[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7512P2CJSYCBB8G3ZJ6NHV1":3,"skill-same:01M7512P2CJSYCBB8G3ZJ6NHV1":44},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7512P2CJSYCBB8G3ZJ6NHV1","code-review-and-quality",null,"Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.","chrisbarrantes\u002Fmandrel","chrisbarrantes","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4534419?v=4","01M7511VXT2H7WE09JE4ZMBESG","Chris Barrantes","01M7511VYGPFHQCE9HNVKES0QN",0,"MIT","https:\u002F\u002Fgithub.com\u002Fchrisbarrantes\u002Fmandrel\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcore\u002Fcode-review-and-quality\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: code-review-and-quality\ndescription:\n  Conducts multi-axis code review. Use before merging any change. Use when\n  reviewing code written by yourself, another agent, or a human. Use when you\n  need to assess code quality across multiple dimensions before it enters the\n  main branch.\n---\n\n# Code Review and Quality\n\n## Policy Capsule\n\n- Every change gets reviewed before merge — no exceptions, including agent-authored code.\n- Apply the **five-axis review** to every change: **Correctness, Readability & Simplicity, Architecture, Security, Performance**.\n- Approval standard: approve when the change **definitely improves overall code health**, even if it isn't perfect. Don't block on stylistic preferences that match project conventions.\n- Verify the spec\u002Ftask requirements are met, edge cases (null, empty, boundary) and error paths are handled, and the tests are actually testing the right things — not just that they pass.\n- Reject \"clever\" code in favour of the boring, obvious solution. Abstractions MUST earn their complexity (no generalizing before the third use case).\n- Flag dead code artifacts (`_unused` vars, backwards-compat shims, `\u002F\u002F removed` comments) and require their removal before merge.\n- Defer to `.agents\u002Frules\u002Fsecurity-baseline.md` and the `security-and-hardening` skill for security review; explicit checks include input validation, no hardcoded secrets, parameterized queries, encoded output, authn+authz, and treating external data as untrusted.\n- Defer to `performance-optimization` for perf review; explicit checks include no N+1 queries, no unbounded fetches, no blocking sync work, no obviously oversized bundles.\n- Disallow scope creep in a PR: drive-by cleanups, adjacent refactors, and \"while I'm here\" edits should be split into a separate change.\n- Bug-fix reviews cover **both** the fix and the regression test; a fix without a failing-then-passing test is not approvable.\n\n## Overview\n\nMulti-dimensional code review with quality gates. Every change gets reviewed\nbefore merge — no exceptions. Review covers five axes: correctness, readability,\narchitecture, security, and performance.\n\n**The approval standard:** Approve a change when it definitely improves overall\ncode health, even if it isn't perfect. Perfect code doesn't exist — the goal is\ncontinuous improvement. Don't block a change because it isn't exactly how you\nwould have written it. If it improves the codebase and follows the project's\nconventions, approve it.\n\n## When to Use\n\n- Before merging any PR or change\n- After completing a feature implementation\n- When another agent or model produced code you need to evaluate\n- When refactoring existing code\n- After any bug fix (review both the fix and the regression test)\n\n## The Five-Axis Review\n\nEvery review evaluates code across these dimensions:\n\n### 1. Correctness\n\nDoes the code do what it claims to do?\n\n- Does it match the spec or task requirements?\n- Are edge cases handled (null, empty, boundary values)?\n- Are error paths handled (not just the happy path)?\n- Does it pass all tests? Are the tests actually testing the right things?\n- Are there off-by-one errors, race conditions, or state inconsistencies?\n\n### 2. Readability & Simplicity\n\nCan another engineer (or agent) understand this code without the author\nexplaining it?\n\n- Are names descriptive and consistent with project conventions? (No `temp`,\n  `data`, `result` without context)\n- Is the control flow straightforward (avoid nested ternaries, deep callbacks)?\n- Is the code organized logically (related code grouped, clear module\n  boundaries)?\n- Are there any \"clever\" tricks that should be simplified?\n- **Could this be done in fewer lines?** (1000 lines where 100 suffice is a\n  failure)\n- **Are abstractions earning their complexity?** (Don't generalize until the\n  third use case)\n- Would comments help clarify non-obvious intent? (But don't comment obvious\n  code.)\n- Are there dead code artifacts: no-op variables (`_unused`), backwards-compat\n  shims, or `\u002F\u002F removed` comments?\n\n### 3. Architecture\n\nDoes the change fit the system's design?