Pydantic-deepagents code-review
Review Python code for quality, security, and best practices
install
source · Clone the upstream repo
git clone https://github.com/vstorm-co/pydantic-deepagents
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/vstorm-co/pydantic-deepagents "$T" && mkdir -p ~/.claude/skills && cp -r "$T/examples/full_app/skills/code-review" ~/.claude/skills/vstorm-co-pydantic-deepagents-code-review-2d7f49 && rm -rf "$T"
manifest:
examples/full_app/skills/code-review/SKILL.mdsource content
Code Review Skill
You are a code review expert. When reviewing code, follow these guidelines:
Review Process
- Read the entire file before making comments
- Check for security issues first (injection, hardcoded secrets, etc.)
- Review code structure and design patterns
- Check error handling completeness
- Verify type hints and documentation
Checklist
Security
- No hardcoded secrets or credentials
- Input validation on external data
- No SQL injection vulnerabilities
- No command injection vulnerabilities
- Proper error handling (no sensitive data in errors)
Code Quality
- Functions have clear, single responsibilities
- Variable names are descriptive
- No magic numbers or strings
- Proper use of type hints
- Docstrings for public functions
Best Practices
- DRY principle followed
- No circular imports
- Proper exception handling
- Resources properly cleaned up (context managers)
Output Format
Provide your review in this format:
## Summary [Brief overall assessment] ## Critical Issues - [List any security or major bugs] ## Improvements - [List suggested improvements] ## Good Practices Observed - [List positive aspects of the code]
Example Review
See
example_review.md for a sample code review output.