skills.rest
geekdesign27
geekdesign27COMMUNITY
Explore all skills by this author →
GitHub

bmad-code-review

Performs adversarial code reviews using parallel sub-agents to identify issues across staged changes, branch diffs, and commit ranges.

Updated Mar 16, 2026
Search Tags:#automation#git#developer tools#code review#software quality#adversarial testing
One-click install
npx skills add https://github.com/geekdesign27/travailleursisoles --skill bmad-code-review-geekdesign27
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bmad-code-review
Source: https://github.com/geekdesign27/travailleursisoles/tree/main/_bmad/bmm/workflows/4-implementation/bmad-code-review
Command: npx skills add https://github.com/geekdesign27/travailleursisoles --skill bmad-code-review-geekdesign27

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of reviewing code changes by employing multiple adversarial review layers to identify potential issues, ensuring higher code quality and robustness.

Core Features & Use Cases

  • Parallel Review Layers: Utilizes Blind Hunter, Edge Case Hunter, and Acceptance Auditor for comprehensive code analysis.
  • Structured Triage: Categorizes findings into actionable insights like 'patch', 'intent_gap', 'bad_spec', 'defer', or 'reject'.
  • Use Case: When a developer submits a pull request, this Skill can be invoked to perform an in-depth, automated review, flagging potential bugs, spec deviations, or areas needing clarification before human review.

Quick Start

Run code review for the current branch against main.

Frequently Asked Questions about bmad-code-review

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

FAQPage Schema
How does adversarial code review work for automated pull request analysis?▼

Adversarial code review works by deploying parallel sub-agents, such as Blind Hunter and Edge Case Hunter, to analyze code changes against project specifications and triage findings into actionable categories like 'patch' or 'reject'.

How do I automate code review for staged git changes before submitting a pull request?▼

You can automate code review by running the Skill against staged changes, branch diffs, or specific commit ranges, allowing it to flag potential bugs and spec deviations for developers to resolve before human review.

Can I use automated code review to find edge cases and spec deviations in my branch diff?▼

Yes, automated code review can find edge cases and spec deviations by using an Acceptance Auditor layer to analyze your branch diff against project context, categorizing issues for developers to address before merging.

What is the best way to triage automated code review findings during software development?▼

The best way to triage automated code review findings is by categorizing them into structured insights such as 'patch', 'intent_gap', 'bad_spec', 'defer', or 'reject', ensuring developers receive actionable feedback for code quality improvements.

Does automated code review require specific dependencies to analyze commit ranges?▼

No, automated code review requires no specific dependencies to analyze commit ranges, operating directly on your project context and git history to perform multi-dimensional adversarial testing and identify potential software quality issues.

Related Skills

Explore More Software Engineering Skills→
LumenWipeLumenWipe
3

code-review

Review code diffs adversarially and triage findings into actionable categories.

Official
Advanced
deltatreedeltatree

bmad-code-review

Review code changes with parallel adversarial layers and structured triage.

Community
Advanced
lorenzogmlorenzogm
15

bmad-code-review

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

Community
Advanced
nicolanoviellnicolanoviell
2

code-review

Review code changes for bugs, style issues, and best practices.

Community
Intermediate