multi-agent-review

Coordinate multiple AI agents to review documents and generate a final report.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/carrotcake5774-ai/forge --skill multi-agent-review-carrotcake5774-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: multi-agent-review
Source: https://github.com/carrotcake5774-ai/forge/tree/main/skills/multi-agent-review
Command: npx skills add https://github.com/carrotcake5774-ai/forge --skill multi-agent-review-carrotcake5774-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Multi-Agent Review orchestrates independent expert reviews, debates, and synthesis of complex Markdown documents (plans, PRDs, design specs) to validate quality and consistency.

Core Features & Use Cases

  • Independent expert reviews by up to five agents, with a built-in Devil's Advocate to ensure critical perspectives.
  • Structured 2-round debate workflow (R1 and R2) with issue tracking, status updates, and escalation to unresolved points.
  • Centralized synthesis and final report that aggregates findings, risks, and actionable recommendations for product/design governance.
  • References-based protocol driving evaluation through debate, with clear quality gates and audit trail.

Quick Start

Pass the path to the Markdown document you want reviewed to the /multi-agent-review trigger.

Frequently Asked Questions about multi-agent-review

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

FAQPage Schema
How do I review a PRD or design spec for cross-domain consistency?

Multi-agent review validates PRDs and design specs by orchestrating up to five independent expert agents to evaluate the document, debate findings, and synthesize a final governance report.

What is the debate workflow for document validation and governance?

The debate workflow for document governance uses a strict 2-round structure where expert agents track issues, update statuses, and escalate unresolved points to ensure traceability and accountability.

Can I use a devil's advocate approach to audit my planning documents?

Yes, you can audit planning documents using a built-in Devil's Advocate agent alongside independent expert reviewers to ensure critical perspectives challenge assumptions during the validation process.

Does multi-agent review work with Markdown files for automated audit trails?

Yes, automated audit trails work with Markdown files by passing the document path to the trigger, applying a references-based protocol to evaluate content, and generating a centralized synthesis report.

When do I need cross-domain validation for product management documents?

You need cross-domain validation for product management documents when plans, PRDs, or design specs require strict governance, traceability, and accountability across multiple expert domains.