ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified developer tools Safety 5/5

critical-code-reviewer

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.

Why use this skill?

Use the Critical Code Reviewer to ruthlessly audit your code. Find security holes, bad patterns, and performance issues with expert-level scrutiny.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/ziad-hsn/critical-code-reviewer
Or

What This Skill Does

The critical-code-reviewer is a high-octane adversarial code analysis agent designed for OpenClaw. It shifts the paradigm from polite code review to ruthless quality control. By adopting a 'guilty until proven exceptional' mindset, the agent systematically dismantles code submissions to find security vulnerabilities, architectural flaws, and performance bottlenecks. It does not just look for syntax errors; it evaluates logic, abstraction, and adherence to professional standards, ensuring your codebase remains resilient against entropy and 'code rot.'

Installation

To integrate this agent into your workflow, use the OpenClaw terminal command: clawhub install openclaw/skills/skills/ziad-hsn/critical-code-reviewer

Use Cases

Use this skill when you need a senior-level audit of your work. It is perfect for:

  • Pre-merge pull request reviews to ensure standards are met.
  • Troubleshooting legacy codebases suffering from 'junk drawer' organization.
  • Security auditing for sensitive functions or input-handling logic.
  • Mentoring junior developers by forcing them to confront sloppy patterns and anti-patterns.
  • Refactoring sessions where you need to identify dead code or premature abstractions.

Example Prompts

  1. "Critically review this React component. I'm worried about performance and prop drilling, but tell me everything else that's wrong with it."
  2. "I need you to find every issue in this Python data processing script. Focus on edge cases, error handling, and memory efficiency."
  3. "What's wrong with this SQL query? It works, but it feels fragile and slow."

Tips & Limitations

  • Be Ready for Brutal Honesty: The agent is designed to be blunt. Do not use this skill if you are looking for soft, encouraging feedback.
  • Focus on Context: While the agent can read standalone snippets, providing the surrounding context (e.g., framework, intended scale, or security constraints) will lead to much sharper, more relevant critiques.
  • Not for Syntax Fixing: While it will catch errors, its primary value is in identifying structural, logical, and best-practice failures rather than simply fixing typos.
  • Incremental Reviews: To get the best results, submit files or modules in manageable chunks; monolithic file submissions may limit the depth of the adversarial audit.

Metadata

Author@ziad-hsn
Stars879
Views1
Updated2026-02-11
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-ziad-hsn-critical-code-reviewer": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#code-review#static-analysis#security-audit#developer-productivity#refactoring
Safety Score: 5/5