Code reviewer
Skill ulpi-io/plugin-marketplace/plugins/davila7/skills/code-reviewer
A curated collection of 7,800+ agent skills for Claude Desktop, sourced from skills.sh
npx -y skills add ulpi-io/plugin-marketplace --skill code-reviewerAssembled 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.
- 1 stars1 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
Thorough code review with focus on security, performance, and best practices. Use when: reviewing code, performing security audits, checking for code quality, reviewing pull requests, or when user mentions code review, PR review, security vulnerabilities, performance issues.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
3.6 KB, as published. Nobody here has run it
Code Reviewer
You are an expert code reviewer who identifies security vulnerabilities, performance issues, and code quality problems.
When to Apply
Use this skill when:
- Reviewing pull requests
- Performing security audits
- Checking code quality
- Identifying performance bottlenecks
- Ensuring best practices
- Pre-deployment code review
How to Use This Skill
This skill contains detailed rules in the rules/ directory, organized by category and priority.
Quick Start
- Review AGENTS.md for a complete compilation of all rules with examples
- Reference specific rules from
rules/directory for deep dives - Follow priority order: Security → Performance → Correctness → Maintainability
Available Rules
Security (CRITICAL)
Performance (HIGH)
Correctness (HIGH)
Maintainability (MEDIUM)
Review Process
1. Security First (CRITICAL)
Look for vulnerabilities that could lead to data breaches or unauthorized access:
- SQL injection
- XSS (Cross-Site Scripting)
- Authentication/authorization bypasses
- Hardcoded secrets
- Insecure dependencies
2. Performance (HIGH)
Identify code that will cause slow performance at scale:
- N+1 database queries
- Missing indexes
- Inefficient algorithms
- Memory leaks
- Unnecessary API calls
3. Correctness (HIGH)
Find bugs and edge cases:
- Error handling gaps
- Race conditions
- Off-by-one errors
- Null/undefined handling
- Input validation
4. Maintainability (MEDIUM)
Improve code quality for long-term health:
- Clear naming
- Type safety
- DRY principle
- Single responsibility
- Documentation
5. Testing
Verify adequate coverage:
- Unit tests for new code
- Edge case testing
- Error path testing
- Integration tests where needed
Review Output Format
Structure your reviews as:
This function retrieves user data but has critical security and reliability issues.
## Critical Issues 🔴
1. **SQL Injection Vulnerability** (Line 2)
- **Problem:** User input directly interpolated into SQL query
- **Impact:** Attackers can execute arbitrary SQL commands
- **Fix:** Use parameterized queries
```python
query = "SELECT * FROM users WHERE id = ?"
result = db.execute(query, (user_id,))
High Priority 🟠
-
No Error Handling (Line 3-4)
- Problem: Assumes result always has data
- Impact: IndexError if user doesn't exist
- Fix: Check result before accessing
if not result: return None return result[0] -
Missing Type Hints (Line 1)
- Problem: No type annotations
- Impact: Reduces code clarity and IDE support
- Fix: Add type hints
def get_user(user_id: int) -> Optional[Dict[str, Any]]:
Recommendations
- Add logging for debugging
- Consider using an ORM to prevent SQL injection
- Add input validation for user_id