mcpField
C
code-review

code-review

github.com/langchain-aiTesting & quality30.8k213 installsUpdated today
Repository

About code-review

A code-review skill for developers and coding agents to check implemented changes before delivery. It combines a checklist for correctness, quality, tests, and safety with a defined review process and helper lint script.

Key features

  1. 01Correctness and edge-case checklist
  2. 02Code quality review
  3. 03Test coverage and execution steps
  4. 04Security and input-safety checks
  5. 05Bundled Python lint script

Use cases

  1. 01Reviewing changes before delivery
  2. 02Checking test coverage and failure cases
  3. 03Scanning Python code for common lint issues

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/langchain-ai/deepagents --skill code-review

After installing, type/code-reviewin Claude Code to confirm it loaded.

Bundled fileslint_check.py

Details

From the project README

Code Review Skill

Use this skill after implementing changes to validate your work before delivering.

Review Checklist

1. Correctness
  • Changes solve the original issue/task
  • No unintended side effects on existing functionality
  • Edge cases are handled
  • Error handling is appropriate (not excessive)
2. Code Quality
  • Code matches existing style and patterns
  • No unnecessary complexity or abstraction
  • Variable and function names are clear
  • No dead code, commented-out code, or TODOs left behind
3. Tests
  • New functionality has test coverage
  • Existing tests still pass
  • Tests cover both happy path and error cases
  • Tests are not brittle (don't test implementation details)
4. Safety
  • No hardcoded secrets or credentials
  • User input is validated at boundaries
  • No SQL injection, XSS, or command injection vectors
  • File operations use safe paths

Process

  1. Read each modified file end-to-end (not just the diff)
  2. Run the test suite: execute("python -m pytest -v")
  3. Run linters if available: execute("ruff check .")
  4. Run the bundled lint check: execute("python /skills/code-review/lint_check.py .")
  5. Check against each item in the review checklist
  6. If any issues found, fix them and re-review
  7. When everything passes, the review is complete

Helper Scripts

  • /skills/code-review/lint_check.py — Scans Python files for missing docstrings, long functions (>50 lines), and bare except: clauses. Run it via execute("python /skills/code-review/lint_check.py [path ...]").

Comments

Markdown supported