\n\n- Does it follow existing patterns or introduce a new one? If new, is it\n  justified?\n- Does it maintain clean module boundaries?\n- Is there code duplication that should be shared?\n- Are dependencies flowing in the right direction (no circular dependencies)?\n- Is the abstraction level appropriate (not over-engineered, not too coupled)?\n\n### 4. Security\n\nFor detailed security guidance, see `security-and-hardening`. Does the change\nintroduce vulnerabilities?\n\n- Is user input validated and sanitized?\n- Are secrets kept out of code, logs, and version control?\n- Is authentication\u002Fauthorization checked where needed?\n- Are SQL queries parameterized (no string concatenation)?\n- Are outputs encoded to prevent XSS?\n- Are dependencies from trusted sources with no known vulnerabilities?\n- Is data from external sources (APIs, logs, user content, config files) treated\n  as untrusted?\n- Are external data flows validated at system boundaries before use in logic or\n  rendering?\n\n### 5. Performance\n\nFor detailed profiling and optimization, see `performance-optimization`. Does\nthe change introduce performance problems?\n\n- Any N+1 query patterns?\n- Any unbounded loops or unconstrained data fetching?\n- Any synchronous operations that should be async?\n- Any unnecessary re-renders in UI components?\n- Any missing pagination on list endpoints?\n- Any large objects created in hot paths?\n\n## Change Sizing\n\nSmall, focused changes are easier to review, faster to merge, and safer to\ndeploy. Target these sizes:\n\n```text\n~100 lines changed   → Good. Reviewable in one sitting.\n~300 lines changed   → Acceptable if it's a single logical change.\n~1000 lines changed  → Too large. Split it.\n```\n\n**What counts as \"one change\":** A single self-contained modification that\naddresses one thing, includes related tests, and keeps the system functional\nafter submission. One part of a feature — not the whole feature.\n\n**Splitting strategies when a change is too large:**\n\n| Strategy          | How                                                     | When                    |\n| ----------------- | ------------------------------------------------------- | ----------------------- |\n| **Stack**         | Submit a small change, start the next one based on it   | Sequential dependencies |\n| **By file group** | Separate changes for groups needing different reviewers | Cross-cutting concerns  |\n| **Horizontal**    | Create shared code\u002Fstubs first, then consumers          | Layered architecture    |\n| **Vertical**      | Break into smaller full-stack slices of the feature     | Feature work            |\n\n**When large changes are acceptable:** Complete file deletions and automated\nrefactoring where the reviewer only needs to verify intent, not every line.\n\n**Separate refactoring from feature work.** A change that refactors existing\ncode and adds new behavior is two changes — submit them separately. Small\ncleanups (variable renaming) can be included at reviewer discretion.\n\n## Change Descriptions\n\nEvery change needs a description that stands alone in version control history.\n\n**First line:** Short, imperative, standalone. \"Delete the FizzBuzz RPC\" not\n\"Deleting the FizzBuzz RPC.\" Must be informative enough that someone searching\nhistory can understand the change without reading the diff.\n\n**Body:** What is changing and why. Include context, decisions, and reasoning\nnot visible in the code itself. Link to bug numbers, benchmark results, or\ndesign docs where relevant. Acknowledge approach shortcomings when they exist.\n\n**Anti-patterns:** \"Fix bug,\" \"Fix build,\" \"Add patch,\" \"Moving code from A to\nB,\" \"Phase 1,\" \"Add convenience functions.\"\n\n## Review Process\n\n### Step 1: Understand the Context\n\nBefore looking at code, understand the intent:\n\n```text\n- What is this change trying to accomplish?\n- What spec or task does it implement?\n- What is the expected behavior change?\n```\n\n### Step 2: Review the Tests First\n\nTests reveal intent and coverage:\n\n```text\n- Do tests exist for the change?\n- Do they test behavior (not implementation details)?\n- Are edge cases covered?\n- Do tests have descriptive names?\n- Would the tests catch a regression if the code changed?\n```\n\n### Step 3: Review the Implementation\n\nWalk through the code with the five axes in mind:\n\n```text\nFor each file changed:\n1. Correctness: Does this code do what the test says it should?\n2. Readability: Can I understand this without help?\n3. Architecture: Does this fit the system?\n4. Security: Any vulnerabilities?\n5. Performance: Any bottlenecks?