code-reviewer

Orchestrate a parallel four-reviewer code review workflow on PR diffs.

2|1|Updated Mar 8, 2026
One-click install
npx skills add https://github.com/mattstruble/skills --skill code-reviewer-mattstruble
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-reviewer
Source: https://github.com/mattstruble/skills/tree/main/code-reviewer
Command: npx skills add https://github.com/mattstruble/skills --skill code-reviewer-mattstruble

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill orchestrates a four-reviewer code review pipeline. Spawn all four specialized reviewers in parallel, aggregate their findings, drive the fix cycle, and report results. The skill covers two entry points: manual review (user-driven) and automated post-implementation review (coder-driven).

Core Features & Use Cases

  • Spawn all four reviewers in parallel (see Spawning Instructions)
  • Aggregate findings into a structured report (see Aggregating Results)
  • Support manual review and automated post-implementation review
  • Enforce a review cycle cap and a final convergence sweep

Quick Start

Provide a PR diff or inline diff to initiate the four-reviewer pipeline and begin automatic orchestration.

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 review for a PR diff?

To automate code review for a PR diff, provide the diff to initiate a parallel four-reviewer pipeline. The system spawns all four specialized reviewers simultaneously, aggregates their findings, and consolidates the feedback into a structured report.

Can I run parallel code reviews to accelerate PR feedback?

Yes, you can run parallel code reviews to accelerate PR feedback. The orchestration pipeline spawns four specialized reviewers concurrently, aggregating their findings to provide simultaneous expert evaluation rather than sequential manual checks.

How does the four-reviewer code review cycle handle blocking findings?

The four-reviewer code review cycle handles blocking findings by aggregating them alongside non-blocking issues, driving a fix cycle capped by a review limit, and performing a final convergence sweep to ensure all critical issues are resolved.

What is the best way to structure automated post-implementation code checks?

The best way to structure automated post-implementation code checks is using a coordinated review loop. This workflow supports automated entry points, spawns four expert reviewers in parallel, and produces a consolidated report of blocking and non-blocking findings.

Does the parallel code review workflow support manual entry points?

Yes, the parallel code review workflow supports both manual and automated entry points. You can initiate a user-driven manual review by providing an inline or PR diff, or trigger it automatically after implementation.

When should I use an orchestrated code review pipeline instead of manual review?

You should use an orchestrated code review pipeline when you need to accelerate structured feedback on PRs. It enforces a review cycle cap and final sweep, ensuring comprehensive parallel expert evaluation that manual sequential reviews often miss.