codex-review
Professional code review with auto CHANGELOG generation, integrated with Codex AI. Use when you want professional code review before commits, you need automatic CHANGELOG generation, or reviewing large-scale refactoring.
About this skill
The `codex-review` skill offers advanced capabilities for professional-grade code review, leveraging the intelligence of Codex AI. It automates the process of analyzing code changes, providing insightful feedback, and automatically generating a `CHANGELOG` entry. This skill is particularly useful for ensuring code quality and consistency before committing changes, streamlining the review process for large-scale refactorings, and maintaining project documentation effortlessly. It integrates with Codex AI for deep code understanding and suggestion generation, enhancing the development workflow.
Best use case
This skill is designed for developers and teams seeking to enhance their code quality assurance workflow. It's ideal for pre-commit code scrutiny, automating the often tedious task of `CHANGELOG` creation, and efficiently managing reviews for substantial code overhauls or refactoring projects.
Professional code review with auto CHANGELOG generation, integrated with Codex AI. Use when you want professional code review before commits, you need automatic CHANGELOG generation, or reviewing large-scale refactoring.
Detailed, AI-powered code review feedback and suggestions for improvements. Automatically generated and formatted CHANGELOG entries reflecting the code changes. Increased code quality, maintainability, and consistency. Reduced manual effort in code review and documentation.
Practical example
Example input
Review the following Python code for best practices and potential bugs, and generate a CHANGELOG entry:
```python
def calculate_area(radius):
"""Calculates the area of a circle."""
import math
return math.pi * radius ** 2
# New feature: calculate circumference
def calculate_circumference(radius):
"""Calculates the circumference of a circle."""
import math
return 2 * math.pi * radius
```Example output
```json
{
"review_summary": "The code introduces a new function for calculating circumference. Both functions correctly use `math.pi` for precision.",
"suggestions": [
{"line": 3, "severity": "info", "suggestion": "It's good practice to place imports at the top of the file, not within function bodies, to avoid repeated imports.", "code_change": "import math\n\ndef calculate_area(radius):"}
],
"changelog_entry": "### Added\n- New function `calculate_circumference` to calculate the circumference of a circle.\n\n### Changed\n- Ensured `calculate_area` uses `math.pi` for better precision.",
"overall_score": 9.0,
"issues_found": 0
}
```When to use this skill
- Before committing code, for a professional-level review.
- When you need automatic CHANGELOG generation.
- When reviewing large-scale refactoring efforts.
When not to use this skill
- For very minor bug fixes or trivial changes that don't warrant a full AI review.
- When working with highly sensitive proprietary code that cannot be exposed to external AI services.
- When a purely human, subjective, or stylistic code review is preferred without AI intervention.
- For immediate, rapid prototyping where strict code quality checks might hinder initial development speed.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/codex-review/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How codex-review Compares
| Feature / Agent | codex-review | Standard Approach |
|---|---|---|
| Platform Support | Claude, Codex | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | medium | N/A |
Frequently Asked Questions
What does this skill do?
Professional code review with auto CHANGELOG generation, integrated with Codex AI. Use when you want professional code review before commits, you need automatic CHANGELOG generation, or reviewing large-scale refactoring.
Which AI agents support this skill?
This skill is designed for Claude, Codex.
How difficult is it to install?
The installation complexity is rated as medium. You can find the installation instructions above.
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
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
SKILL.md Source
# codex-review ## Overview Professional code review with auto CHANGELOG generation, integrated with Codex AI ## When to Use - When you want professional code review before commits - When you need automatic CHANGELOG generation - When reviewing large-scale refactoring ## Installation ```bash npx skills add -g BenedictKing/codex-review ``` ## Step-by-Step Guide 1. Install the skill using the command above 2. Ensure Codex CLI is installed 3. Use `/codex-review` or natural language triggers ## Examples See [GitHub Repository](https://github.com/BenedictKing/codex-review) for examples. ## Best Practices - Keep CHANGELOG.md in your project root - Use conventional commit messages ## Troubleshooting See the GitHub repository for troubleshooting guides. ## Related Skills - context7-auto-research, tavily-web, exa-search, firecrawl-scraper
Related Skills
code-review-checklist
Comprehensive checklist for conducting thorough code reviews covering functionality, security, performance, and maintainability
data-structure-protocol
Give agents persistent structural memory of a codebase — navigate dependencies, track public APIs, and understand why connections exist without re-reading the whole repo.
code-refactoring-context-restore
Use when working with code refactoring context restore
code-documentation-code-explain
You are a code education expert specializing in explaining complex code through clear narratives, visual diagrams, and step-by-step breakdowns. Transform difficult concepts into understandable explanations for developers at all levels.
c4-architecture-c4-architecture
Generate comprehensive C4 architecture documentation for an existing repository/codebase using a bottom-up analysis approach.
lightning-architecture-review
Review Bitcoin Lightning Network protocol designs, compare channel factory approaches, and analyze Layer 2 scaling tradeoffs. Covers trust models, on-chain footprint, consensus requirements, HTLC/PTLC compatibility, liveness, and watchtower support.
gha-security-review
Find exploitable vulnerabilities in GitHub Actions workflows. Every finding MUST include a concrete exploitation scenario — if you can't build the attack, don't report it.
gh-review-requests
Fetch unread GitHub notifications for open PRs where review is requested from a specified team or opened by a team member. Use when asked to "find PRs I need to review", "show my review requests", "what needs my review", "fetch GitHub review requests", or "check team review queue".
fix-review
Verify fix commits address audit findings without new bugs
error-debugging-multi-agent-review
Use when working with error debugging multi agent review
django-perf-review
Django performance code review. Use when asked to "review Django performance", "find N+1 queries", "optimize Django", "check queryset performance", "database performance", "Django ORM issues", or audit Django code for performance problems.
django-access-review
django-access-review