\n```\n\n### Step 4: Categorize Findings\n\nLabel every comment with its severity so the author knows what's required vs\noptional:\n\n| Prefix                        | Meaning            | Author Action                                           |\n| ----------------------------- | ------------------ | ------------------------------------------------------- |\n| _(no prefix)_                 | Required change    | Must address before merge                               |\n| **Critical:**                 | Blocks merge       | Security vulnerability, data loss, broken functionality |\n| **Nit:**                      | Minor, optional    | Author may ignore — formatting, style preferences       |\n| **Optional:** \u002F **Consider:** | Suggestion         | Worth considering but not required                      |\n| **FYI**                       | Informational only | No action needed — context for future reference         |\n\nThis prevents authors from treating all feedback as mandatory and wasting time\non optional suggestions.\n\n### Step 5: Verify the Verification\n\nCheck the author's verification story:\n\n```text\n- What tests were run?\n- Did the build pass?\n- Was the change tested manually?\n- Are there screenshots for UI changes?\n- Is there a before\u002Fafter comparison?\n```\n\n## Multi-Model Review Pattern\n\nUse different models for different review perspectives:\n\n```text\nModel A writes the code\n    │\n    ▼\nModel B reviews for correctness and architecture\n    │\n    ▼\nModel A addresses the feedback\n    │\n    ▼\nHuman makes the final call\n```\n\nThis catches issues that a single model might miss — different models have\ndifferent blind spots.\n\n**Example prompt for a review agent:**\n\n```text\nReview this code change for correctness, security, and adherence to\nour project conventions. The spec says [X]. The change should [Y].\nFlag any issues as Critical, Important, or Suggestion.\n```\n\n## Dead Code Hygiene\n\nAfter any refactoring or implementation change, check for orphaned code:\n\n1. Identify code that is now unreachable or unused\n2. List it explicitly\n3. **Ask before deleting:** \"Should I remove these now-unused elements: [list]?\"\n\nDon't leave dead code lying around — it confuses future readers and agents. But\ndon't silently delete things you're not sure about. When in doubt, ask.\n\n```text\nDEAD CODE IDENTIFIED:\n- formatLegacyDate() in src\u002Futils\u002Fdate.ts — replaced by formatDate()\n- OldTaskCard component in src\u002Fcomponents\u002F — replaced by TaskCard\n- LEGACY_API_URL constant in src\u002Fconfig.ts — no remaining references\n→ Safe to remove these?\n```\n\n## Review Speed\n\nSlow reviews block entire teams. The cost of context-switching to review is less\nthan the waiting cost imposed on others.\n\n- **Respond within one business day** — this is the maximum, not the target\n- **Ideal cadence:** Respond shortly after a review request arrives, unless deep\n  in focused coding. A typical change should complete multiple review rounds in\n  a single day\n- **Prioritize fast individual responses** over quick final approval. Quick\n  feedback reduces frustration even if multiple rounds are needed\n- **Large changes:** Ask the author to split them rather than reviewing one\n  massive changeset\n\n## Handling Disagreements\n\nWhen resolving review disputes, apply this hierarchy:\n\n1. **Technical facts and data** override opinions and preferences\n2. **Style guides** are the absolute authority on style matters\n3. **Software design** must be evaluated on engineering principles, not personal\n   preference\n4. **Codebase consistency** is acceptable if it doesn't degrade overall health\n\n**Don't accept \"I'll clean it up later.\"** Experience shows deferred cleanup\nrarely happens. Require cleanup before submission unless it's a genuine\nemergency. If surrounding issues can't be addressed in this change, require\nfiling a bug with self-assignment.\n\n## Honesty in Review\n\nWhen reviewing code — whether written by you, another agent, or a human:\n\n- **Don't rubber-stamp.** \"LGTM\" without evidence of review helps no one.\n- **Don't soften real issues.** \"This might be a minor concern\" when it's a bug\n  that will hit production is dishonest.\n- **Quantify problems when possible.** \"This N+1 query will add ~50ms per item\n  in the list\" is better than \"this could be slow.\"\n- **Push back on approaches with clear problems.** Sycophancy is a failure mode\n  in reviews. If the implementation has issues, say so directly and propose\n  alternatives.\n- **Accept override gracefully.** If the author has full context and disagrees,\n  defer to their judgment. Comment on code, not people — reframe personal\n  critiques to focus on the code itself.\n\n## Dependency Discipline\n\nPart of code review is dependency review:\n\n**Before adding any dependency:**\n\n1. Does the existing stack solve this? (Often it does.)\n2. How large is the dependency? (Check bundle impact.)