[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AFJHVYYGFG64PH4EQ8DBMS":3,"skill-same:01M7AFJHVYYGFG64PH4EQ8DBMS":48},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M7AFJHVYYGFG64PH4EQ8DBMS","trove-review",null,"Code review skill that checks for common issues, security vulnerabilities, and style violations. Use when reviewing code changes or PRs.","bravew\u002Ftrove","bravew","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10855844?v=4","01M7ACJ91JZSQYHT81XPVYR7VA","Yong","01M7AFERNR92HDPGNGP5QA16DM",10,"MIT","https:\u002F\u002Fgithub.com\u002Fbravew\u002Ftrove\u002Fblob\u002Fmain\u002Fplugins\u002Ftrove-dev\u002F.agents\u002Fskills\u002Ftrove-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: trove-review\ndescription: \"Code review skill that checks for common issues, security vulnerabilities, and style violations. Use when reviewing code changes or PRs.\"\nmetadata:\n  trove-category: pull-requests\n  trove-category-label: \"Pull requests\"\n---\n\u003C!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->\n\u003C!-- Regenerate: bun run build:skills -->\n\n## Session Init\n\nThis skill ships Trove conventions. Prefer existing project patterns over generic best practices when they conflict.\n\n# Code Review Guidelines\n\n## Review Checklist\n\nWhen reviewing code, check for these categories in order:\n\nIf a PRP or implementation plan drove the change, read it first and review\nagainst its requirements. With no explicit scope, review staged changes; with a\nPR number, inspect the PR metadata and files; with paths, read those files in\nfull before judging.\n\n### 1. Correctness\n- Does the code do what it claims to do?\n- Are edge cases handled (null, empty, boundary values)?\n- Are error paths handled correctly?\n\n### 2. Security\n- No hardcoded secrets, API keys, or credentials\n- Input validation on all external data\n- SQL injection prevention (parameterized queries)\n- XSS prevention (proper escaping\u002Fsanitization)\n- Authentication\u002Fauthorization checks in place\n\n### 3. Performance\n- No N+1 queries\n- Appropriate use of caching\n- No unnecessary re-renders (React) or re-computations\n- Pagination for large datasets\n\n### 4. Maintainability\n- Clear naming (variables, functions, files)\n- Reasonable function length (under 50 lines preferred)\n- No code duplication\n- Appropriate abstraction level\n\n### 5. Testing\n- Tests cover the happy path\n- Tests cover error\u002Fedge cases\n- Mocks are used appropriately\n- Test names describe the behavior being tested\n\n### 6. Reader load\n- **Layers to trace** — flag one-caller wrappers and indirection that exists only to forward a call; collapse them.\n- **State to hold** — flag mutable scope wider than it needs to be.\n- The \u003C30s test: can a new reader answer \"where does X come from?\" and \"what can change X?\" without spelunking? If not, say where it breaks.\n\n## Deep mode (adversarial, optional)\n\nOn request (\"tear this apart\", \"stress test\", \"find blind spots\") or for sensitive surfaces, run a deeper pass: review the change through several independent lenses (correctness, security, failure modes, maintainability), optionally via read-only sub-agents on disjoint concerns. State the change's intent first so the review challenges the execution, not the goal. Synthesize one verdict and sort every finding into **Act on \u002F Consider \u002F Noted \u002F Dismissed**. Do not silently rewrite the diff — the deliverable is the verdict. For a true multi-model cloud review, point the user at `\u002Fcode-review ultra`.\n\n## Delegated exploration\n\nWhen the diff is wide enough that linear reading is wasteful, dispatch\nread-only sub-agents in parallel for **bounded** investigation. Examples\nof good delegations:\n\n- \"Map every callsite of the modified function in `services\u002F`. Return file:line.\"\n- \"Verify whether the new validation path is reachable from the public API\n  surface. Read-only. Yes\u002Fno plus one cite.