skills.rest
ldk-hub
ldk-hubCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

bmad-code-review

Run parallel adversarial code review layers and triage findings into actionable categories.

Updated Apr 25, 2026
Search Tags:#automation#triage#code-review#adversarial#diff-review
One-click install
npx skills add https://github.com/ldk-hub/broke-shopping --skill bmad-code-review-ldk-hub
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bmad-code-review
Source: https://github.com/ldk-hub/broke-shopping/tree/main/_bmad/bmm/4-implementation/bmad-code-review
Command: npx skills add https://github.com/ldk-hub/broke-shopping --skill bmad-code-review-ldk-hub

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Adversarial, multi-layered code review challenges are common during software changes. This Skill coordinates parallel review layers to surface precise, actionable issues in code diffs and PRs.

Core Features & Use Cases

  • Parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) run concurrently to surface issues.
  • Structured triage: normalize findings, deduplicate, categorize into patch/decision_needed/defer/dismiss, and produce a concise, actionable summary.
  • Works with PRs, diffs, and commits, and supports optional spec workflows and context documents for acceptance criteria.

Quick Start

Trigger the code-review workflow against the target diff to surface adversarial findings.

Frequently Asked Questions about bmad-code-review

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

FAQPage Schema
How do I automate adversarial code review for pull requests?▼

Adversarial code review runs parallel layers such as Blind Hunter and Edge Case Hunter against pull requests to surface issues, then triages findings into actionable categories including patch, decision_needed, defer, and dismiss.

What is the best way to triage code review findings across large projects?▼

Triage code review findings by normalizing and deduplicating results from parallel review layers, categorizing them into patch, defer, or dismiss, and producing a concise at-a-glance summary across large projects and languages.

Does automated code review work with commits and diffs across different programming languages?▼

Automated code review works with commits, diffs, and pull requests across languages and project sizes, applying parallel review layers to output structured findings with sources, locations, and recommended actions.

How do I configure code review workflows with team overrides?▼

Configure code review workflows by loading workflow blocks from a base customize.toml file and applying team or user overrides, allowing you to tailor parallel review layers and triage behavior to your specific project.

Can I use acceptance criteria documents for automated diff review?▼

Automated diff review supports optional spec workflows and context documents to check against acceptance criteria, allowing the Acceptance Auditor layer to verify that code changes meet defined project requirements.

Related Skills

Explore More Software Engineering Skills→
skyoxuskyoxu

bmad-checkpoint-preview

Guide human-in-the-loop review of code diffs, design proposals, or documentation changes.

Community
Advanced
ryan-mahoneyryan-mahoney

specops-ambiguity-audit

Identify ambiguities in SpecOps analysis files and resolve them via legacy source code.

Community
Advanced
tunneleventunneleven

c4flow:pr-review

Process pull request comments and push code updates iteratively.

Community
Intermediate
shogo-labsshogo-labs
12

health

Aggregate type checker, linter, test, and coverage results into a normalized health score.

Official
Advanced