\n3. Is it actively maintained? (Check last commit, open issues.)\n4. Does it have known vulnerabilities? (`npm audit`)\n5. What's the license? (Must be compatible with the project.)\n\n**Rule:** Prefer standard library and existing utilities over new dependencies.\nEvery dependency is a liability.\n\n## The Review Checklist\n\n```markdown\n## Review: [PR\u002FChange title]\n\n### Context\n\n- [ ] I understand what this change does and why\n\n### Correctness\n\n- [ ] Change matches spec\u002Ftask requirements\n- [ ] Edge cases handled\n- [ ] Error paths handled\n- [ ] Tests cover the change adequately\n\n### Readability\n\n- [ ] Names are clear and consistent\n- [ ] Logic is straightforward\n- [ ] No unnecessary complexity\n\n### Architecture\n\n- [ ] Follows existing patterns\n- [ ] No unnecessary coupling or dependencies\n- [ ] Appropriate abstraction level\n\n### Security\n\n- [ ] No secrets in code\n- [ ] Input validated at boundaries\n- [ ] No injection vulnerabilities\n- [ ] Auth checks in place\n- [ ] External data sources treated as untrusted\n\n### Performance\n\n- [ ] No N+1 patterns\n- [ ] No unbounded operations\n- [ ] Pagination on list endpoints\n\n### Verification\n\n- [ ] Tests pass\n- [ ] Build succeeds\n- [ ] Manual verification done (if applicable)\n\n### Verdict\n\n- [ ] **Approve** — Ready to merge\n- [ ] **Request changes** — Issues must be addressed\n```\n\n## Common Rationalizations\n\n| Rationalization                      | Reality                                                                                                                   |\n| ------------------------------------ | ------------------------------------------------------------------------------------------------------------------------- |\n| \"It works, that's good enough\"       | Working code that's unreadable, insecure, or architecturally wrong creates debt that compounds.                           |\n| \"I wrote it, so I know it's correct\" | Authors are blind to their own assumptions. Every change benefits from another set of eyes.                               |\n| \"We'll clean it up later\"            | Later never comes. The review is the quality gate — use it. Require cleanup before merge, not after.                      |\n| \"AI-generated code is probably fine\" | AI code needs more scrutiny, not less. It's confident and plausible, even when wrong.                                     |\n| \"The tests pass, so it's good\"       | Tests are necessary but not sufficient. They don't catch architecture problems, security issues, or readability concerns. |\n\n## Red Flags\n\n- PRs merged without any review\n- Review that only checks if tests pass (ignoring other axes)\n- \"LGTM\" without evidence of actual review\n- Security-sensitive changes without security-focused review\n- Large PRs that are \"too big to review properly\" (split them)\n- No regression tests with bug fix PRs\n- Review comments without severity labels — makes it unclear what's required vs\n  optional\n- Accepting \"I'll fix it later\" — it never happens\n\n## Verification\n\nAfter review is complete:\n\n- [ ] All Critical issues are resolved\n- [ ] All Important issues are resolved or explicitly deferred with\n      justification\n- [ ] Tests pass\n- [ ] Build succeeds\n- [ ] The verification story is documented (what changed, how it was verified)\n","# Code Review and Quality\n\n## Policy Capsule\n\n- Every change gets reviewed before merge — no exceptions, including agent-authored code.\n- Apply the **five-axis review** to every change: **Correctness, Readability & Simplicity, Architecture, Security, Performance**.\n- Approval standard: approve when the change **definitely improves overall code health**, even if it isn't perfect. Don't block on stylistic preferences that match project conventions.\n- Verify the spec\u002Ftask requirements are met, edge cases (null, empty, boundary) and error paths are handled, and the tests are actually testing the right things — not just that they pass.\n- Reject \"clever\" code in favour of the boring, obvious solution. Abstractions MUST earn their complexity (no generalizing before the third use case).\n- Flag dead code artifacts (`_unused` vars, backwards-compat shims, `\u002F\u002F removed` comments) and require their removal before merge.\n- Defer to `.agents\u002Frules\u002Fsecurity-baseline.md` and the `security-and-hardening` skill for security review; explicit checks include input validation, no hardcoded secrets, parameterized queries, encoded output, authn+authz, and treating external data as untrusted.\n- Defer to `performance-optimization` for perf review; explicit checks include no N+1 queries, no unbounded fetches, no blocking sync work, no obviously oversized bundles.\n- Disallow scope creep in a PR: drive-by cleanups, adjacent refactors, and \"while I'm here\" edits should be split into a separate change.