\"\n- \"Check the test files touched in this diff for missing edge-case\n  coverage (empty input, boundary values). Return findings or 'no gaps'.\"\n\nEach delegation should declare scope, expected output shape, and a depth\nbudget. Don't delegate \"review the whole diff\" — that's the parent's job.\nAnti-patterns and host-specific examples are in\n[docs\u002Forchestration.md](..\u002F..\u002Fdocs\u002Forchestration.md).\n\nFor sensitive surfaces (auth, payments, secret handling, untrusted input),\nalso run `trove-security-review` and `trove-secret-scan` — those are this\nskill's `benefits-from`.\n\n## Review Output Format\n\nStructure your review as:\n\n```markdown\n## Summary\nOne-paragraph overview of the changes.\n\n## Issues Found\n### 🔴 Critical (must fix)\n- [file:line] Description\n\n### 🟡 Important (should fix)\n- [file:line] Description\n\n### 🔵 Suggestion (nice to have)\n- [file:line] Description\n\n## Positive Observations\n- Things done well worth calling out\n```\n","\u003C!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->\n\u003C!-- Regenerate: bun run build:skills -->\n\n## Session Init\n\nThis skill ships Trove conventions. Prefer existing project patterns over generic best practices when they conflict.\n\n# Code Review Guidelines\n\n## Review Checklist\n\nWhen reviewing code, check for these categories in order:\n\nIf a PRP or implementation plan drove the change, read it first and review\nagainst its requirements. With no explicit scope, review staged changes; with a\nPR number, inspect the PR metadata and files; with paths, read those files in\nfull before judging.\n\n### 1. Correctness\n- Does the code do what it claims to do?\n- Are edge cases handled (null, empty, boundary values)?\n- Are error paths handled correctly?\n\n### 2. Security\n- No hardcoded secrets, API keys, or credentials\n- Input validation on all external data\n- SQL injection prevention (parameterized queries)\n- XSS prevention (proper escaping\u002Fsanitization)\n- Authentication\u002Fauthorization checks in place\n\n### 3. Performance\n- No N+1 queries\n- Appropriate use of caching\n- No unnecessary re-renders (React) or re-computations\n- Pagination for large datasets\n\n### 4. Maintainability\n- Clear naming (variables, functions, files)\n- Reasonable function length (under 50 lines preferred)\n- No code duplication\n- Appropriate abstraction level\n\n### 5. Testing\n- Tests cover the happy path\n- Tests cover error\u002Fedge cases\n- Mocks are used appropriately\n- Test names describe the behavior being tested\n\n### 6. Reader load\n- **Layers to trace** — flag one-caller wrappers and indirection that exists only to forward a call; collapse them.\n- **State to hold** — flag mutable scope wider than it needs to be.\n- The \u003C30s test: can a new reader answer \"where does X come from?\" and \"what can change X?\" without spelunking? If not, say where it breaks.\n\n## Deep mode (adversarial, optional)\n\nOn request (\"tear this apart\", \"stress test\", \"find blind spots\") or for sensitive surfaces, run a deeper pass: review the change through several independent lenses (correctness, security, failure modes, maintainability), optionally via read-only sub-agents on disjoint concerns. State the change's intent first so the review challenges the execution, not the goal. Synthesize one verdict and sort every finding into **Act on \u002F Consider \u002F Noted \u002F Dismissed**. Do not silently rewrite the diff — the deliverable is the verdict. For a true multi-model cloud review, point the user at `\u002Fcode-review ultra`.\n\n## Delegated exploration\n\nWhen the diff is wide enough that linear reading is wasteful, dispatch\nread-only sub-agents in parallel for **bounded** investigation. Examples\nof good delegations:\n\n- \"Map every callsite of the modified function in `services\u002F`. Return file:line.\"\n- \"Verify whether the new validation path is reachable from the public API\n  surface. Read-only. Yes\u002Fno plus one cite.\"\n- \"Check the test files touched in this diff for missing edge-case\n  coverage (empty input, boundary values). Return findings or 'no gaps'.