skills/core/requesting-code-review/SKILL.md
Use when completing tasks or major features. Know when and how to request reviews. Provides git commit range to code-reviewer agent.
npx skillsauth add liauw-media/codeassist requesting-code-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Request reviews at logical completion points with clear context.
Code review is most effective when requested at appropriate times with sufficient context. This skill defines when to request reviews and how to provide reviewers with what they need.
MANDATORY: Use code-review skill before requesting external review
I'm completing self-review using the code-review skill before requesting external review.
[Perform comprehensive self-review]
Self-review complete ✅
- All tests pass
- No obvious issues found
- Code quality verified
Now ready for external review.
# Find first commit of your feature branch
git log --oneline --reverse origin/main..HEAD | head -1
# Find last commit
git log --oneline -1
# Example output:
abc1234 feat: add authentication (first commit)
def5678 test: add authentication tests (last commit)
Template:
I'm requesting code review using the code-reviewer agent.
Commit range: abc1234..def5678
Feature: User authentication implementation
Context:
- Implemented JWT token authentication with Laravel Sanctum
- Added registration, login, logout endpoints
- Includes 15 tests covering auth flows
- API documentation generated
Please review for:
- Security vulnerabilities
- Performance issues
- Test coverage
- Code quality
Dispatching code-reviewer agent...
[Use Task tool to deploy code-reviewer agent]
Agent prompt:
You are a specialized code reviewer.
Review the changes in commit range abc1234..def5678.
Focus areas:
- Security (authentication implementation)
- Performance (database queries)
- Test coverage (15 new tests)
- Code quality (controller, service, model)
Provide detailed review with:
- Critical issues (must fix)
- Important issues (should fix)
- Minor issues (nice to have)
- Positive observations
Use the code-review skill for systematic review.
Code Review Results Received:
Critical Issues (0):
[None found]
Important Issues (2):
1. [Issue description]
- Impact: [Explanation]
- Fix: [Recommendation]
2. [Issue description]
- Impact: [Explanation]
- Fix: [Recommendation]
Minor Issues (1):
1. [Issue description]
- Suggestion: [Recommendation]
I'll address the important issues before proceeding.
Code Review Request
Commit Range: [first-commit]..[last-commit]
Branch: feature/authentication
Base: main
Changes:
- Added AuthController with 3 endpoints
- Created 15 authentication tests
- Updated API documentation
- Added Sanctum dependency
Files Changed: 12 files
Lines Added: +450
Lines Removed: -20
Focus Areas:
- Security: JWT implementation
- Performance: Database queries
- Tests: Coverage and quality
Requesting code-reviewer agent dispatch.
## Code Review Request
**Branch:** feature/authentication
**Commits:** abc1234..def5678 (8 commits)
**Changes:** Authentication system implementation
### What Changed
- Implemented JWT authentication with Laravel Sanctum
- Added user registration endpoint
- Added login/logout endpoints
- Protected routes with auth middleware
- 15 tests covering auth flows
### How to Review
1. Check out branch: `git checkout feature/authentication`
2. Run tests: `./scripts/safe-test.sh vendor/bin/paratest`
3. Test endpoints: See API docs at `/docs/api`
### Focus Areas
- **Security**: JWT implementation, password hashing
- **Performance**: Database queries (should be no N+1)
- **Tests**: Coverage of edge cases
### Self-Review Completed
- ✅ All tests pass (127 total, 15 new)
- ✅ No security issues found
- ✅ Performance verified
- ✅ Code quality checked
Ready for review.
Definition: Must fix immediately, blocks merge
Examples:
Action: Fix before any further work
Definition: Should fix before merging
Examples:
Action: Resolve before merge, document if deferring
Definition: Nice to have, can defer
Examples:
Action: Fix if quick, otherwise create follow-up issue
Task Complete: User Registration Endpoint
I'm requesting code review before marking task complete.
Commit: abc1234
Changes:
- Added POST /api/register endpoint
- Validation for email/password
- Returns JWT token on success
- 5 tests added
Self-review complete ✅
Requesting code-reviewer agent for commit abc1234.
Feature Complete: Authentication System
I'm requesting comprehensive code review before creating PR.
Commit range: abc1234..def5678 (8 commits)
Changes summary:
- Registration endpoint
- Login endpoint
- Logout endpoint
- Protected route middleware
- 15 tests
- API documentation
Self-review complete ✅
Critical focus areas:
- Security: JWT implementation
- Performance: Database queries
- Tests: Edge case coverage
Requesting code-reviewer agent for full feature review.
Ready for Merge: Authentication Feature
Final code review before merging to main.
Branch: feature/authentication
Commits: abc1234..def5678
Base: main (up to date)
All previous review feedback addressed:
✅ Added rate limiting
✅ Fixed N+1 query
✅ Added missing test cases
Final check requested before merge.
Requesting code-reviewer agent for final review.
❌ Bad: Requesting review without self-review
"Please review my code" [without checking yourself first]
✅ Good: Self-review then request
"I've completed self-review (all tests pass, no issues found).
Requesting code review for commit range abc1234..def5678"
❌ Bad: No context
"Please review"
✅ Good: Clear context
"Please review authentication implementation (commits abc1234..def5678).
Focus on security and performance. 15 new tests added."
❌ Bad: Mid-implementation
"I'm halfway through, can you review what I have so far?"
✅ Good: At completion
"Implementation complete, all tests passing. Ready for review."
❌ Bad: Unclear what to review
"Review the authentication feature"
✅ Good: Specific commits
"Review commits abc1234..def5678 (authentication feature)"
Prerequisites:
code-review - Self-review BEFORE requesting external reviewverification-before-completion - Verify all tests passUse with:
receiving-code-review - Process feedback receivedfinishing-a-development-branch - After review approvedAgents:
code-reviewer agent for automated reviewBefore requesting review:
code-review skillThis skill is based on:
Social Proof: All professional development teams use structured code review processes.
When requesting reviews:
Bottom Line: Request reviews at completion points with clear context. Self-review first, then provide commit range and focus areas to reviewer.
development
Use when decomposing complex work. Dispatch fresh subagent per task, review between tasks. Flow: Load plan → Dispatch task → Review output → Apply feedback → Mark complete → Next task. No skipping reviews, no parallel dispatch.
development
# Server Documentation System Set up a documentation system that tracks changes and maintains server/project documentation with Claude Code hooks. ## When to Use - Setting up a new server or development environment - Need to track configuration changes over time - Want automatic documentation of work sessions - Maintaining changelog for infrastructure ## Directory Structure ``` ~/docs/ # User home directory (cross-platform) ├── changelog.md # Global over
development
Delegate tasks to remote Claude Code agent containers for parallel execution, long-running analysis, or resource-intensive operations.
development
Use when working on multiple features simultaneously. Creates isolated workspaces without branch switching, enabling parallel development.