bmad-code-review

Review code diffs for defects, edge cases, and spec mismatches.

Updated May 23, 2026

Search Tags:#code review #pull request #edge cases #spec compliance #triage #adversarial analysis

Ready to run

npx skills add https://github.com/diegosanchespereira1/lavarapido --skill bmad-code-review-diegosanchespereira1

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: bmad-code-review
Source: https://github.com/diegosanchespereira1/lavarapido/tree/main/lava-rapido/.agents/skills/bmad-code-review
Command: npx skills add https://github.com/diegosanchespereira1/lavarapido --skill bmad-code-review-diegosanchespereira1

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you review code changes quickly and rigorously by combining adversarial analysis, edge-case checking, and acceptance validation into one structured workflow.

Core Features & Use Cases

Parallel review layers: Runs multiple perspectives to catch logic bugs, boundary issues, and spec drift.
Structured triage: Deduplicates findings and classifies them into patch, defer, dismissal, or decision-needed.
Workflow integration: Writes findings back to review artifacts and supports iterative follow-up on stories or branches.
Use case: Use it when you need a thorough review of a branch, commit range, staged changes, or a story tied to product requirements.

Quick Start

Ask the skill to review the current branch changes against the relevant spec or story file and report actionable 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 review branch diffs for edge cases and spec mismatches before merge?▼

Review branch diffs by extracting changes and running adversarial multi-layer analysis to catch logic bugs, boundary issues, and spec drift before merge. Structured triage then classifies findings into patch, defer, dismissal, or decision-needed categories.

What's the best way to triage code review findings across a commit range?▼

Triage code review findings by deduplicating issues and classifying them into patch, defer, dismissal, or decision-needed categories. This structured triage applies to commit ranges and ensures actionable validation against product requirements.

Can I use story-driven review workflows to check staged or uncommitted changes?▼

Story-driven review workflows support staged or uncommitted changes by validating them against story files and product requirements. The process extracts the diff, applies adversarial analysis, and optionally updates sprint status based on findings.

Does adversarial code analysis work for catching boundary issues and spec drift?▼

Adversarial code analysis works by running parallel review layers to catch boundary issues, logic bugs, and spec drift. It applies multiple perspectives to branch diffs and commit ranges to identify defects before merge.

Why does my pull request review miss logic bugs that an adversarial analysis catches?▼

Pull request reviews miss logic bugs because they lack parallel adversarial analysis layers. Running multiple perspectives against the diff catches boundary issues and spec drift that standard single-pass reviews overlook.

When do I need to update sprint status during a story-driven code review?▼

Update sprint status during a story-driven code review when findings need to be written back to review artifacts. This happens after triaging defects, edge cases, and spec mismatches found in the branch diff or commit range.