bmad-code-review

Run adversarial multi-layer code reviews on diffs with triaged findings.

1|Updated Aug 3, 2025

Search Tags:#automation #workflow #diff #triage #code-review #adversarial-review

Ready to run

npx skills add https://github.com/MazenMrad/Obsidio --skill bmad-code-review-mazenmrad

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: bmad-code-review
Source: https://github.com/MazenMrad/Obsidio/tree/main/.cursor/skills/bmad-code-review
Command: npx skills add https://github.com/MazenMrad/Obsidio --skill bmad-code-review-mazenmrad

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Streamlines rigorous code reviews by executing adversarial, multi-layer analyses that surface edge cases, ensure alignment with specifications, and deliver actionable triage insights.

Core Features & Use Cases

Parallel reviewer roles (Blind Hunter, Edge Case Hunter, Acceptance Auditor) operate on code diffs to identify gaps in coverage and specification conformance.
Structured triage with a unified findings format that includes location references, priority, and recommended actions (patches, decisions, defers, or dismissals).
Deterministic, step-file workflow that enforces reproducible reviews, clear progression, and auditable artifacts.
Diff-driven context awareness: loads optional spec and project documentation to inform the review and reduce ambiguity.

Quick Start

Trigger a code review on a changeset to run parallel reviewers and produce triaged findings for quick action.

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 to surface edge cases in my diffs?▼

Adversarial code review automates multi-layer analysis on diffs to surface edge cases and ensure specification compliance. It uses parallel reviewer roles to identify coverage gaps and produces triaged findings for quick action.

What is the best way to triage code review findings into actionable categories?▼

Triage code review findings into structured categories like patches, decisions, defers, and dismissals. A unified findings format provides location references, priority levels, and recommended actions to streamline the review process.

How do I ensure my code changes align with project specifications during review?▼

Specification alignment during code review is ensured by loading optional spec and project documentation as context. This diff-driven context awareness informs the review, reduces ambiguity, and verifies compliance with requirements.

Can I run parallel reviewer roles to check specification conformance on a changeset?▼

Yes, you can run parallel reviewer roles such as Blind Hunter, Edge Case Hunter, and Acceptance Auditor on code diffs. These roles operate simultaneously to identify gaps in coverage and specification conformance.

How do step-file driven workflows make code review reproducible and auditable?▼

Step-file driven workflows enforce reproducible code reviews by maintaining clear progression and generating auditable artifacts. This deterministic process loads diffs, specs, and context documents across multiple review layers.

Are there limitations to using automated triage for software development workflows?▼

Automated triage for software development workflows relies heavily on the quality of provided diffs, specs, and context documents. Limitations arise when optional project documentation is missing, increasing ambiguity during the automated review.