multi-agent-codereview

Community

Coordinate expert agents for robust code review.

Authorcarrotcake5774-ai
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill orchestrates a multi-agent code review workflow where independent expert roles and a Devil's Advocate collaboratively identify defects, architectural concerns, and practical risks across review cycles, improving review quality and consensus.

Core Features & Use Cases

  • Independent role assignment for code review (backend architect, security, operations, UX, etc.)
  • 2-round debate with cross-entity evaluation to surface issues
  • Final synthesis report with issue tracking, prioritization, and recommended actions
  • Applicable to PR reviews, architectural reviews, service-layer assessments, and security reviews

Quick Start

Trigger the skill with /multi-agent-codereview <target> and let the agents perform independent analysis, debate, and synthesis to produce a final report.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: multi-agent-codereview
Download link: https://github.com/carrotcake5774-ai/forge/archive/main.zip#multi-agent-codereview

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.