code-review
Review code for correctness, security, performance, and Resume Matcher conventions. Use when receiving code review feedback or before submitting PRs. Requires technical rigor, not performative agreement.
How do I install this agent skill?
npx skills add https://github.com/srbhr/resume-matcher --skill code-reviewIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill consists of a behavioral guideline and checklist for conducting code reviews. It promotes high-quality technical standards and security best practices, such as input validation and avoiding hardcoded secrets. No malicious patterns or dangerous capabilities were detected.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
- Runlayerwarn
1/1 file flagged
What does this agent skill do?
Code Review
Code review requires technical evaluation, not emotional performance.
Core principle: Verify before implementing. Ask before assuming. Technical correctness over social comfort.
Review Checklist
Backend (Python/FastAPI)
- All functions have type hints
-
copy.deepcopy()for mutable defaults - Error handling: detailed logs server-side, generic messages to clients
- API keys via
api_key=parameter, notos.environ - Async functions for I/O operations
- Pydantic schemas for request/response bodies
- No blocking calls in async routes
-
asyncio.Lock()for shared resource initialization
Frontend (Next.js/React)
- Swiss International Style compliance
-
rounded-noneeverywhere - Textareas have Enter key handler
- Direct icon imports (not barrel)
-
next/dynamicfor heavy components -
Promise.all()for independent fetches - Server Actions check auth inside
Security
- No secrets in code
- Input validation on user data
- CORS configured properly
- Auth checks on protected endpoints
Response Pattern
WHEN receiving feedback:
1. READ: Complete feedback without reacting
2. UNDERSTAND: Restate requirement in own words
3. VERIFY: Check against codebase reality
4. EVALUATE: Technically sound for THIS codebase?
5. RESPOND: Technical acknowledgment or reasoned pushback
6. IMPLEMENT: One item at a time, test each
Forbidden Responses
- "You're absolutely right!" (performative)
- "Great point!" (performative)
- "Let me implement that now" (before verification)
When to Push Back
- Suggestion breaks existing functionality
- Reviewer lacks full context
- Violates YAGNI (unused feature)
- Technically incorrect for this stack
- Conflicts with architectural decisions
Severity Format
[CRITICAL] file:line - Security, data loss, crash
[ERROR] file:line - Bug, missing validation
[WARNING] file:line - Style, convention
[INFO] file:line - Suggestion, not required
References
- Backend guide:
docs/agent/architecture/backend-guide.md - Coding standards:
docs/agent/coding-standards.md - Style guide:
docs/agent/design/style-guide.md
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/srbhr/resume-matcher/code-review">View code-review on skillZs</a>