code-review

Coordinate two competing subagents to review code diffs for architecture and implementation issues.

48|8|Updated Oct 17, 2025
One-click install
npx skills add https://github.com/maragudk/skills --skill code-review-maragudk
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/maragudk/skills/tree/main/code-review
Command: npx skills add https://github.com/maragudk/skills --skill code-review-maragudk

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill guides you through code reviews by inspecting changes and ensuring both architecture and implementation quality before commit or merge.

Core Features & Use Cases

  • Two-subagent review: Dispatch two reviewers who compete to identify issues, encouraging thorough evaluation of design and code.
  • Balanced evaluation: Emphasize architectural considerations alongside implementation details.

Quick Start

Ask the AI to review the staged or diff changes and propose improvements before committing.

Frequently Asked Questions about code-review

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

FAQPage Schema
How do I review code changes before merging to the main branch?

Code review systematically inspects changes to catch architectural and implementation issues. This Skill coordinates two competing reviewers to evaluate your diff, identify problems, and prioritize actionable recommendations before commit or merge.

What's the best way to ensure both architecture and implementation quality in pull requests?

Balanced code review addresses design decisions alongside implementation details. This Skill dispatches two subagents to compete in evaluating both dimensions, surfacing issues that single reviews often miss and improving overall code quality.

Can I use code review for staged changes in git workflows?

Yes. Code review works across staged changes and diffs against the main branch. It's designed for pre-commit and pull-request contexts, letting you catch issues before finalizing your changes in git.

How does competitive review improve code quality?

Competitive review encourages thorough evaluation by having two independent reviewers assess the same changes. Each reviewer competes to identify issues, resulting in more comprehensive feedback than a single review and reducing blind spots in both architecture and implementation.

What feedback does code review produce?

Code review produces a prioritized list of identified issues with actionable recommendations. Output is structured to guide next steps, making it clear what to fix and why before proceeding to commit or merge.