bmad-code-review

Automate adversarial code review with parallel review layers and structured triage.

Updated Jan 21, 2026
One-click install
npx skills add https://github.com/zerAda/RestaurantAgentAutomation --skill bmad-code-review-zerada
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bmad-code-review
Source: https://github.com/zerAda/RestaurantAgentAutomation/tree/main/_bmad/bmm/workflows/4-implementation/bmad-code-review
Command: npx skills add https://github.com/zerAda/RestaurantAgentAutomation --skill bmad-code-review-zerada

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the challenge of manually reviewing code changes by automating the process with adversarial layers and structured triage, providing actionable insights for developers.

Core Features & Use Cases

  • Adversarial Code Review: Utilizes parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) for comprehensive code analysis.
  • Structured Triage: Organizes findings into actionable categories, improving developer efficiency.
  • Use Case: Ideal for teams that need to review code changes quickly and accurately, ensuring quality and adherence to standards.

Quick Start

Run the 'bmad-code-review' skill to start a code review workflow.

Frequently Asked Questions about bmad-code-review

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

FAQPage Schema
What is adversarial code review and how does it improve software quality?

Automated code review streamlines triage by organizing findings into structured, actionable categories, which improves developer efficiency by reducing manual sorting time and allowing immediate remediation of code changes.

How do I automate code review workflows for standard adherence?

You can automate code review workflows by running an adversarial process with parallel review layers, which analyzes code changes against standards and outputs structured triage findings for developers.

Does bmad-code-review require any specific workflow architecture to function?

Yes, bmad-code-review requires a step-file architecture for workflow management to properly execute its parallel review layers and organize the resulting findings into structured triage.

Can I use parallel review layers for triage in large software engineering projects?

Yes, parallel review layers like Blind Hunter and Edge Case Hunter are designed for software engineering workflows to comprehensively analyze large code changes and output structured triage for rapid developer action.

What is the best way to triage code findings from an adversarial review?

The best way to triage code findings is to use an automated adversarial review process that categorizes findings into structured, actionable insights, directly improving developer efficiency and standard adherence.