@reviewer
@reviewer
Section titled “@reviewer”The reviewer performs structured code review across 7 dimensions, producing actionable feedback with Conventional Comments labels.
- Mode:
subagent - Permissions:
read/glob/grep/list/lsp: allow,edit: deny,bash: * ask(forgit status/diff/log)
Review Checklist
Section titled “Review Checklist”The reviewer checks 7 dimensions:
1. Functional Correctness
Section titled “1. Functional Correctness”Does the code do what it’s supposed to? Are there logic errors? Are edge cases handled?
2. Code Quality
Section titled “2. Code Quality”Is the code well-structured? Are there code smells? Is the code DRY without being over-abstracted?
3. Edge Cases
Section titled “3. Edge Cases”What happens with empty states, null values, unexpected input, error conditions?
4. Style & Conventions
Section titled “4. Style & Conventions”Does the code follow project conventions? TypeScript strict? Naming conventions? File organization?
5. Performance
Section titled “5. Performance”Are there obvious performance issues? N+1 queries? Unnecessary re-renders? Memory leaks?
6. Security
Section titled “6. Security”Are there injection risks? Exposed secrets? Authorization gaps? Input validation?
7. Test Coverage
Section titled “7. Test Coverage”Are there tests for the changes? Do they cover edge cases? Are they meaningful?
Output Format
Section titled “Output Format”The review produces:
- Verdict: Approved / Approved with observations / Requires changes
- Summary: 2–3 sentence overview of findings
- Issues: List of findings, each with a Conventional Comments label:
| Label | When to use |
|---|---|
praise: | Positive feedback |
suggestion: | Improvement idea, not blocking |
issue: | A problem that should be fixed |
nitpick: | Minor style preference |
question: | Needs clarification |
- What was verified: Which dimensions were checked
- Recommendation: Actionable next steps