Code Reviewer

Analyze code changes for architecture, security, performance, and style feedback.

40|11|Updated Aug 15, 2025
One-click install
npx skills add https://github.com/Uniswap/ai-toolkit --skill code-reviewer-uniswap
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Code Reviewer
Source: https://github.com/Uniswap/ai-toolkit/tree/main/packages/plugins/development-pr-workflow/skills/review-code
Command: npx skills add https://github.com/Uniswap/ai-toolkit --skill code-reviewer-uniswap

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Comprehensive, automated code reviews that coordinate multiple analysis agents to assess architecture, security, performance, and style across changes.

Core Features & Use Cases

  • Multi-agent review orchestration across architecture, security, performance, and maintainability.
  • Diff-aware inputs with focus controls for architecture, security, performance, or all aspects.
  • Actionable recommendations and fixes with prioritized tasks for PRs.
  • Structured summaries suitable for PR discussions and handoffs.

Quick Start

Ask Claude to review the current changes by saying 'Review my changes'.

Frequently Asked Questions about Code Reviewer

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

FAQPage Schema
How do I automate code reviews for pull requests?

Automated code reviews for pull requests analyze local diffs and staged changes using multi-agent orchestration. Coordinated agents assess architecture, security, performance, and style to provide actionable fixes and structured summaries suitable for PR discussions.

Can I focus code review feedback on security or performance only?

Focusing code review feedback on security or performance is supported through diff-aware inputs with focus controls. The multi-agent orchestration targets specific areas to provide actionable recommendations and prioritized tasks for the selected aspect.

What is multi-agent orchestration for code review?

Multi-agent orchestration for code review is a mechanism where multiple analysis agents coordinate to assess architecture, security, performance, and maintainability. It applies specialized agents to code changes to provide comprehensive, actionable feedback.

Does automated code review work with local diffs and staged changes?

Automated code review works with local diffs and staged changes by identifying and analyzing code modifications. It applies multi-agent orchestration to provide architecture, security, performance, and style feedback directly on local file changes.

How do I get actionable fixes from a code review?

Actionable fixes from a code review are generated as prioritized tasks for pull requests. The multi-agent analysis provides structured summaries suitable for PR discussions and handoffs, delivering clear recommendations for improving code quality.

When should I use automated code review instead of manual review?

Automated code review should be used when you need comprehensive, coordinated analysis across architecture, security, performance, and style. It is suited for pull requests, local diffs, and staged changes where structured summaries and prioritized actionable fixes are required.