skills.rest
Joao-Victor-Medeiros
Joao-Victor-MedeirosCOMMUNITY
Explore all skills by this author →
GitHub

bmad-code-review

Review code changes with parallel independent reviewers, then triage and present findings.

Updated Sep 4, 2026
Search Tags:#code review#edge cases#subagents#triage#git diff#sprint tracking#parallel reviewers
One-click install
npx skills add https://github.com/Joao-Victor-Medeiros/save-sc --skill bmad-code-review-joao-victor-medeiros
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bmad-code-review
Source: https://github.com/Joao-Victor-Medeiros/save-sc/tree/main/.agents/skills/bmad-code-review
Command: npx skills add https://github.com/Joao-Victor-Medeiros/save-sc --skill bmad-code-review-joao-victor-medeiros

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Code reviews often miss edge cases, verification gaps, and spec deviations because a single reviewer cannot cover every angle. This Skill runs several independent reviewers in parallel against a diff, then triages every finding so only verified, actionable issues reach you. ## Core Features & Use Cases - Parallel adversarial review layers: Launch independent reviewers (Blind Hunter, Edge Case Hunter, Verification Gap, Acceptance Auditor) against a unified diff, each with its own methodology. - Evidence-based triage: Verify every finding against the actual code, assign verdicts (high/medium/low/false/maybe-false), group by root cause, and route to decision-needed, patch, or defer buckets. - Sprint integration: Write findings into story files, sync sprint-status.yaml, and optionally apply patches directly. - Use Case: After finishing a feature branch, ask for a code review; the Skill diffs against main, runs four reviewers in parallel, filters out false positives, and presents only confirmed issues with fix options. ## Quick Start Ask the assistant to run a code review on your current branch changes against main.

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 a code review on uncommitted changes?▼

Ask for a code review and choose the uncommitted changes option when prompted. The Skill runs git diff HEAD to capture staged and unstaged changes into a diff file, then launches the review layers against it.

What review layers does this code review workflow use?▼

It runs four layers: Blind Hunter (context-free issue hunting), Edge Case Hunter (exhaustive path tracing), Verification Gap (test coverage analysis), and Acceptance Auditor (spec compliance, full mode only). Layers can be customized or disabled via TOML overrides.

Can I review a branch diff against main?▼

Yes, select the branch diff option and specify the base branch. The Skill verifies the base branch exists, runs git diff base...HEAD, and reviews the resulting diff. It also collects commit messages as a claims file for narrative verification.

How are false positive findings handled in triage?▼

Every finding is verified against the actual code before being kept. Findings where the claimed bad outcome does not occur are marked false with a written refutation and rejected, and only verified findings proceed to grouping and routing.

What happens if subagents are not available in my session?▼

The Skill writes each reviewer's prompt with the full diff content into files under the implementation artifacts directory, then pauses so you can run each prompt in a separate session and paste the findings back to resume the workflow.

Does the code review update sprint status automatically?▼

Yes, when a story file and story key are available. After findings are resolved, the story status is set to done or in-progress and the matching entry in sprint-status.yaml is updated, preserving all existing file structure and comments.

Related Skills

Explore More Software Engineering Skills→
Asygnuz-S-A-SAsygnuz-S-A-S

bmad-code-review

Reviews code changes with parallel adversarial layers and structured triage into actionable findings.

Official
Advanced
thuantan2060thuantan2060

bmad-dev-story

Implement story specs via red-green-refactor with test and quality gates.

Community
Advanced
nagisanzeninnagisanzenin
176

code-reviewer

Reviews codebases for architecture conformance, code quality, performance, and test coverage gaps.

Community
Advanced
laicluselaicluse
4

council

Runs a five-lens adversarial advisory review with blind peer review and chairman synthesis.

Official
Advanced