From claudekit
Guides structured code review requests with scope, context, concerns, tests, and checklist template. Use before PRs, merges, or for feedback on security/auth/data changes.
npx claudepluginhub duthaho/claudekit --plugin claudekitThis skill uses the workspace's default tool permissions.
- After completing a task (before proceeding to next)
Dispatches code-reviewer subagent to evaluate code changes via git SHAs after tasks, major features, or before merging, with focused context on implementation and requirements.
Guides code review: rigorous feedback reception, subagent reviews after tasks/features, verification before completion claims. For subagent dev and PRs.
Guides effective code reviews with mindset, actionable feedback examples, scope, and phased process. Use for pull requests, standards, mentoring, architecture reviews.
Share bugs, ideas, or general feedback.
Clearly state what should be reviewed:
## Review Scope
**Files changed**:
- src/services/user-service.ts (modified)
- src/services/user-service.test.ts (added)
- src/types/user.ts (modified)
**Lines changed**: ~150 additions, ~20 deletions
**Not in scope** (don't review):
- package.json changes (unrelated dependency update)
- Generated files in dist/
Explain why these changes were made:
## Context
**Task**: Implement user email verification
**Requirements**:
- Users must verify email before accessing features
- Verification link expires after 24 hours
- Users can request new verification email
**Design decisions**:
- Used JWT for verification token (stateless)
- Stored verification status in existing User table
Highlight where you want focused attention:
## Areas of Concern
1. **Security**: Is the token generation secure enough?
2. **Error handling**: Are all edge cases covered?
3. **Performance**: Will the verification lookup be efficient?
Show what's tested:
## Test Coverage
- Unit tests: 8 new tests in user-service.test.ts
- Integration: Manual testing of full flow
- Edge cases: Expired token, invalid token, already verified
**Not tested** (known gaps):
- Load testing with many concurrent verifications
## Code Review Request
### Summary
[1-2 sentence description of changes]
### Files Changed
- `path/to/file1.ts` - [Brief description]
- `path/to/file2.ts` - [Brief description]
### Context
[Why these changes were needed]
### Implementation Notes
[Key decisions made and why]
### Areas for Focus
1. [Specific concern 1]
2. [Specific concern 2]
### Testing
- [x] Unit tests added/updated
- [x] Integration tests pass
- [ ] E2E tests (not applicable)
### Checklist
- [x] Code follows project conventions
- [x] No security vulnerabilities introduced
- [x] Documentation updated if needed
For small, low-risk changes:
## Quick Review: Fix typo in error message
**File**: src/errors.ts
**Change**: Fixed "recieved" → "received" in error message
**Risk**: None
For typical feature work:
## Review: Add user preferences
**Files**: 3 files, ~200 lines
**Context**: Users can now save display preferences
**Focus**: Data validation, storage approach
For high-risk changes:
## CRITICAL REVIEW: Authentication refactor
**Files**: 12 files, ~800 lines
**Risk**: HIGH - Authentication system changes
**Required reviewers**: Security team
**Focus**: Token handling, session management, encryption
BAD: "Review my last week of work"
GOOD: "Review the user verification feature (3 files)"
## To test locally
1. git checkout feature/email-verification
2. npm install
3. npm test -- --grep "email verification"
BAD: "Let me know if anything looks wrong"
GOOD: "I'm unsure about the error handling in lines 45-60"
Related:
- Ticket: PROJ-123
- Design doc: [link]
- Previous discussion: [link]
Reviewer will return:
- Critical issues (must fix)
- Important issues (should fix)
- Minor issues (optional)
- Approval/rejection status
See receiving-code-review skill for detailed guidance.
What reviewers need to know, by stack:
requirements.txt?mypy --strict passes?)class-validator decorators correct?)AppModule?whitelist: true on ValidationPipe?'use client' directive where needed?next build)receiving-code-review - Companion skill for processing and acting on review feedback after it is receivedverification-before-completion - Run verification checks before requesting review to ensure code is actually readyfinishing-a-development-branch - Use after review approval to complete the branch merge/PR workflow