skills.rest
Wizarck
WizarckCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

bmad-code-review

Reviews code changes adversarially using parallel review layers with structured triage into actionable categories.

2|Updated Apr 19, 2026
Search Tags:#code review#subagents#acceptance criteria#triage#sprint#git diff#adversarial review
One-click install
npx skills add https://github.com/Wizarck/nexandro --skill bmad-code-review-wizarck
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bmad-code-review
Source: https://github.com/Wizarck/nexandro/tree/main/skills/bmad-code-review
Command: npx skills add https://github.com/Wizarck/nexandro --skill bmad-code-review-wizarck

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code reviews often miss edge cases, spec deviations, and subtle bugs because a single reviewer pass lacks diverse perspectives. This Skill runs adversarial multi-layer reviews of git diffs and triages every finding into clear, actionable categories. ## Core Features & Use Cases - Parallel Adversarial Review Layers: Launches a Blind Hunter (diff only), an Edge Case Hunter (diff plus project access), and an Acceptance Auditor (diff against spec) to catch different classes of issues. - Structured Triage: Normalizes, deduplicates, and classifies findings into decision-needed, patch, defer, or dismiss buckets, then writes them to the story file. - Sprint Integration: Emits a canonical QA verdict (APPROVED, ISSUES FOUND, CLARIFICATION NEEDED, ARCHITECTURE QUESTIONED) and syncs story status with sprint-status.yaml. - Use Case: After finishing a story implementation, ask for a code review of your branch diff against the spec; the Skill gathers context, runs the review layers, applies approved patches, and updates sprint tracking. ## Quick Start Say "run code review" or "review this code" and specify the diff source such as uncommitted changes, a branch diff, or a commit range.

Frequently Asked Questions about bmad-code-review

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

FAQPage Schema
How do I run an adversarial code review on my changes?▼

Trigger the review by saying "run code review" and specify a diff source such as uncommitted changes, staged changes, a branch diff, or a commit range. The workflow gathers context, launches parallel review layers, and triages findings into actionable categories.

What review layers does an adversarial code review use?▼

It uses three parallel layers: a Blind Hunter that sees only the diff, an Edge Case Hunter with project read access, and an Acceptance Auditor that checks the diff against the spec and context docs. Findings are merged, deduplicated, and classified.

Can I review code without a spec or story file?▼

Yes, the review runs in no-spec mode when no spec file is provided. The Acceptance Auditor layer is skipped, and findings that would need a decision are reclassified as patch or defer since no acceptance criteria exist.

What happens if a review subagent fails or returns empty results?▼

The failed layer name is recorded and the review proceeds with findings from the remaining layers. If zero findings remain and any layer failed, the workflow warns that the review may be incomplete instead of declaring a clean pass.

How are code review findings tracked and resolved?▼

Findings are written to the story file as decision-needed, patch, or defer items, and deferred items are logged to a deferred-work file. The review ends with a canonical verdict such as APPROVED or ISSUES FOUND, and the story status syncs to sprint-status.yaml.

Related Skills

Explore More Software Engineering Skills→
MathematicGuyMathematicGuy

bmad-code-review

Reviews code changes adversarially using parallel review layers and structured triage.

Community
Advanced
diegosanchespereira1diegosanchespereira1

bmad-dev-story

Execute story implementation workflows with test-first validation and status updates.

Community
Advanced
uzumaki-incuzumaki-inc

health

Run code health checks and compute a weighted 0-10 score.

Official
Advanced
summarybotngsummarybotng
2

code-review-quality

Conduct context-driven code reviews focusing on quality, testability, and maintainability.

Official
Advanced