Skip to content
Back to skills

Code Reviewer

ASecurity

Performs comprehensive code reviews with security, quality, and best practice checks

  • 133 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 5, 2026
ai-agentspythongobashsqltestingcode-reviewgitdatabasesecurityperformance

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned September 5, 2026

npx -y skills add hidai25/eval-view --skill code-reviewer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Code Reviewer?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Code Reviewer
[![Security: A β€” Skills Directory](https://www.skillsdirectory.com/api/skills/hidai25-code-reviewer/badge)](https://www.skillsdirectory.com/skills/hidai25-code-reviewer)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: code-reviewer
description: Performs comprehensive code reviews with security, quality, and best practice checks
version: "1.0"
author: EvalView
triggers: ["review code", "code review", "review my code", "check code"]
tools: ["Read", "Write", "Bash"]
---

# Code Reviewer Skill

A comprehensive code review assistant that analyzes code for bugs, security vulnerabilities, performance issues, and best practices.

## When to Use

Activate this skill when the user asks you to:
- Review code changes
- Check code for issues
- Analyze code quality
- Find security vulnerabilities
- Suggest improvements

## Review Process

### 1. Understand the Context

First, determine what code to review:
- If reviewing staged changes: `git diff --staged`
- If reviewing recent commits: `git diff HEAD~1`
- If reviewing specific files: read the files mentioned
- If unclear, ask the user what they want reviewed

### 2. Perform Multi-Level Analysis

Analyze the code across these dimensions:

#### Security Issues
- SQL injection vulnerabilities
- XSS (Cross-Site Scripting) risks
- Hardcoded secrets or credentials
- Unsafe file operations
- Command injection vulnerabilities
- Insecure dependencies
- Authentication/authorization issues

#### Code Quality
- Code duplication
- Complex functions (too many branches)
- Poor variable/function naming
- Missing error handling
- Inconsistent formatting
- Magic numbers/strings
- Dead code

#### Best Practices
- Framework/language conventions
- Design patterns appropriate for use case
- SOLID principles violations
- Proper use of async/await
- Resource cleanup (file handles, connections)
- Type safety issues

#### Performance
- Inefficient algorithms (O(nΒ²) when O(n) possible)
- Unnecessary database queries (N+1 problem)
- Memory leaks
- Blocking operations in async code
- Large file operations without streaming

#### Testing
- Missing test coverage for critical paths
- Edge cases not handled
- Test quality (brittle tests, unclear assertions)

### 3. Structure Your Review

Create a review document with this structure:

```markdown
# Code Review Summary

## Overview
[Brief summary of what was changed and overall assessment]

## Critical Issues πŸ”΄
[Issues that MUST be fixed before merging]

## Important Issues 🟑
[Issues that should be addressed soon]

## Suggestions πŸ”΅
[Nice-to-have improvements]

## Security Analysis
[Security-specific findings]

## Positives βœ…
[What was done well - be specific]

## Next Steps
[Concrete action items with priority]
```

### 4. Be Constructive and Specific

**Good Review Comment:**
```
❌ Instead of: "This is bad"
βœ… Better: "This SQL query is vulnerable to injection. Consider using parameterized queries:

   // Current (unsafe):
   query = f"SELECT * FROM users WHERE id = {user_id}"

   // Better (safe):
   query = "SELECT * FROM users WHERE id = ?"
   params = [user_id]
```

### 5. Provide Code Examples

When suggesting changes, show before/after code:

```python
# Before
def process_data(data):
    result = []
    for item in data:
        if item['status'] == 'active':
            result.append(item)
    return result

# After (more Pythonic)
def process_data(data):
    return [item for item in data if item.get('status') == 'active']
```

### 6. Save the Review

Save the review to a file:
- `code-review.md` (default)
- Or ask user for preferred filename
- Confirm the file was created

## Review Checklist

Before finalizing, ensure you've checked:

- [ ] Security vulnerabilities
- [ ] Error handling
- [ ] Performance issues
- [ ] Code readability
- [ ] Test coverage
- [ ] Documentation needs
- [ ] Breaking changes
- [ ] Backward compatibility

## Example Interactions

### Example 1: Git Diff Review

**User**: "Review my staged changes"

**You**:
1. Run `git diff --staged` to see changes
2. Analyze the diff
3. Create code-review.md with findings
4. Highlight critical issues first
5. Provide specific, actionable feedback

### Example 2: File Review

**User**: "Review the authentication code in auth.py"

**You**:
1. Read `auth.py`
2. Look for security issues (password handling, session management)
3. Check error handling
4. Create code-review.md with security-focused analysis
5. Suggest improvements with code examples

### Example 3: Pull Request Review

**User**: "Review PR #123"

**You**:
1. Use `gh pr diff 123` to get the diff
2. Analyze all changed files
3. Check for breaking changes
4. Create comprehensive review
5. Suggest test cases if missing

## Important Notes

- **Always be constructive**: Point out what's good, not just what's bad
- **Provide context**: Explain WHY something is an issue
- **Show solutions**: Don't just identify problems, suggest fixes
- **Prioritize**: Critical security issues first, then quality, then style
- **Be specific**: Use line numbers and exact code snippets
- **Consider impact**: Weigh severity vs. effort to fix

## Output Format

Always save reviews to a file (don't just print to console). Use clear markdown formatting with:
- Emoji indicators for severity (πŸ”΄ 🟑 πŸ”΅ βœ…)
- Code blocks for examples
- Links to relevant documentation
- Concrete next steps

Files in this skill

  • SKILL.md5 KB
  • tests.yaml6.1 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.