critical-code-reviewer

Run multi-persona critical code reviews with severity-classified findings.

5|4|Updated Nov 9, 2025
One-click install
npx skills add https://github.com/takusaotome/claude-skills-library --skill critical-code-reviewer-takusaotome
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: critical-code-reviewer
Source: https://github.com/takusaotome/claude-skills-library/tree/main/skills/critical-code-reviewer
Command: npx skills add https://github.com/takusaotome/claude-skills-library --skill critical-code-reviewer-takusaotome

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

This Skill helps you perform a comprehensive critical code review by identifying design quality issues, poor testability, readability problems, and likely runtime bugs before they reach production.

Core Features & Use Cases

  • Multi-persona review: Runs parallel reviews using four expert perspectives (Veteran Engineer, TDD Expert, Clean Code Expert, Bug Hunter) to surface issues from multiple angles.
  • Language-aware checkpoints: Applies extra checks for Python and JavaScript/TypeScript, including type-safety and async error patterns.
  • Bug-focused resilience analysis: The Bug Hunter persona targets state transitions, exception paths, dependency completeness, and async/concurrency race risks.
  • Integrated severity and actionable output: Deduplicates findings, assigns severity using authoritative criteria, and generates a structured report template.

Quick Start

Review a codebase by telling the AI to run a critical code review on your pull request or the specific files you want assessed.

Frequently Asked Questions about critical-code-reviewer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I find design flaws and runtime bugs before merging a pull request?

To find design flaws and runtime bugs before merging a pull request, you can run a multi-persona critical code review that analyzes testability, readability, and state transitions across your codebase to identify production risks.

What is the best way to perform a critical code review on Python and JavaScript code?

The best way to perform a critical code review on Python and JavaScript code is to apply language-aware checkpoints that scan for type-safety issues and async error patterns while concurrently checking for general design quality and bug risks.

How does a multi-persona code review identify testability and concurrency issues?

A multi-persona code review identifies testability and concurrency issues by running parallel expert perspectives, including a TDD expert and a bug hunter, to analyze exception paths, dependency completeness, and async race risks.

Can I use critical code review for refactoring and troubleshooting existing codebases?

Yes, you can use critical code review for refactoring and troubleshooting existing codebases, as the review process deduplicates findings, assigns severity triage, and generates a structured report to guide code quality improvements.

Does the critical code review process provide severity classification for detected bugs?

Yes, the critical code review process provides severity classification for detected bugs by deduplicating evidence-backed findings and assigning severity levels using authoritative criteria to generate a consolidated report.