| name | code-review |
| description | Review code written during a run, auto-fix no-brainer issues, and suggest improvements requiring confirmation. Invoked after tests pass. |
| version | 1.0.0 |
Review code written during a run, auto-fix no-brainer issues, and suggest improvements requiring confirmation.
- Invoked by run-execute after tests pass (Step 6b)
- Receives: files_created, files_modified, run_id, intent context
<degrees_of_freedom>
- AUTO-FIX: LOW — Only mechanical, non-semantic changes
- SUGGESTIONS: MEDIUM — Present options, let user decide
</degrees_of_freedom>
REVIEW all files created/modified in current run
AUTO-FIX only mechanical, non-semantic issues
ALWAYS CONFIRM security, architecture, and behavioral changes
RESPECT project coding standards from .specs-fire/standards/
NEVER break working code — if tests passed, be conservative
RE-RUN tests after auto-fixes — revert if tests fail
<input_context>
The skill receives from run-execute:
files_created:
- path: src/auth/login.ts
purpose: Login endpoint handler
- path: src/auth/login.test.ts
purpose: Unit tests for
Receive files_created and files_modified from parent workflow
Load project standards:
.specs-fire/standards/coding-standards.md
.specs-fire/standards/testing-standards.md
Run: npm run lint --fix 2>&1 || npx eslint --fix {files}
Parse output for remaining issues
For each file, check against review categories:
Code Quality — unused imports, console statements, formatting
Security — hardcoded secrets, injection vulnerabilities, missing validation
Architecture — code placement, coupling, error handling
Testing — coverage gaps, edge cases, brittle patterns
Apply all AUTO-FIX changes
Track each change made (file, line, before, after)
Create review report using template: templates/review-report.md.hbs
Write to: .specs-fire/runs/{run-id}/review-report.md
Include: auto-fixed issues, pending suggestions, skipped items
## Code Review Complete
Apply all suggestions
Re-run tests
Update review-report.md with applied status
Return summary to run-execute workflow:
{
"success": true,
"auto_fixed_count": {count},
"suggestions_applied": {count},
"suggestions_skipped": {count},
"tests_passing": true,
"report_path": ".specs-fire/runs/{run-id}/review-report.md"
}
