[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AGCV5FXG2VG4SFWWYAAFTK":3,"skill-same:01M7AGCV5FXG2VG4SFWWYAAFTK":77},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":29,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7AGCV5FXG2VG4SFWWYAAFTK","ck:code-review",null,"Review code quality, receive feedback with technical rigor, verify completion claims. Use before PRs, after implementing features, when claiming task completion. Includes scout-based edge case detection and native Task pipeline orchestration.","manhvann\u002Fcodexkit","manhvann","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F108862213?v=4","01M7AGBGXSB8Z8HXXR27QKX035","Manh Nguyen Van","01M7AGBGYDJPBR2EYEWJ0G1K8J",88,"MIT","https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcode-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ck:code-review\ndescription: \"Review code quality, receive feedback with technical rigor, verify completion claims. Use before PRs, after implementing features, when claiming task completion. Includes scout-based edge case detection and native Task pipeline orchestration.\"\nargument-hint: \"[context] OR codebase [parallel]\"\n---\n\n# Code Review\n\nGuide proper code review practices emphasizing technical rigor, evidence-based claims, and verification over performative responses.\n\n## Default (No Arguments)\n\nIf invoked with context (recent changes\u002FPR), proceed with review. If invoked WITHOUT arguments, ask the user to choose available review operations:\n\n| Operation | Description |\n|-----------|-------------|\n| `(default)` | Review recent changes\u002FPR |\n| `codebase` | Full codebase scan & analysis |\n| `codebase parallel` | Parallel multi-reviewer audit |\n\nPresent options with header \"Review Operation\", question \"What would you like to do?\".\n\n## Core Principle\n\n**YAGNI**, **KISS**, **DRY** always. Technical correctness over social comfort.\n**Be honest, be brutal, straight to the point, and be concise.**\n\nVerify before implementing. Ask before assuming. Evidence before claims.\n\n## Practices\n\n| Practice | When | Reference |\n|----------|------|-----------|\n| Receiving feedback | Unclear feedback, external reviewers, needs prioritization | `references\u002Fcode-review-reception.md` |\n| Requesting review | After tasks, before merge, stuck on problem | `references\u002Frequesting-code-review.md` |\n| Verification gates | Before any completion claim, commit, PR | `references\u002Fverification-before-completion.md` |\n| Edge case scouting | After implementation, before review | `references\u002Fedge-case-scouting.md` |\n| **Task-managed reviews** | Multi-file features (3+ files), parallel reviewers, fix cycles | `references\u002Ftask-management-reviews.md` |\n\n## Quick Decision Tree\n\n```\nSITUATION?\n│\n├─ Received feedback → STOP if unclear, verify if external, implement if human partner\n├─ Completed work → Scout edge cases → Request code_reviewer subagent\n├─ Multi-file feature (3+ files) → Create review pipeline tasks (scout→review→fix→verify)\n└─ About to claim status → RUN verification command FIRST\n```\n\n## Receiving Feedback\n\n**Pattern:** READ → UNDERSTAND → VERIFY → EVALUATE → RESPOND → IMPLEMENT\n\n**Rules:**\n- No performative agreement: \"You're absolutely right!\", \"Great point!\"\n- No implementation before verification\n- Restate, ask questions, push back with reasoning, or just work\n- YAGNI check: grep for usage before implementing \"proper\" features\n\n**Source handling:**\n- Human partner: Trusted - implement after understanding\n- External reviewers: Verify technically, check breakage, push back if wrong\n\n**Full protocol:** `references\u002Fcode-review-reception.md`\n\n## Requesting Review\n\n**When:** After each task, major features, before merge\n\n**Process:**\n1. **Scout edge cases first** (see below)\n2. Get SHAs: `BASE_SHA=$(git rev-parse HEAD~1)` and `HEAD_SHA=$(git rev-parse HEAD)`\n3. Dispatch code_reviewer subagent with: WHAT, PLAN, BASE_SHA, HEAD_SHA, DESCRIPTION\n4. Fix Critical immediately, Important before proceeding\n\n**Full protocol:** `references\u002Frequesting-code-review.md`\n\n## Edge Case Scouting\n\n**When:** After implementation, before requesting code_reviewer\n\n**Process:**\n1. Invoke `$scout` with edge-case-focused prompt\n2. Scout analyzes: affected files, data flows, error paths, boundary conditions\n3. Review scout findings for potential issues\n4. Address critical gaps before code review\n\n**Full protocol:** `references\u002Fedge-case-scouting.md`\n\n## Task-Managed Review Pipeline\n\n**When:** Multi-file features (3+ changed files), parallel code_reviewer scopes, review cycles with Critical fix iterations.