How do I install the Code Review skill?

Run npx skillmds@latest add tomevault-io/code-review-299 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Code Review safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Code Review?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Code Review free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Code Review?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Code Review by tomevault-io — Agent Skill

Name: Code Review
Author: tomevault-io

Code Review

Perform a maximally picky and professional code review of recent changes. Reviews all code added since the last review, checking for thread safety, async safety, security vulnerabilities, data integrity, test quality, and code smells. Use before committing significant changes. Use when this capability is needed.

tomevault-io Updated Sep 17, 2026

File contents

Code Review Skill

Perform a professional code review following the standards in prompts/CODE_REVIEW.md.

When to Use

Before committing significant code changes
After completing a spike or feature
When the Stop hook reminds you
When explicitly requested by user

Process

Identify scope - Determine what code needs review:
- Check git status and git diff for uncommitted changes
- Check git log to find commits since last review
- Look for any existing code review documents to find the last review point
Read the review template - Load prompts/CODE_REVIEW.md for the full criteria
Perform the review - Apply all criteria from the template:
- MANDATORY: No Quick Hacks policy
- Race Condition Audit Checklist
- Critical issues (thread safety, async safety, security, data integrity)
- High priority (type hints, input validation, logging, test coverage)
- Medium priority (magic numbers, hard-coded config, duplication)
- Test quality (primary use cases tested, no anti-patterns)
Write the review document - Save to .claude/plans/ with:
- Executive summary
- Issues grouped by severity with file:line references
- Specific code fixes (before/after)
- Checklist of items to fix
- Verification steps
- Notes for future work
Report the path - Tell the user where to find the review document

Key Principles

Be specific and critical
Every issue needs a file:line reference
Provide concrete fixes, not just descriptions
Consider whether code enables future architectural goals
Quick hacks are absolutely forbidden

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: code-review-299description: Perform a maximally picky and professional code review of recent changes. Reviews all code added since the last review, checking for thread safety, async safety, security vulnerabilities, data integrity, test quality, and code smells. Use before committing significant changes. Use when this capability is needed.---# Code Review SkillPerform a professional code review following the standards in `prompts/CODE_REVIEW.md`.## When to Use- Before committing significant code changes- After completing a spike or feature- When the Stop hook reminds you- When explicitly requested by user## Process1. **Identify scope** - Determine what code needs review: - Check `git status` and `git diff` for uncommitted changes - Check `git log` to find commits since last review - Look for any existing code review documents to find the last review point2. **Read the review template** - Load `prompts/CODE_REVIEW.md` for the full criteria3. **Perform the review** - Apply all criteria from the template: - MANDATORY: No Quick Hacks policy - Race Condition Audit Checklist - Critical issues (thread safety, async safety, security, data integrity) - High priority (type hints, input validation, logging, test coverage) - Medium priority (magic numbers, hard-coded config, duplication) - Test quality (primary use cases tested, no anti-patterns)4. **Write the review document** - Save to `.claude/plans/` with: - Executive summary - Issues grouped by severity with file:line references - Specific code fixes (before/after) - Checklist of items to fix - Verification steps - Notes for future work5. **Report the path** - Tell the user where to find the review document## Key Principles- Be specific and critical- Every issue needs a file:line reference- Provide concrete fixes, not just descriptions- Consider whether code enables future architectural goals- Quick hacks are absolutely forbidden---> Converted and distributed by [TomeVault](https://tomevault.io/claim/mqfacultyofarts) — claim your Tome and manage your conversions.

Frequently asked questions