skill-code-review

Perform thorough, constructive code reviews focusing on correctness, security, maintainability, and best practices

16 stars

Best use case

skill-code-review is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Perform thorough, constructive code reviews focusing on correctness, security, maintainability, and best practices

Teams using skill-code-review should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/skill-code-review/SKILL.md --create-dirs "https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/main/skills/development/skill-code-review/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/skill-code-review/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How skill-code-review Compares

Feature / Agentskill-code-reviewStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Perform thorough, constructive code reviews focusing on correctness, security, maintainability, and best practices

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# skill-code-review


# Code Review Skill Instructions

## Purpose
Conduct comprehensive code reviews that improve code quality, catch bugs early, ensure security, and promote team learning through constructive feedback.

## When to Use
- Pull request reviews
- Pre-merge code inspections
- Security audits
- Refactoring validation
- New feature implementation reviews

---

## Review Process

### 1. Understand Context First
- Read the PR/change description and linked issues
- Understand the **intent** and **scope** of the change
- Check if tests and documentation are included
- Review the overall architecture impact

### 2. Review Checklist

#### ✅ Correctness
- [ ] Does the code do what it's supposed to do?
- [ ] Are edge cases handled properly?
- [ ] Is the logic correct and complete?
- [ ] Are there any off-by-one errors, null pointer issues, or race conditions?

#### 🔒 Security
- [ ] Input validation and sanitization
- [ ] No hardcoded secrets, API keys, or credentials
- [ ] Proper authentication and authorization checks
- [ ] SQL injection, XSS, CSRF protection
- [ ] Secure handling of sensitive data
- [ ] Dependencies free of known vulnerabilities

#### 🏗️ Architecture & Design
- [ ] Follows SOLID principles
- [ ] Appropriate separation of concerns
- [ ] No unnecessary coupling between components
- [ ] Consistent with existing patterns in the codebase
- [ ] Scalability considerations addressed

#### 📖 Readability & Maintainability
- [ ] Clear, descriptive naming (variables, functions, classes)
- [ ] Functions are small and do one thing well
- [ ] No magic numbers or strings (use constants)
- [ ] Complex logic is commented or self-documenting
- [ ] No dead code or commented-out code blocks

#### ⚡ Performance
- [ ] No N+1 queries or unnecessary database calls
- [ ] Efficient algorithms and data structures
- [ ] Proper caching where appropriate
- [ ] No memory leaks or resource exhaustion risks
- [ ] Async operations used correctly

#### 🧪 Testing
- [ ] Unit tests cover new functionality
- [ ] Edge cases and error paths tested
- [ ] Tests are readable and maintainable
- [ ] No flaky or brittle tests
- [ ] Integration tests where appropriate

#### 📝 Documentation
- [ ] Public APIs documented
- [ ] Complex business logic explained
- [ ] README updated if needed
- [ ] Breaking changes documented

---

## Feedback Guidelines

### Be Constructive
```
❌ "This code is bad"
✅ "Consider extracting this into a separate function for better testability"
```

### Be Specific
```
❌ "Fix the naming"
✅ "Rename `data` to `userProfile` to clarify its purpose"
```

### Explain the Why
```
❌ "Don't use var"
✅ "Use `const` instead of `var` to prevent accidental reassignment and improve code clarity"
```

### Categorize Feedback Severity

| Prefix | Meaning | Action Required |
|--------|---------|-----------------|
| 🚨 **BLOCKER** | Critical issue, must fix | Cannot merge |
| ⚠️ **WARNING** | Should fix, potential problem | Strongly recommended |
| 💡 **SUGGESTION** | Improvement opportunity | Optional |
| ❓ **QUESTION** | Clarification needed | Please explain |
| 👍 **PRAISE** | Great work! | Keep it up |

---

## Comment Templates

### Security Issue
```
🚨 **BLOCKER - Security**: User input is not sanitized before being used in the SQL query. 
This creates a SQL injection vulnerability.

**Suggestion**: Use parameterized queries or an ORM to safely handle user input.
```

### Performance Concern
```
⚠️ **WARNING - Performance**: This loop makes a database call on each iteration, 
resulting in N+1 queries.

**Suggestion**: Batch the queries or use eager loading to fetch all data upfront.
```