\n- Bug-fix reviews cover **both** the fix and the regression test; a fix without a failing-then-passing test is not approvable.\n\n## Overview\n\nMulti-dimensional code review with quality gates. Every change gets reviewed\nbefore merge — no exceptions. Review covers five axes: correctness, readability,\narchitecture, security, and performance.\n\n**The approval standard:** Approve a change when it definitely improves overall\ncode health, even if it isn't perfect. Perfect code doesn't exist — the goal is\ncontinuous improvement. Don't block a change because it isn't exactly how you\nwould have written it. If it improves the codebase and follows the project's\nconventions, approve it.\n\n## When to Use\n\n- Before merging any PR or change\n- After completing a feature implementation\n- When another agent or model produced code you need to evaluate\n- When refactoring existing code\n- After any bug fix (review both the fix and the regression test)\n\n## The Five-Axis Review\n\nEvery review evaluates code across these dimensions:\n\n### 1. Correctness\n\nDoes the code do what it claims to do?\n\n- Does it match the spec or task requirements?\n- Are edge cases handled (null, empty, boundary values)?\n- Are error paths handled (not just the happy path)?\n- Does it pass all tests? Are the tests actually testing the right things?\n- Are there off-by-one errors, race conditions, or state inconsistencies?\n\n### 2. Readability & Simplicity\n\nCan another engineer (or agent) understand this code without the author\nexplaining it?\n\n- Are names descriptive and consistent with project conventions? (No `temp`,\n  `data`, `result` without context)\n- Is the control flow straightforward (avoid nested ternaries, deep callbacks)?\n- Is the code organized logically (related code grouped, clear module\n  boundaries)?\n- Are there any \"clever\" tricks that should be simplified?\n- **Could this be done in fewer lines?** (1000 lines where 100 suffice is a\n  failure)\n- **Are abstractions earning their complexity?** (Don't generalize until the\n  third use case)\n- Would comments help clarify non-obvious intent? (But don't comment obvious\n  code.)\n- Are there dead code artifacts: no-op variables (`_unused`), backwards-compat\n  shims, or `\u002F\u002F removed` comments?\n\n### 3. Architecture\n\nDoes the change fit the system's design?\n\n- Does it follow existing patterns or introduce a new one? If new, is it\n  justified?\n- Does it maintain clean module boundaries?\n- Is there code duplication that should be shared?\n- Are dependencies flowing in the right direction (no circular dependencies)?\n- Is the abstraction level appropriate (not over-engineered, not too coupled)?\n\n### 4. Security\n\nFor detailed security guidance, see `security-and-hardening`. Does the change\nintroduce vulnerabilities?\n\n- Is user input validated and sanitized?\n- Are secrets kept out of code, logs, and version control?\n- Is authentication\u002Fauthorization checked where needed?\n- Are SQL queries parameterized (no string concatenation)?\n- Are outputs encoded to prevent XSS?\n- Are dependencies from trusted sources with no known vulnerabilities?\n- Is data from external sources (APIs, logs, user content, config files) treated\n  as untrusted?\n- Are external data flows validated at system boundaries before use in logic or\n  rendering?\n\n### 5. Performance\n\nFor detailed profiling and optimization, see `performance-optimization`. Does\nthe change introduce performance problems?\n\n- Any N+1 query patterns?\n- Any unbounded loops or unconstrained data fetching?\n- Any synchronous operations that should be async?\n- Any unnecessary re-renders in UI components?\n- Any missing pagination on list endpoints?\n- Any large objects created in hot paths?\n\n## Change Sizing\n\nSmall, focused changes are easier to review, faster to merge, and safer to\ndeploy. Target these sizes:\n\n```text\n~100 lines changed   → Good. Reviewable in one sitting.\n~300 lines changed   → Acceptable if it's a single logical change.\n~1000 lines changed  → Too large. Split it.\n```\n\n**What counts as \"one change\":** A single self-contained modification that\naddresses one thing, includes related tests, and keeps the system functional\nafter submission. One part of a feature — not the whole feature.\n\n**Splitting strategies when a change is too large:**\n\n| Strategy          | How                                                     | When                    |\n| ----------------- | ------------------------------------------------------- | ----------------------- |\n| **Stack**         | Submit a small change, start the next one based on it   | Sequential dependencies |\n| **By file group** | Separate changes for groups needing different reviewers | Cross-cutting concerns  |\n| **Horizontal**    | Create shared code\u002Fstubs first, then consumers          | Layered architecture    |\n| **Vertical**      | Break into smaller full-stack slices of the feature     | Feature work            |\n\n**When large changes are acceptable:** Complete file deletions and automated\nrefactoring where the reviewer only needs to verify intent, not every line.