claude-review

Review code changes with a different model before merging.

407|29|Updated Mar 19, 2026
One-click install
npx skills add https://github.com/Ancienttwo/repo-harness --skill claude-review-ancienttwo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claude-review
Source: https://github.com/Ancienttwo/repo-harness/tree/main/assets/skills/claude-review
Command: npx skills add https://github.com/Ancienttwo/repo-harness --skill claude-review-ancienttwo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires claude-code-cli, and includes scripts (resource) components.

What problem does it solve?

This Skill provides an independent code review from Anthropic Claude, catching issues that the original code's model might miss.

Core Features & Use Cases

  • Cross-Model Review: Offers a second opinion from a different model to catch blind spots and errors.
  • Read-Only Review: Claude can only read and report findings, ensuring no changes are made to the code.
  • Use Case: Before merging a critical code change, use Claude to review the code for potential issues that might have been overlooked.

Quick Start

Run 'claude review' to initiate a code review by Claude.

Frequently Asked Questions about claude-review

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

FAQPage Schema
How do I get a second opinion on code changes before merging?

To get a second opinion on code changes before merging, you can run 'claude review' to initiate an independent code review by Claude, catching issues missed by the original model.

How does cross-model code review work for catching missed issues?

Cross-model code review works by utilizing a different AI model to analyze code changes, providing an independent perspective to catch blind spots and errors that the original code's model might have missed.

Do I need Claude Code CLI to perform an independent code review?

Yes, you need Claude Code CLI installed to perform an independent code review, as it provides the necessary read-only capabilities for Claude to analyze your codebase and report findings.

Can Claude modify my code during the review process?

No, Claude cannot modify your code during the review process because the service operates in a strictly read-only mode, ensuring it can only read and report findings without making any changes to your files.

When should I use an independent AI code review for my project?

You should use an independent AI code review for critical, complex, or sensitive code changes before merging, ensuring potential issues overlooked by the original model are caught.