### Code Quality Suggestion
```
💡 **SUGGESTION**: This function is 80 lines long with multiple responsibilities.

Consider splitting into:
- `validateInput()` - Input validation
- `processData()` - Core business logic  
- `formatResponse()` - Response formatting
```

### Positive Feedback
```
👍 **PRAISE**: Excellent error handling here! The fallback mechanism and 
detailed logging will make debugging much easier.
```

---

## Review Output Format

Structure your review as follows:

```markdown
## Code Review Summary

**Overall Assessment**: ✅ Approved | ⚠️ Needs Changes | 🚨 Request Changes

### Overview
Brief summary of what was reviewed and overall impressions.

### Critical Issues (Must Fix)
- Issue 1 with location and fix suggestion
- Issue 2 with location and fix suggestion

### Recommendations (Should Fix)
- Recommendation 1
- Recommendation 2

### Suggestions (Nice to Have)
- Suggestion 1
- Suggestion 2

### Positive Highlights
- What was done well

### Questions
- Any clarifications needed
```

---

## Best Practices

1. **Review in small batches** - Keep PRs small (<400 lines) for effective review
2. **Take your time** - Don't rush; bugs missed in review are expensive later
3. **Be respectful** - Review the code, not the person
4. **Assume good intent** - Authors did their best with available information
5. **Offer alternatives** - Don't just criticize; provide solutions
6. **Learn together** - Reviews are learning opportunities for everyone
7. **Follow up** - Verify fixes address the concerns raised

---

## Anti-Patterns to Avoid

- ❌ Nitpicking style issues (use linters instead)
- ❌ Rewriting someone's code in your style
- ❌ Blocking PRs for subjective preferences
- ❌ Reviewing without understanding context
- ❌ Being vague or unconstructive
- ❌ Ignoring positive aspects of the code

Related Skills

sop-code-review

16
from diegosouzapw/awesome-omni-skill

Comprehensive code review workflow coordinating quality, security, performance, and documentation reviewers. 4-hour timeline for thorough multi-agent review.

software-code-review

16
from diegosouzapw/awesome-omni-skill

Use when reviewing code, pull requests, or diffs. Provides patterns, checklists, and templates for systematic code review with a focus on correctness, security, readability, performance, and maintainability.

semgrep-coderabbit-review

16
from diegosouzapw/awesome-omni-skill

Two-stage code review combining fast pattern detection (Semgrep) with AI-powered semantic analysis (CodeRabbit)

security-review

16
from diegosouzapw/awesome-omni-skill

Performs security reviews of Hone code using OWASP guidelines. Use when reviewing database queries, CSV import logic, API endpoints, authentication, encryption, or when the user asks about security.

reviewing-python-architecture

16
from diegosouzapw/awesome-omni-skill

Review ADRs to check they follow testing principles and parent PDR constraints. Use when reviewing ADRs or architecture decisions.

review-implementation

16
from diegosouzapw/awesome-omni-skill

Use after hyperpowers:executing-plans completes all tasks - verifies implementation against bd spec, all success criteria met, anti-patterns avoided

review-fix

16
from diegosouzapw/awesome-omni-skill

Read the latest code review, plan fixes for all findings, then execute the fixes — all in one command. Produces a dated plan and execution log in .reviews/.

review-changes

16
from diegosouzapw/awesome-omni-skill

[Review & Quality] Review all uncommitted changes before commit

review-architecture

16
from diegosouzapw/awesome-omni-skill

Verify DDD patterns, Clean Architecture boundaries, and bITdevKit-specific conventions in modular monolith projects

requesting-code-review

16
from diegosouzapw/awesome-omni-skill

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

receiving-code-review

16
from diegosouzapw/awesome-omni-skill

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performat...

Python Backend Architecture Review

16
from diegosouzapw/awesome-omni-skill

Comprehensive design architecture review for Python backend applications. Use this skill when users ask you to review, analyze, or provide feedback on backend architecture designs, system design documents, or Python application architecture. Covers scalability, security, performance, database design, API design, microservices patterns, deployment architecture, and best practices.