Refactor high-complexity React components in Dify frontend. Use when `pnpm analyze-component...
npx skills add DonTizi/CodeGeass --skill "review"
Install specific skill from multi-skill repository
# Description
Comprehensive code review for PRs or recent changes. Checks correctness, security, performance, maintainability, and tests.
# SKILL.md
name: review
description: Comprehensive code review for PRs or recent changes. Checks correctness, security, performance, maintainability, and tests.
context: fork
agent: Explore
allowed-tools: Read, Grep, Glob, Bash(git diff ), Bash(git log ), Bash(git status), Bash(git show *)
disable-model-invocation: true
Code Review Instructions
Review the code for:
- Correctness: Logic errors, edge cases, null handling
- Security: Injection, XSS, secrets exposure, auth issues
- Performance: N+1 queries, unnecessary loops, memory leaks
- Maintainability: Complexity, naming, documentation
- Tests: Coverage, edge cases, meaningful assertions
Dynamic Context
- Recent changes: !
git diff HEAD~5 --stat 2>/dev/null || echo "No recent changes" - Current branch: !
git branch --show-current 2>/dev/null || echo "unknown" - Uncommitted changes: !
git status --short 2>/dev/null || echo "Not a git repo"
Review Process
- Gather Context
- Check
git statusfor current state - Review
git difffor recent changes -
Identify the most modified files
-
Analyze Code
- Focus on files with recent changes
- Check for security issues (hardcoded secrets, SQL injection, XSS)
- Look for performance problems
-
Evaluate code organization and readability
-
Provide Feedback
- Be specific with file paths and line numbers
- Explain why something is an issue
- Suggest concrete fixes
- Rate severity
Severity Ratings
Format: Provide feedback as:
- Critical: Must fix before merge
- Important: Should fix, but not blocking
- Suggestion: Nice to have improvements
Output Format
Return a structured report:
{
"summary": "Brief overview of code health",
"files_reviewed": ["list of files"],
"issues": [
{
"file": "path/to/file.py",
"line": 42,
"severity": "critical|important|suggestion",
"category": "security|performance|correctness|maintainability",
"description": "What's wrong",
"suggestion": "How to fix it"
}
],
"recommendations": [
"General improvement suggestions"
],
"metrics": {
"total_issues": 5,
"critical": 0,
"important": 1,
"suggestions": 4
}
}
$ARGUMENTS
# Supported AI Coding Agents
This skill is compatible with the SKILL.md standard and works with all major AI coding agents:
Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.