Agent skill
code-reviewer
Use when asked to review MERN stack code - comprehensive code reviewer that checks project health, security, maintainability, performance, testing, and architecture. Combines general code quality analysis with MERN-specific expertise.
Install this agent skill to your Project
npx add-skill https://github.com/9tykeshav/mern-ninja-cc/tree/main/skills/code-reviewer
SKILL.md
Code Reviewer
Overview
Comprehensive code review: General intelligence + MERN specialization.
Philosophy: Check project health FIRST, then dive into code. A 6,000-line file is a problem regardless of what's in it.
Review Workflow
Phase 0: Project Health (Do This First)
Before reading any code, assess project health:
- Build status: Run
tsc --noEmitor check for compilation errors - Project docs: Read README, any STATUS/BUGS/TODO files - look for deployment blockers
- Test health: Do tests exist? Check
package.jsonscripts, look for test directories - File sizes:
find src -name "*.ts" -o -name "*.tsx" | xargs wc -l | sort -n | tail -20 - Dependencies: Check for
npm auditissues, unusual deps (Angular in React?)
Stop here if: Build is broken, docs say "DO NOT DEPLOY", or critical blockers found. Report immediately.
Phase 1: Scope Detection
- Identify scope from context:
- Full repo → Broad review, sample key files
- Feature/PR → All changed files
- Single file → Deep dive
- Detect layers: React? Express? MongoDB? Node.js?
- If ambiguous → ask user
Phase 2: Review by Priority
| Priority | Focus | Severity |
|---|---|---|
| 0. Blockers | Build failures, "DO NOT DEPLOY", broken deploys | STOP |
| 1. Security | Injection, auth, secrets, XSS | Critical |
| 2. Maintainability | God files, complexity, duplication | Critical/Important |
| 3. Performance | N+1, missing indexes, re-renders | Important |
| 4. Testing | No tests, low coverage, flaky tests | Important |
| 5. Best Practices | Error handling, async patterns | Suggestion |
| 6. Architecture | API design, state management | Suggestion |
Load reference files ON-DEMAND when you hit MERN-specific edge cases.
Phase 3: Report
Use the output format below. Offer to fix starting with Critical.
Output Format
# MERN Code Review
## Project Health
- Build: [Compiles / X errors / Not checked]
- Tests: [X passing / X failing / None found]
- Blockers: [Any deployment blockers from docs]
- Large files: [Files >500 lines]
## Scope
[What was reviewed]
## Summary
- Files reviewed: X
- Issues: X Critical, X Important, X Suggestions
## Critical (Must Fix)
### [C1] Category: Title
**File:** `path:line`
**Why:** [1-2 sentences]
**Fix:** [Code or instruction]
## Important (Should Fix)
### [I1] Category: Title
...
## Suggestions
- `file:line` - Note
## What's Good
- [Positive observations]
## Verdict
[Ready to deploy / Blocked / Needs fixes] - [1 sentence reason]
---
**Ready to fix these?** Starting with Critical issues.
Checklists
Minimum required checks. Report other issues you find during review.
Blockers (Check First)
- Project compiles without errors
- No "DO NOT DEPLOY" or similar warnings in docs
- No critical security advisories in
npm audit
Security
- No
$where,$ne,$regexwith user input (NoSQL injection/ReDoS) - No
dangerouslySetInnerHTMLwithout DOMPurify - JWT in httpOnly cookies, not localStorage
- Secrets in env vars, not hardcoded (check config files too, not just code)
- Helmet middleware configured
- CORS properly restricted
- Rate limiting on auth endpoints
- Input validation on all endpoints
- No
eval()ornew Function()with user input
Maintainability
- No file >500 lines (god files)
- No function >50 lines
- No class/component with >20 methods
- No deep nesting (>4 levels)
- No copy-paste blocks >10 lines (DRY)
- Clear naming (no cryptic abbreviations)
- Consistent code style
Performance
- No N+1 queries (use populate/$lookup)
- Indexes on frequently queried fields
-
.lean()for read-only Mongoose queries - No
fs.readFileSyncin request handlers - React.memo on expensive components
- useCallback/useMemo where beneficial
- Pagination on list endpoints
Testing
- Tests exist for critical paths (auth, payments, core flows)
- Test coverage reasonable (>50% for services)
- No skipped/commented-out tests
- Tests actually assert behavior (not just "doesn't crash")
- Mocks don't hide real integration issues
Best Practices
- Async errors handled (try/catch or error middleware)
- useEffect cleanup functions present
- No floating promises (unhandled async)
- Middleware order correct (body-parser before routes, error handler last)
- Environment variables validated at startup
- Graceful shutdown handlers
Architecture
- Consistent API response format
- Service layer between controllers and DB
- Types aligned frontend/backend
- No circular dependencies
- Clear module boundaries
- No god components (React >300 lines)
- State management appropriate for complexity
Red Flags (Immediate Critical)
These are automatic Critical issues:
eval(),new Function()with user input- Hardcoded secrets/credentials in code
dangerouslySetInnerHTMLwithout sanitization- JWT/auth tokens in localStorage
- Missing auth middleware on protected routes
$whereclause with user input- File >1000 lines
- "DO NOT DEPLOY" in project docs
npm auditcritical vulnerabilities
Scope Calibration
| Scope | Phase 0 | Code Depth | Focus |
|---|---|---|---|
| Single file | Skip | Deep | All checklists on that file |
| Last commit | Quick | Medium | Changed lines + immediate context |
| Feature/PR | Quick | Medium | All changed files |
| Full repo | Full | Broad | Sample key files, architecture |
Reference Files
Load ONLY when you encounter MERN-specific patterns you need to verify:
| When to Load | Reference |
|---|---|
| NoSQL query security question | security.md |
| React hooks/re-render issue | react.md |
| Express middleware question | express.md |
| MongoDB schema/index question | mongodb.md |
| Node.js async/memory issue | nodejs.md |
| API design/auth flow question | fullstack.md |
Do NOT load all references upfront. They're for edge cases, not general review.
Don't
- Don't claim "no issues found" without actually searching for them
- Don't report on code you haven't read
- Don't classify style issues as Critical
Examples
God File Detection
Found: EventService.ts - 6,165 lines
→ Critical [C1] Maintainability: God file
→ Recommend split into: EventQueryService, EventBookingService,
EventGuestService, EventInviteService (~500 lines each)
Missing Health Check
Found: CURRENT_STATUS_AND_BUGS.md contains "DO NOT DEPLOY"
→ Critical [C1] Blocker: Deployment blocked by known issues
→ Fix TypeScript errors in EditEventModal.tsx before proceeding
Security + Specific Fix
Found: No Helmet middleware in index.ts
→ Critical [C2] Security: Missing security headers
→ Fix: npm install helmet && app.use(helmet())
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
backend-test-writer
Use when generating tests for backend code (Express routes, MongoDB models, Node services) - analyzes file type, detects test framework from package.json, generates comprehensive tests with setup/teardown and edge case coverage
mongodb-query-patterns
Use when writing ANY Mongoose query (.find, .findOne, .findById, .aggregate, .populate), adding database operations to services or controllers, wiring data between services, building endpoints that read or write to MongoDB, or reviewing code that chains service calls. TRIGGER especially when about to write a new findById or pass an ID where a document could be passed instead.
handoff
Compact the current conversation into a handoff document for another agent to pick up.
edit-article
Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.
obsidian-vault
Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.
scaffold-exercises
Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
Didn't find tool you were looking for?