\n\n**Separate refactoring from feature work.** A change that refactors existing\ncode and adds new behavior is two changes — submit them separately. Small\ncleanups (variable renaming) can be included at reviewer discretion.\n\n## Change Descriptions\n\nEvery change needs a description that stands alone in version control history.\n\n**First line:** Short, imperative, standalone. \"Delete the FizzBuzz RPC\" not\n\"Deleting the FizzBuzz RPC.\" Must be informative enough that someone searching\nhistory can understand the change without reading the diff.\n\n**Body:** What is changing and why. Include context, decisions, and reasoning\nnot visible in the code itself. Link to bug numbers, benchmark results, or\ndesign docs where relevant. Acknowledge approach shortcomings when they exist.\n\n**Anti-patterns:** \"Fix bug,\" \"Fix build,\" \"Add patch,\" \"Moving code from A to\nB,\" \"Phase 1,\" \"Add convenience functions.\"\n\n## Review Process\n\n### Step 1: Understand the Context\n\nBefore looking at code, understand the intent:\n\n```text\n- What is this change trying to accomplish?\n- What spec or task does it implement?\n- What is the expected behavior change?\n```\n\n### Step 2: Review the Tests First\n\nTests reveal intent and coverage:\n\n```text\n- Do tests exist for the change?\n- Do they test behavior (not implementation details)?\n- Are edge cases covered?\n- Do tests have descriptive names?\n- Would the tests catch a regression if the code changed?\n```\n\n### Step 3: Review the Implementation\n\nWalk through the code with the five axes in mind:\n\n```text\nFor each file changed:\n1. Correctness: Does this code do what the test says it should?\n2. Readability: Can I understand this without help?\n3. Architecture: Does this fit the system?\n4. Security: Any vulnerabilities?\n5. Performance: Any bottlenecks?\n```\n\n### Step 4: Categorize Findings\n\nLabel every comment with its severity so the author knows what's required vs\noptional:\n\n| Prefix                        | Meaning            | Author Action                                           |\n| ----------------------------- | ------------------ | ------------------------------------------------------- |\n| _(no prefix)_                 | Required change    | Must address before merge                               |\n| **Critical:**                 | Blocks merge       | Security vulnerability, data loss, broken functionality |\n| **Nit:**                      | Minor, optional    | Author may ignore — formatting, style preferences       |\n| **Optional:** \u002F **Consider:** | Suggestion         | Worth considering but not required                      |\n| **FYI**                       | Informational only | No action needed — context for future reference         |\n\nThis prevents authors from treating all feedback as mandatory and wasting time\non optional suggestions.\n\n### Step 5: Verify the Verification\n\nCheck the author's verification story:\n\n```text\n- What tests were run?\n- Did the build pass?\n- Was the change tested manually?\n- Are there screenshots for UI changes?\n- Is there a before\u002Fafter comparison?\n```\n\n## Multi-Model Review Pattern\n\nUse different models for different review perspectives:\n\n```text\nModel A writes the code\n    │\n    ▼\nModel B reviews for correctness and architecture\n    │\n    ▼\nModel A addresses the feedback\n    │\n    ▼\nHuman makes the final call\n```\n\nThis catches issues that a single model might miss — different models have\ndifferent blind spots.\n\n**Example prompt for a review agent:**\n\n```text\nReview this code change for correctness, security, and adherence to\nour project conventions. The spec says [X]. The change should [Y].\nFlag any issues as Critical, Important, or Suggestion.\n```\n\n## Dead Code Hygiene\n\nAfter any refactoring or implementation change, check for orphaned code:\n\n1. Identify code that is now unreachable or unused\n2. List it explicitly\n3. **Ask before deleting:** \"Should I remove these now-unused elements: [list]?\"\n\nDon't leave dead code lying around — it confuses future readers and agents. But\ndon't silently delete things you're not sure about. When in doubt, ask.\n\n```text\nDEAD CODE IDENTIFIED:\n- formatLegacyDate() in src\u002Futils\u002Fdate.ts — replaced by formatDate()\n- OldTaskCard component in src\u002Fcomponents\u002F — replaced by TaskCard\n- LEGACY_API_URL constant in src\u002Fconfig.ts — no remaining references\n→ Safe to remove these?