How to Get Started with Critical Code Reviewer in Your AI Workflow

Critical Code Reviewer is a powerful AI agent skill that extends your assistant with new capabilities. Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations. This guide walks you through installing Critical Code Reviewer, configuring it for your setup, and running your first commands — so you can start getting value in minutes.

Step-by-Step Guide

1. 1

   Install Critical Code Reviewer: npx clawhub@latest --dir ~/.claude/skills install critical-code-reviewer

2. 2

   Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)

3. 3

   Type a natural language request related to developer & devops to trigger Critical Code Reviewer

4. 4

   Review the output and refine your prompt for better results

5. 5

   Combine Critical Code Reviewer with other skills to build multi-step workflows

Example Prompts

Copy these prompts and use them with your AI agent after installing Critical Code Reviewer

More Use Cases for Critical Code Reviewer