,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":77},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":106,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":77},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":114,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":77},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]