\n\n**Pipeline:** scout → review → fix → verify (each a Task with dependency chain)\n\n```\ntracked task creation: \"Scout edge cases\"         → pending\ntracked task creation: \"Review implementation\"    → pending, blockedBy: [scout]\ntracked task creation: \"Fix critical issues\"      → pending, blockedBy: [review]\ntracked task creation: \"Verify fixes pass\"        → pending, blockedBy: [fix]\n```\n\n**Parallel reviews:** Spawn scoped code_reviewer subagents for independent file groups (e.g., backend + frontend). Fix task blocks on all reviewers completing.\n\n**Re-review cycles:** If fixes introduce new issues, create cycle-2 review task. Limit 3 cycles, escalate to user after.\n\n**Full protocol:** `references\u002Ftask-management-reviews.md`\n\n## Verification Gates\n\n**Iron Law:** NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE\n\n**Gate:** IDENTIFY command → RUN full → READ output → VERIFY confirms → THEN claim\n\n**Requirements:**\n- Tests pass: Output shows 0 failures\n- Build succeeds: Exit 0\n- Bug fixed: Original symptom passes\n- Requirements met: Checklist verified\n\n**Red Flags:** \"should\"\u002F\"probably\"\u002F\"seems to\", satisfaction before verification, trusting agent reports\n\n**Full protocol:** `references\u002Fverification-before-completion.md`\n\n## Integration with Workflows\n\n- **Subagent-Driven:** Scout edge cases → Review after EACH task → Verify before next\n- **Pull Requests:** Scout → Verify tests → Code-reviewer review → Merge\n- **Task Pipeline:** Create review tasks with dependencies → auto-unblock through chain\n- **Cook Handoff:** Cook completes phase → review pipeline tasks → all complete → cook proceeds\n\n## Codebase Analysis Subcommands\n\n| Subcommand | Reference | Purpose |\n|------------|-----------|---------|\n| `$code-review codebase` | `references\u002Fcodebase-scan-workflow.md` | Scan & analyze the codebase |\n| `$code-review codebase parallel` | `references\u002Fparallel-review-workflow.md` | Ultrathink edge cases, then parallel verify |\n\n## Bottom Line\n\n1. Technical rigor over social performance\n2. Scout edge cases before review\n3. Task-manage reviews for multi-file features\n4. Evidence before claims\n\nVerify. Scout. Question. Then implement. Evidence. Then claim.\n","# Code Review\n\nGuide proper code review practices emphasizing technical rigor, evidence-based claims, and verification over performative responses.\n\n## Default (No Arguments)\n\nIf invoked with context (recent changes\u002FPR), proceed with review. If invoked WITHOUT arguments, ask the user to choose available review operations:\n\n| Operation | Description |\n|-----------|-------------|\n| `(default)` | Review recent changes\u002FPR |\n| `codebase` | Full codebase scan & analysis |\n| `codebase parallel` | Parallel multi-reviewer audit |\n\nPresent options with header \"Review Operation\", question \"What would you like to do?\".\n\n## Core Principle\n\n**YAGNI**, **KISS**, **DRY** always. Technical correctness over social comfort.\n**Be honest, be brutal, straight to the point, and be concise.**\n\nVerify before implementing. Ask before assuming. Evidence before claims.\n\n## Practices\n\n| Practice | When | Reference |\n|----------|------|-----------|\n| Receiving feedback | Unclear feedback, external reviewers, needs prioritization | `references\u002Fcode-review-reception.md` |\n| Requesting review | After tasks, before merge, stuck on problem | `references\u002Frequesting-code-review.md` |\n| Verification gates | Before any completion claim, commit, PR | `references\u002Fverification-before-completion.md` |\n| Edge case scouting | After implementation, before review | `references\u002Fedge-case-scouting.md` |\n| **Task-managed reviews** | Multi-file features (3+ files), parallel reviewers, fix cycles | `references\u002Ftask-management-reviews.md` |\n\n## Quick Decision Tree\n\n```\nSITUATION?