This is your systematic code reviewer that catches what you miss in pull requests. It prioritizes security first (SQL injection, XSS, auth holes), then moves through performance bottlenecks like N+1 queries and memory leaks, code quality issues, and best practice violations. Every finding comes with before/after code snippets and severity ratings from critical to low priority. The output format is solid: grouped by urgency, includes a quick wins section for high impact fixes, and actually acknowledges what you did right. Use it when you need a thorough audit beyond linter warnings, especially on unfamiliar codebases or before production deploys.
npx -y skills add onewave-ai/claude-skills --skill code-review-pro --agent claude-codeInstalls into .claude/skills of the current project.
Deep code analysis covering security, performance, maintainability, and best practices.
Activate when the user:
Security Analysis (Critical Priority)
Performance Analysis
Code Quality & Maintainability
Best Practices
Bugs and Edge Cases
Provide Actionable Fixes
# Code Review Report
## Critical Issues (Fix Immediately)
### 1. SQL Injection Vulnerability (line X)
**Severity**: Critical
**Issue**: User input directly concatenated into SQL query
**Impact**: Database compromise, data theft
**Current Code:**
```javascript
const query = `SELECT * FROM users WHERE email = '${userEmail}'`;
Fixed Code:
const query = 'SELECT * FROM users WHERE email = ?';
db.query(query, [userEmail]);
Explanation: Always use parameterized queries to prevent SQL injection.
[Details...]
[Details...]
[Details...]
Changes with high impact and low effort:
calculateDiscount()
## Examples
**User**: "Review this authentication code"
**Response**: Analyze auth logic → Identify security issues (weak password hashing, no rate limiting) → Check token handling → Note missing CSRF protection → Provide specific fixes with code examples → Prioritize by severity
**User**: "Can you find performance issues in this React component?"
**Response**: Analyze component → Identify unnecessary re-renders → Find missing useMemo/useCallback → Note large state objects → Check for expensive operations in render → Provide optimized version with explanations
**User**: "Review this API endpoint"
**Response**: Check input validation → Analyze error handling → Test for SQL injection → Review authentication → Check rate limiting → Examine response structure → Suggest improvements with code samples
## Best Practices
- Always prioritize security issues first
- Provide specific line numbers for issues
- Include before/after code examples
- Explain *why* something is a problem
- Consider the language/framework context
- Don't just criticize—acknowledge good code too
- Suggest gradual improvements for large refactors
- Link to documentation for recommendations
- Consider project constraints (legacy code, deadlines)
- Balance perfectionism with pragmatism
- Focus on impactful changes
- Group similar issues together
- Make recommendations actionable
cursor/plugins
github/awesome-copilot
alirezarezvani/claude-skills
microsoft/win-dev-skills