extensions/opencode/skills/code_review_expert/SKILL.md
Code Review Expert for static analysis, security auditing, architecture review, and ensuring code quality standards.
npx skillsauth add sawrus/agent-guides code_review_expertInstall 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.
Expert code reviewer specializing in static analysis, security auditing, architecture review, and ensuring code quality for Flutter/Dart applications. Validates that code meets team standards and is production-ready.
flutter build apk --debugflutter analyzeflutter test// ❌ BAD: Hardcoded secrets
const apiKey = 'sk-1234567890';
// ✅ GOOD: Environment variables
final apiKey = const String.fromEnvironment('API_KEY');
// ❌ BAD: Insecure storage
SharedPreferences.setMockInitialValues({});
final prefs = await SharedPreferences.getInstance();
prefs.setString('token', token);
// ✅ GOOD: Secure storage
final secureStorage = SecureStorage();
await secureStorage.write(key: 'token', value: token);
| Check | Status | Notes |
|-------|--------|-------|
| Static Analysis | ✅/❌ | X warnings, Y errors |
| Security Audit | ✅/❌ | X vulnerabilities found |
| Architecture | ✅/❌ | Clean Architecture compliant |
| Code Quality | ✅/❌ | Team standards met |
| Tests | ✅/❌ | X tests, XX% coverage |
| Build | ✅/❌ | Builds successfully |
### Final Verdict
[APPROVED / REQUEST_CHANGES]
Comments:
- Issue 1: ...
- Issue 2: ...
### Feature Feasibility
[FEASIBLE / NOT_FEASIBLE]
Reasoning:
- Design is implementable: Yes/No
- Technical constraints: ...
- Risks: ...
Always provide clear approval or rejection with detailed reasoning.
testing
QA Expert for writing E2E tests, test scenarios, test plans, and ensuring test coverage quality.
development
Expert UI/UX design intelligence for creating distinctive, high-craft, and mobile-first interfaces. Focuses on premium aesthetics, touch-first ergonomics, and Flutter performance.
development
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep watching open PRs so fresh review feedback is surfaced promptly. Use when the user asks Codex to monitor a PR, watch CI, handle review comments, or keep an eye on failures and feedback on an open PR.
development
Apply STRIDE threat modeling to system designs, identify IDOR and authorization vulnerabilities, and build threat matrices for security reviews. Use when the user designs a new system, reviews an architecture, prepares for a security audit, or asks about common API vulnerabilities like IDOR or broken access control.