\n│\n├─ Received feedback → STOP if unclear, verify if external, implement if human partner\n├─ Completed work → Scout edge cases → Request code_reviewer subagent\n├─ Multi-file feature (3+ files) → Create review pipeline tasks (scout→review→fix→verify)\n└─ About to claim status → RUN verification command FIRST\n```\n\n## Receiving Feedback\n\n**Pattern:** READ → UNDERSTAND → VERIFY → EVALUATE → RESPOND → IMPLEMENT\n\n**Rules:**\n- No performative agreement: \"You're absolutely right!\", \"Great point!\"\n- No implementation before verification\n- Restate, ask questions, push back with reasoning, or just work\n- YAGNI check: grep for usage before implementing \"proper\" features\n\n**Source handling:**\n- Human partner: Trusted - implement after understanding\n- External reviewers: Verify technically, check breakage, push back if wrong\n\n**Full protocol:** `references\u002Fcode-review-reception.md`\n\n## Requesting Review\n\n**When:** After each task, major features, before merge\n\n**Process:**\n1. **Scout edge cases first** (see below)\n2. Get SHAs: `BASE_SHA=$(git rev-parse HEAD~1)` and `HEAD_SHA=$(git rev-parse HEAD)`\n3. Dispatch code_reviewer subagent with: WHAT, PLAN, BASE_SHA, HEAD_SHA, DESCRIPTION\n4. Fix Critical immediately, Important before proceeding\n\n**Full protocol:** `references\u002Frequesting-code-review.md`\n\n## Edge Case Scouting\n\n**When:** After implementation, before requesting code_reviewer\n\n**Process:**\n1. Invoke `$scout` with edge-case-focused prompt\n2. Scout analyzes: affected files, data flows, error paths, boundary conditions\n3. Review scout findings for potential issues\n4. Address critical gaps before code review\n\n**Full protocol:** `references\u002Fedge-case-scouting.md`\n\n## Task-Managed Review Pipeline\n\n**When:** Multi-file features (3+ changed files), parallel code_reviewer scopes, review cycles with Critical fix iterations.\n\n**Pipeline:** scout → review → fix → verify (each a Task with dependency chain)\n\n```\ntracked task creation: \"Scout edge cases\"         → pending\ntracked task creation: \"Review implementation\"    → pending, blockedBy: [scout]\ntracked task creation: \"Fix critical issues\"      → pending, blockedBy: [review]\ntracked task creation: \"Verify fixes pass\"        → pending, blockedBy: [fix]\n```\n\n**Parallel reviews:** Spawn scoped code_reviewer subagents for independent file groups (e.g., backend + frontend). Fix task blocks on all reviewers completing.\n\n**Re-review cycles:** If fixes introduce new issues, create cycle-2 review task. Limit 3 cycles, escalate to user after.\n\n**Full protocol:** `references\u002Ftask-management-reviews.md`\n\n## Verification Gates\n\n**Iron Law:** NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE\n\n**Gate:** IDENTIFY command → RUN full → READ output → VERIFY confirms → THEN claim\n\n**Requirements:**\n- Tests pass: Output shows 0 failures\n- Build succeeds: Exit 0\n- Bug fixed: Original symptom passes\n- Requirements met: Checklist verified\n\n**Red Flags:** \"should\"\u002F\"probably\"\u002F\"seems to\", satisfaction before verification, trusting agent reports\n\n**Full protocol:** `references\u002Fverification-before-completion.md`\n\n## Integration with Workflows\n\n- **Subagent-Driven:** Scout edge cases → Review after EACH task → Verify before next\n- **Pull Requests:** Scout → Verify tests → Code-reviewer review → Merge\n- **Task Pipeline:** Create review tasks with dependencies → auto-unblock through chain\n- **Cook Handoff:** Cook completes phase → review pipeline tasks → all complete → cook proceeds\n\n## Codebase Analysis Subcommands\n\n| Subcommand | Reference | Purpose |\n|------------|-----------|---------|\n| `$code-review codebase` | `references\u002Fcodebase-scan-workflow.md` | Scan & analyze the codebase |\n| `$code-review codebase parallel` | `references\u002Fparallel-review-workflow.md` | Ultrathink edge cases, then parallel verify |\n\n## Bottom Line\n\n1. Technical rigor over social performance\n2. Scout edge cases before review\n3. Task-manage reviews for multi-file features\n4. Evidence before claims\n\nVerify. Scout. Question. Then implement. Evidence. Then claim.