bmad-review

Runs one or more installed review lenses — adversarial critique, edge cases, verification gaps, structure, prose — and reports triaged findings. Use when, and only when, the user asks you to review a diff, a pull request, or an artifact — code or documents, one or many — and actually says "review"; an explicit skill:bmad-review directive from another skill counts as that ask. A request to act on feedback from an earlier review is a change, not a review. Never invoke this uninvited, including on edits you just made.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable skill body that appropriately delegates lens detail to reference files and gives concrete commands and schemas. The main trim opportunity is the duplicated subagent-constraint block and minor validation gaps at the assembly boundary.

Suggestions

State the subagent constraint ("Return ONLY your findings ... do not spawn subagents of your own ...") once and reference it from both step 5 and step 6 instead of duplicating the full block.

Add a brief verification checkpoint in step 7 to confirm each lens's findings conform to the declared shape before assembling, closing the assembly-boundary validation gap.

Tighten the long run-on sentences in steps 5 and 6 by splitting the spawn-time constraint list from the concurrency guidance.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence with no concept padding, but the full subagent-constraint block is duplicated verbatim in steps 5 and 6 and a few sentences are overstuffed.	4 / 5
Actionability	Provides an exact resolve_customization command, a copy-paste JSON fallback array for empty input, precise finding-field schemas, and ready-to-paste subagent constraint strings covering the common cases.	5 / 5
Workflow Clarity	A clear 7-step sequence with explicit checkpoints (empty input → return JSON and stop; resolve failure → fallback) is present, but there is no verification of lens-output shape at assembly and recovery is fallback rather than fix-and-retry.	4 / 5
Progressive Disclosure	SKILL.md is an overview orchestrator pointing one level deep to seven lens/editororial reference files and the word_metrics script; all in-bundle referenced paths exist and navigation is clearly signaled.	5 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, highly specific description that clearly states both capability and trigger conditions with explicit boundary guidance. Its only gap is slightly incomplete synonym coverage for trigger terms.

Dimension	Reasoning	Score
Specificity	Enumerates five concrete review lenses (adversarial critique, edge cases, verification gaps, structure, prose) and the action "reports triaged findings," giving comprehensive coverage of what the skill does.	5 / 5
Completeness	It explicitly answers both what ("Runs one or more installed review lenses ... and reports triaged findings") and when ("Use when, and only when, the user asks you to review a diff, a pull request, or an artifact ... and actually says 'review'") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger terms are present ("review," "diff," "pull request," "artifact") but common synonyms like "PR" or "code review" are missing, leaving it just short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	Active disambiguation — "A request to act on feedback from an earlier review is a change, not a review" and "Never invoke this uninvited" — carves a clear niche and minimizes conflict with adjacent skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: bmad-code-org/BMAD-METHOD
Path: src/core-skills/bmad-review/SKILL.md
Commit: 05bfbd4

Reviewed: 15 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.