\n```\n\n## Review Speed\n\nSlow reviews block entire teams. The cost of context-switching to review is less\nthan the waiting cost imposed on others.\n\n- **Respond within one business day** — this is the maximum, not the target\n- **Ideal cadence:** Respond shortly after a review request arrives, unless deep\n  in focused coding. A typical change should complete multiple review rounds in\n  a single day\n- **Prioritize fast individual responses** over quick final approval. Quick\n  feedback reduces frustration even if multiple rounds are needed\n- **Large changes:** Ask the author to split them rather than reviewing one\n  massive changeset\n\n## Handling Disagreements\n\nWhen resolving review disputes, apply this hierarchy:\n\n1. **Technical facts and data** override opinions and preferences\n2. **Style guides** are the absolute authority on style matters\n3. **Software design** must be evaluated on engineering principles, not personal\n   preference\n4. **Codebase consistency** is acceptable if it doesn't degrade overall health\n\n**Don't accept \"I'll clean it up later.\"** Experience shows deferred cleanup\nrarely happens. Require cleanup before submission unless it's a genuine\nemergency. If surrounding issues can't be addressed in this change, require\nfiling a bug with self-assignment.\n\n## Honesty in Review\n\nWhen reviewing code — whether written by you, another agent, or a human:\n\n- **Don't rubber-stamp.** \"LGTM\" without evidence of review helps no one.\n- **Don't soften real issues.** \"This might be a minor concern\" when it's a bug\n  that will hit production is dishonest.\n- **Quantify problems when possible.** \"This N+1 query will add ~50ms per item\n  in the list\" is better than \"this could be slow.\"\n- **Push back on approaches with clear problems.** Sycophancy is a failure mode\n  in reviews. If the implementation has issues, say so directly and propose\n  alternatives.\n- **Accept override gracefully.** If the author has full context and disagrees,\n  defer to their judgment. Comment on code, not people — reframe personal\n  critiques to focus on the code itself.\n\n## Dependency Discipline\n\nPart of code review is dependency review:\n\n**Before adding any dependency:**\n\n1. Does the existing stack solve this? (Often it does.)\n2. How large is the dependency? (Check bundle impact.)\n3. Is it actively maintained? (Check last commit, open issues.)\n4. Does it have known vulnerabilities? (`npm audit`)\n5. What's the license? (Must be compatible with the project.)\n\n**Rule:** Prefer standard library and existing utilities over new dependencies.\nEvery dependency is a liability.\n\n## The Review Checklist\n\n```markdown\n## Review: [PR\u002FChange title]\n\n### Context\n\n- [ ] I understand what this change does and why\n\n### Correctness\n\n- [ ] Change matches spec\u002Ftask requirements\n- [ ] Edge cases handled\n- [ ] Error paths handled\n- [ ] Tests cover the change adequately\n\n### Readability\n\n- [ ] Names are clear and consistent\n- [ ] Logic is straightforward\n- [ ] No unnecessary complexity\n\n### Architecture\n\n- [ ] Follows existing patterns\n- [ ] No unnecessary coupling or dependencies\n- [ ] Appropriate abstraction level\n\n### Security\n\n- [ ] No secrets in code\n- [ ] Input validated at boundaries\n- [ ] No injection vulnerabilities\n- [ ] Auth checks in place\n- [ ] External data sources treated as untrusted\n\n### Performance\n\n- [ ] No N+1 patterns\n- [ ] No unbounded operations\n- [ ] Pagination on list endpoints\n\n### Verification\n\n- [ ] Tests pass\n- [ ] Build succeeds\n- [ ] Manual verification done (if applicable)\n\n### Verdict\n\n- [ ] **Approve** — Ready to merge\n- [ ] **Request changes** — Issues must be addressed\n```\n\n## Common Rationalizations\n\n| Rationalization                      | Reality                                                                                                                   |\n| ------------------------------------ | ------------------------------------------------------------------------------------------------------------------------- |\n| \"It works, that's good enough\"       | Working code that's unreadable, insecure, or architecturally wrong creates debt that compounds.                           |\n| \"I wrote it, so I know it's correct\" | Authors are blind to their own assumptions. Every change benefits from another set of eyes.                               |\n| \"We'll clean it up later\"            | Later never comes. The review is the quality gate — use it. Require cleanup before merge, not after.                      |\n| \"AI-generated code is probably fine\" | AI code needs more scrutiny, not less. It's confident and plausible, even when wrong.                                     |\n| \"The tests pass, so it's good\"       | Tests are necessary but not sufficient. They don't catch architecture problems, security issues, or readability concerns. |\n\n## Red Flags\n\n- PRs merged without any review\n- Review that only checks if tests pass (ignoring other axes)\n- \"LGTM\" without evidence of actual review\n- Security-sensitive changes without security-focused review\n- Large PRs that are \"too big to review properly\" (split them)\n- No regression tests with bug fix PRs\n- Review comments without severity labels — makes it unclear what's required vs\n  optional\n- Accepting \"I'll fix it later\" — it never happens\n\n## Verification\n\nAfter review is complete:\n\n- [ ] All Critical issues are resolved\n- [ ] All Important issues are resolved or explicitly deferred with\n      justification\n- [ ] Tests pass\n- [ ] Build succeeds\n- [ ] The verification story is documented (what changed, how it was verified)\n",{"name":5,"description":7},"main","22b1847659cc2a98f4fb8c24858f2199d91fda66",".agents\u002Fskills\u002Fcore\u002Fcode-review-and-quality","https:\u002F\u002Fgithub.com\u002Fchrisbarrantes\u002Fmandrel","https:\u002F\u002Fgithub.com\u002Fchrisbarrantes","2026-05-27 08:16:47",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add chrisbarrantes\u002Fmandrel --skill code-review-and-quality",{"tool":36,"command":37},"bunx","bunx skills add chrisbarrantes\u002Fmandrel --skill code-review-and-quality",{"tool":39,"command":40},"pnpm","pnpm dlx skills add chrisbarrantes\u002Fmandrel --skill code-review-and-quality","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fchrisbarrantes\u002Fmandrel\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcore\u002Fcode-review-and-quality\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":19},"01M75171YZD373TXY5ZWJNXGS9","no-capsule-skill","Fixture without a Policy Capsule section.","https:\u002F\u002Fgithub.com\u002Fchrisbarrantes\u002Fmandrel\u002Fblob\u002Fmain\u002Ftests\u002Forchestration\u002Ffixtures\u002Fskill-capsule\u002Fno-capsule-skill\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7516ZA88ESAAY3JWXBNA56K","backend-security-patterns","Combined backend protocols for authentication (Clerk JWT verification) and PII-safe observability. Use when handling auth on the server, verifying Clerk webhooks via `svix`, scoping metadata via `publicMetadata`\u002F `privateMetadata`, or sanitizing logs to keep emails, tokens, and request bodies out of telemetry.","https:\u002F\u002Fgithub.com\u002Fchrisbarrantes\u002Fmandrel\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstack\u002Fsecurity\u002Fbackend-security-patterns\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7516WFQMKD2NGFMDNFG6C4A","vitest","Writes fast, isolated unit and integration tests with Vitest. Use when each test must run on file-save without shared state — `vi.mock()` for external deps, `vi.spyOn()` for call monitoring, AAA structure, and edge-case coverage for null\u002Fundefined\u002Fboundary inputs.","https:\u002F\u002Fgithub.com\u002Fchrisbarrantes\u002Fmandrel\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstack\u002Fqa\u002Fvitest\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7516T8FX7B0B0D510EE2FAP","playwright","Robust E2E browser testing with Playwright. Use when writing browser-driven tests — leverage auto-waiting (no `waitForTimeout`), prefer user-visible locators (`getByRole`, `getByText`, `getByLabel`) over CSS\u002FXPath, reuse `storageState` for auth, and enable trace-on-first-retry for CI debugging.","https:\u002F\u002Fgithub.com\u002Fchrisbarrantes\u002Fmandrel\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstack\u002Fqa\u002Fplaywright\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7516PHY868BJXHHZJ0FRYSX","playwright-bdd","Wires Gherkin `.feature` files to Playwright via the `playwright-bdd` library. Use when running BDD scenarios on a Playwright runtime — pairs with the `gherkin-authoring` skill (scenario prose) and the `playwright` skill (browser conventions). Drives execution by tag expression with trace-first debugging and Playwright-native sharding.","https:\u002F\u002Fgithub.com\u002Fchrisbarrantes\u002Fmandrel\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstack\u002Fqa\u002Fplaywright-bdd\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7516KEGSBBFJXRZWYBKYM4P","lighthouse-baseline","Codifies the capture-and-check baseline pattern for long-running quality signals (Lighthouse scores, bundle size, p95 latency, runtime memory). Use when wiring a new metric that needs a baseline file, paired :capture \u002F :check npm scripts, a tolerance-bounded gate, and a weekly refresh cadence — the goal is a hard CI signal that ratchets only with intent.","https:\u002F\u002Fgithub.com\u002Fchrisbarrantes\u002Fmandrel\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstack\u002Fqa\u002Flighthouse-baseline\u002FSKILL.md",[],[]]