code-review

Analyze diffs across commits and PRs with Writer/Reviewer separation and five-dimensional review.

Updated Mar 23, 2026
One-click install
npx skills add https://github.com/0xEdenY/eden-claude-skills --skill code-review-0xedeny
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/0xEdenY/eden-claude-skills/tree/main/code-review
Command: npx skills add https://github.com/0xEdenY/eden-claude-skills --skill code-review-0xedeny

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI 生成的代码存在系统性偏见——逻辑错误、安全漏洞、以及对自己写的代码的认知盲点。本 Skill 通过 Writer/Reviewer 分离和多维度审查来对抗这些偏见,提升代码审查的质量和客观性。

Core Features & Use Cases

  • Writer/Reviewer separation to prevent cognitive bias while reviewing code you wrote.
  • Five-dimensional review across correctness, boundaries, security, scope discipline, and maintainability.
  • Learning loop & documentation that records findings and updates rules to prevent repeat issues.
  • Use Case: In a new session, analyze a diff from a PR to produce a structured review across dimensions and generate actionable recommendations.

Quick Start

In a new session, run a full code-review workflow starting from a diff to identify issues across five dimensions.

Frequently Asked Questions about code-review

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

FAQPage Schema
How do I automate a structured code review for a PR diff?

Automate a structured code review by applying a multi-dimension workflow to PR diffs, separating the Writer and Reviewer roles to enforce checks across correctness, boundaries, security, scope discipline, and maintainability.

What is the best way to check a commit diff for security vulnerabilities and logic errors?

Check a commit diff for security vulnerabilities and logic errors by running a multi-dimensional review that specifically evaluates security and correctness, counteracting cognitive bias through Writer and Reviewer separation.

How does a Writer and Reviewer separation improve code quality assurance?

Writer and Reviewer separation improves quality assurance by preventing cognitive bias during evaluation, allowing the reviewer to objectively assess maintainability and scope discipline without blind spots from writing the code.

Can I generate a post-review report with learning notes after analyzing a diff?

You can generate a post-review report with actionable recommendations and learning notes after analyzing a diff, which records findings and updates rules to prevent repeat issues in future code reviews.

Does automated diff analysis evaluate scope discipline and maintainability?

Automated diff analysis evaluates scope discipline and maintainability as two of its five core review dimensions, ensuring structured checks across the entire commit alongside correctness, boundaries, and security.

Why should I use a multi-dimension code review workflow instead of manual checking?

Use a multi-dimension code review workflow instead of manual checking to counteract systemic biases in AI-generated or self-authored code, enforcing structured quality assurance across five dimensions while building a learning loop.