bmad-review

Review diffs, documents, and specs through configurable adversarial, edge-case, verification-gap, and editorial lenses.

1|Updated Jun 2, 2026
One-click install
npx skills add https://github.com/SevWren/Daily-Motivation-Brain-Helper --skill bmad-review-sevwren
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bmad-review
Source: https://github.com/SevWren/Daily-Motivation-Brain-Helper/tree/main/.claude/skills/bmad-review
Command: npx skills add https://github.com/SevWren/Daily-Motivation-Brain-Helper --skill bmad-review-sevwren

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Reviews of code changes and documents are often shallow or inconsistent, missing edge cases, untested behavior, and structural problems. This Skill runs a disciplined multi-lens review over any diff, file, spec, or document and reports concrete findings in a canonical shape. ## Core Features & Use Cases - Multi-lens review: Ships adversarial, edge-case-hunter, verification-gap, structure, and prose lenses that run singly or together depending on content type. - Canonical findings output: Every finding carries location, trigger condition, guard snippet, and potential consequence, rendered as JSON, markdown, or both. - Customizable workflow: A customize.toml file lets teams add lenses, set style guides, define standing review guidance, and control output format and report destination. - Use Case: Ask for a critical review of a pull request diff; the edge-case lens enumerates unhandled branches while the verification-gap lens checks whether tests would actually catch a regression. ## Quick Start Ask the assistant to review a file or diff, for example: run a full review of the changes in src/scheduler.ps1 and report the findings.

Frequently Asked Questions about bmad-review

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

FAQPage Schema
How do I review a code diff for edge cases?▼

Invoke the review on the diff and the edge-case-hunter lens walks every branch and boundary condition, reporting only unhandled paths. Each finding includes the location, the missing condition, a guard snippet, and the potential consequence.

What lenses are included in this review skill?▼

Five lenses ship by default: adversarial, edge-case-hunter, verification-gap, structure, and prose. The lens set is defined in customize.toml, so teams can add, replace, or disable lenses through override files.

Can I run only one specific review lens?▼

Yes. Naming lenses in the request runs exactly those lenses, bypassing the applies_to and when filters. For example, asking for an editorial review runs only the structure and prose lenses on a document.

Does the verification-gap lens work on documents?▼

No. The verification-gap lens applies only to code reviewed inside a repository where tests can be searched and read. It checks whether changed behavior would actually fail an existing test if it regressed.

How do I customize the review output format?▼

Set output_format in customize.toml to json, markdown, or both, and optionally set report_path to write the report to a file. Team and personal override TOML files merge with the shipped defaults.

What happens when a review finds nothing?▼

An empty findings array is a valid result for most lenses, and the markdown report states the review is clean. The adversarial lens is the exception: it requires at least ten findings and treats an empty list as a signal to re-check.