\"\n\nEach delegation should declare scope, expected output shape, and a depth\nbudget. Don't delegate \"review the whole diff\" — that's the parent's job.\nAnti-patterns and host-specific examples are in\n[docs\u002Forchestration.md](..\u002F..\u002Fdocs\u002Forchestration.md).\n\nFor sensitive surfaces (auth, payments, secret handling, untrusted input),\nalso run `trove-security-review` and `trove-secret-scan` — those are this\nskill's `benefits-from`.\n\n## Review Output Format\n\nStructure your review as:\n\n```markdown\n## Summary\nOne-paragraph overview of the changes.\n\n## Issues Found\n### 🔴 Critical (must fix)\n- [file:line] Description\n\n### 🟡 Important (should fix)\n- [file:line] Description\n\n### 🔵 Suggestion (nice to have)\n- [file:line] Description\n\n## Positive Observations\n- Things done well worth calling out\n```\n",{"name":5,"metadata":24,"description":7},{"trove-category":25,"trove-category-label":26},"pull-requests","Pull requests","main","f88db1f1cf0e0703dd962051ebc142db961d7799","plugins\u002Ftrove-dev\u002F.agents\u002Fskills\u002Ftrove-review",1,"https:\u002F\u002Fgithub.com\u002Fbravew\u002Ftrove","https:\u002F\u002Fgithub.com\u002Fbravew","2026-11-12 07:56:32",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add bravew\u002Ftrove --skill trove-review",{"tool":40,"command":41},"bunx","bunx skills add bravew\u002Ftrove --skill trove-review",{"tool":43,"command":44},"pnpm","pnpm dlx skills add bravew\u002Ftrove --skill trove-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbravew\u002Ftrove\u002Fblob\u002Fmain\u002Fplugins\u002Ftrove-dev\u002F.agents\u002Fskills\u002Ftrove-review\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7AGJDHTQAS1VK6P7VJAV79G","using-trove","Skill discipline anchor for the Trove marketplace. Loaded once per session; routes the agent to the right trove-* skill before code, planning, review, or git actions.","https:\u002F\u002Fgithub.com\u002Fbravew\u002Ftrove\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\u002Fusing-trove\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7AGJAS4V4TXE6TV6F839BGZ","trove-write-skill","Skill authoring workflow. Use when creating or updating a Codex or Trove skill, including rubrics, tasks, metadata, and validation.","https:\u002F\u002Fgithub.com\u002Fbravew\u002Ftrove\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\u002Ftrove-write-skill\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7AGJ87K41ZAC8DDBAV17QFW","trove-worktree","Git worktree workflow for spikes, risky experiments, and broad refactors that should not disturb the user's current branch.","https:\u002F\u002Fgithub.com\u002Fbravew\u002Ftrove\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\u002Ftrove-worktree\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7AGJ32V58VYBFYMS9EMHRY4","trove-why","Reconstruct design rationale and decision history from evidence — source control, issue tracker (Linear), docs (Notion), chat (Slack), error tracking (Sentry) — with calibrated confidence. Use for \"why does X work this way\", \"why did we pick Y\", regressions, and postmortems. Use trove-explain for how it works now.","https:\u002F\u002Fgithub.com\u002Fbravew\u002Ftrove\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\u002Ftrove-why\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7AGJ0FHJSRR8MMXC3V8XNHF","trove-verify","Completion verification workflow. Use before claiming done, fixed, complete, ready, or shipped.","https:\u002F\u002Fgithub.com\u002Fbravew\u002Ftrove\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\u002Ftrove-verify\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7AGHWV4B9SDS60RH5W0B0K5","trove-unslop","Cut AI tells from writing — PR descriptions, release notes, specs, commit bodies, and replies. Use before finalizing prose, or when the user asks to clean up, de-slop, or make text sound human.","https:\u002F\u002Fgithub.com\u002Fbravew\u002Ftrove\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\u002Ftrove-unslop\u002FSKILL.md",[],[]]