doc-review

Coordinate six independent agents to review documents for gaps, conflicts, and risks.

3|2|Updated Jan 12, 2026
One-click install
npx skills add https://github.com/ukwhatn/.claude --skill doc-review-ukwhatn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: doc-review
Source: https://github.com/ukwhatn/.claude/tree/main/skills/doc-review
Command: npx skills add https://github.com/ukwhatn/.claude --skill doc-review-ukwhatn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinating multiple expert reviews of a document can be slow and inconsistent. This skill orchestrates six independent agents to review a document from diverse angles, ensuring comprehensive coverage and faster feedback.

Core Features & Use Cases

  • Six-agent parallel review: Reviewer-1 to Reviewer-4, Devils' Advocate, and Agent CLI review run simultaneously to surface diverse insights.
  • Contextual checks: Cross-verifies design docs, specifications, and plans for completeness, feasibility, and alignment with requirements.
  • Structured output coaching: Produces consolidated findings with clear severity labels and actionable fixes.
  • Use Case: When validating a new spec, a team can run this skill to surface contradictions, gaps, and risk before implementation.

Quick Start

Submit the target document path to initiate a six-agent parallel review (e.g., /path/to/design-spec.md).

Frequently Asked Questions about doc-review

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

FAQPage Schema
How do I run a multi-agent review on a design spec?

To run a multi-agent review on a design spec, submit the target document path to initiate parallel processing. The system orchestrates six independent agents to review the document simultaneously from architecture, security, consistency, usability, and business alignment perspectives.

What is parallel multi-agent document review?

Parallel multi-agent document review is a process where six independent agents evaluate a document simultaneously from diverse angles. This mechanism ensures comprehensive coverage of architecture, security, consistency, usability, and business alignment to surface gaps, conflicts, and risks before implementation.

Can I use parallel review to find contradictions in requirements?

Yes, you can use parallel review to find contradictions in requirements. The six independent agents cross-verify design docs, specifications, and plans for completeness and feasibility, specifically surfacing contradictions, gaps, and risks before implementation begins.

Does multi-agent review output structured findings for quality assurance?

Yes, multi-agent review outputs structured findings for quality assurance by producing consolidated reports with clear severity labels. The output includes AR/R/M findings and a centralized action list to provide actionable fixes for the identified document gaps.

What are the limitations of automated document review?

A limitation of automated document review is its contextual scope; the six independent agents are specifically designed to apply checks to design specs, requirements, and plans. It focuses on surfacing gaps and risks rather than generating new documentation or writing code.