\n",{"name":5,"description":7,"argument-hint":24},"[context] OR codebase [parallel]","main","f4f392e3e6ac09daca9d7c44c3afb20945435e36",".agents\u002Fskills\u002Fcode-review",79,"https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit","https:\u002F\u002Fgithub.com\u002Fmanhvann","Backend Engineer passionate about building reliable systems and contributing to open source.","2026-08-29 12:03:10",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add manhvann\u002Fcodexkit --skill \"ck:code-review\"",{"tool":39,"command":40},"bunx","bunx skills add manhvann\u002Fcodexkit --skill \"ck:code-review\"",{"tool":42,"command":43},"pnpm","pnpm dlx skills add manhvann\u002Fcodexkit --skill \"ck:code-review\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcode-review\u002FSKILL.md",true,[47,53,57,61,65,69,73],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcode-review-reception.md","REFERENCE","参考文档",3101,"https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcode-review\u002Freferences\u002Fcode-review-reception.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fcodebase-scan-workflow.md",1150,"https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcode-review\u002Freferences\u002Fcodebase-scan-workflow.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fedge-case-scouting.md",3015,"https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcode-review\u002Freferences\u002Fedge-case-scouting.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fparallel-review-workflow.md",1903,"https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcode-review\u002Freferences\u002Fparallel-review-workflow.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Frequesting-code-review.md",3069,"https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcode-review\u002Freferences\u002Frequesting-code-review.md",{"path":70,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Ftask-management-reviews.md",4887,"https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcode-review\u002Freferences\u002Ftask-management-reviews.md",{"path":74,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fverification-before-completion.md",4200,"https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcode-review\u002Freferences\u002Fverification-before-completion.md",[78,85,93,100,107,114],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7AGNE44ZPV7VVMCZCDQ0X55","ck:worktree","Create isolated git worktree for parallel development in monorepos.","https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fworktree\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7AGNB7EGT5ZKNRAF5M1V6D0","ck:web-testing","Web testing with Playwright, Vitest, k6. E2E\u002Funit\u002Fintegration\u002Fload\u002Fsecurity\u002Fvisual\u002Fa11y testing. Use for test automation, flakiness, Core Web Vitals, mobile gestures, cross-browser.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweb-testing\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7AGN7W938QCYZ70A8B0X70G","ck:web-frameworks","Build with Next.js (App Router, RSC, SSR, ISR), Turborepo monorepos. Use for React apps, server rendering, build optimization, caching strategies, shared dependencies.","https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweb-frameworks\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7AGN5HKJM49Z49N6XFDQB82","ck:web-design-guidelines","Review UI code for Web Interface Guidelines compliance. Use when asked to \"review my UI\", \"check accessibility\", \"audit design\", \"review UX\", or \"check my site against best practices\".","https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweb-design-guidelines\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M7AGN4D60DGGYM2YGZ80NT2A","ck:watzup","Review recent changes and wrap up the current work session.","https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwatzup\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":19},"01M7AGN308V7338SEEX8A6DZ53","ck:use-mcp","Utilize MCP server tools with intelligent discovery and execution.","https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fuse-mcp\u002FSKILL.md",[],[]]