skills.rest
mjwestcott
mjwestcottCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

review

Coordinate parallel review agents to assess code changes and generate PR-style reports.

7|Updated Apr 2, 2016
Search Tags:#multi-agent#quality-assurance#ai-assistant#code-review#pr-review#parallel-processing
One-click install
npx skills add https://github.com/mjwestcott/dotfiles --skill review-mjwestcott
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/mjwestcott/dotfiles/tree/main/claude/skills/review
Command: npx skills add https://github.com/mjwestcott/dotfiles --skill review-mjwestcott

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinated, objective code reviews by spawning multiple review agents in parallel to surface findings quickly and reduce bias.

Core Features & Use Cases

  • Spawns two review agents to examine changes independently, improving objectivity.
  • Synthesizes findings into a concise PR-style report with actionable recommendations.
  • Supports both report-only mode and a self-edit mode for guided improvements.

Quick Start

Invoke the review skill to spawn parallel agents and generate a concise, actionable report.

Frequently Asked Questions about review

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

FAQPage Schema
How do I run parallel code reviews to reduce bias on my pull requests?▼

Parallel code reviews reduce bias by spawning multiple review agents to independently examine pull request changes, which are then synthesized into a single, objective PR-style summary with actionable recommendations.

What is multi-agent code review and how does it work?▼

Multi-agent code review is a process where multiple autonomous agents examine code changes simultaneously. It works by spawning independent agents to assess diffs and surfacing findings rapidly to provide objective, comprehensive feedback.

Can I apply automated PR review to both commits and diffs across diverse codebases?▼

Yes, automated PR review is applicable to pull requests, commits, or diffs across diverse codebases. The multi-agent approach examines the provided changes and generates actionable findings regardless of the codebase structure.

What's the best way to get actionable recommendations from a code review?▼

The best way to get actionable recommendations is to synthesize findings from multiple independent review agents into a concise PR-style report, providing bite-sized improvements for your changes.

Does multi-agent code review support guided improvements or self-editing?▼

Yes, multi-agent code review supports a self-edit mode for guided improvements. This allows the system to not only generate a report-only summary but also provide actionable, bite-sized recommendations to directly refine the code.

Related Skills

Explore More Software Engineering Skills→
ulpi-ioulpi-io
13

claude-review

Spawn a Claude Code agent in an isolated worktree to review code changes.

Official
Advanced
erclxerclx
2

git-followup

Stage, commit, and push follow-up edits to an open pull request branch.

Community
Advanced
shynlee04shynlee04
51

hivemind-architect-strategist

Analyze codebases for architectural adherence and technical debt.

Community
Advanced
sylvandingsylvanding
9

resolve-pr-parallel

Resolve GitHub pull request review comments via parallel agent processing.

Community
Intermediate