Code review mean

Skill endorphin-ai/claude-code-teams/mean-team/.claude/skills/code-review-mean

🍕 One Pizza Team [AI Agents Team ] | Claude Code Agent Squads

Install

npx -y skills add endorphin-ai/claude-code-teams --skill code-review-mean

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Code review for MEAN stack apps. Use when reviewing backend (Express + MongoDB) and frontend (React) code for quality, security, architecture compliance, performance, and best practices.

SKILL.md

3.3 KB, as published. Nobody here has run it

Code Review Mean

Purpose

Review MEAN stack code (Express + MongoDB backend and React frontend) for quality, security, architecture compliance, and best practices. Produce structured review verdicts that either approve the code or send it back to developers with specific, actionable feedback.

Key Patterns

Review Dimensions

Architecture Compliance — Does code match architect designs? Models match DB schema? Controllers match API contracts? Components match React design?
Security — No exposed secrets, proper auth checks, input validation, XSS prevention
Error Handling — All errors caught, proper status codes, user-friendly messages
Performance — Indexed queries, pagination, no N+1 queries, React memoization where needed
Code Quality — Consistent patterns, DRY, proper naming, no dead code
Best Practices — MEAN-specific patterns followed (Mongoose middleware, Express middleware chain, React hooks rules)

Backend Review Checklist

Models have validators, indexes, timestamps, toJSON transform
Controllers use asyncHandler wrapper
Routes apply auth + validation middleware correctly
Error handler catches Mongoose errors (ValidationError, CastError, 11000)
Passwords hashed with bcrypt, select: false on schema
JWT properly signed and verified
No raw user input in queries (injection prevention)
Environment variables used for secrets

Frontend Review Checklist

Functional components with hooks only
API calls go through services/api.js, not raw axios/fetch
Loading states on all async operations
Error states with retry on all data fetches
Auth context wraps the app, ProtectedRoute guards private pages
No prop drilling deeper than 2 levels
Keys on all list-rendered elements
Responsive design works on mobile

Issue Severity

Critical — Must fix: security vulnerability, data loss risk, broken functionality, auth bypass
Warning — Should fix: performance issue, poor UX, missing error handling, code smell
Info — Nice to have: style improvement, alternative approach

Verdict Logic

PASS — Zero critical issues. Warnings noted but don't block.
FAIL — One or more critical issues. Code goes back to developers with fix instructions.

Conventions

Review BOTH backend and frontend in a single pass
Every issue must be actionable — say what's wrong AND how to fix it
Reference specific files and code patterns
Don't nitpick style if functionality is correct
If same issue in multiple files, report once with "also in: file1, file2"
Maximum 2 review loops — after 2 rounds, remaining warnings ship as tech debt
Include machine-readable JSON verdict block at end of output

Knowledge Strategy

Patterns to capture: Common issues in MEAN apps, security vulnerabilities specific to Node.js/MongoDB/React
Examples to collect: Good review verdicts, patterns that consistently cause issues
Update permission: Agents may freely add/update files in references/. Changes to SKILL.md or scripts/ require user approval.