CtrlK
BlogDocsLog inGet started
Tessl Logo

bmad-code-review

Adversarial code review using parallel review layers and structured triage. Use when the user says "run code review" or "review this code"

58

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./src/bmm-skills/4-implementation/bmad-code-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The body is a well-sequenced activation orchestrator with a clear step-file architecture, but it is held back by redundancy between its rule sections, placeholder-heavy guidance, and a primary step-file reference that is missing from the bundle.

Suggestions

Remove the redundant "Critical Rules (NO EXCEPTIONS)" block that restates the Step Processing Rules, or merge them into a single concise rules list to tighten conciseness.

Ensure the referenced ./steps/ step files (starting with step-01-gather-context.md) are actually bundled, or document where they live, so progressive-disclosure navigation is not broken.

Add at least one concrete validation/checkpoint step for the review workflow itself in the body, rather than delegating all review-side validation to the missing step files.

DimensionReasoningScore

Conciseness

The body is mostly lean and avoids explaining concepts Claude already knows, but the "Critical Rules (NO EXCEPTIONS)" section largely restates the preceding "Step Processing Rules" in negative form and the closing activation paragraph repeats prior instructions, so it could be tightened.

2 / 3

Actionability

It gives one concrete command (the resolve_customization.py invocation) and a concrete fallback merge procedure, but most guidance is template-placeholder driven ({workflow.*}, {project-root} paths) and the referenced step file is not present, leaving it incomplete rather than copy-paste ready.

2 / 3

Workflow Clarity

The activation sequence (Steps 1-6) is clearly ordered with explicit halt checkpoints and a script-failure fallback, but the substantive code-review workflow and its validation steps are delegated to step files that are absent, leaving validation gaps in the actual review process.

2 / 3

Progressive Disclosure

The step-file architecture with just-in-time loading is a sound one-level-deep disclosure design, but the sole referenced file ./steps/step-01-gather-context.md does not exist in the bundle, so navigation is broken against the actual structure.

2 / 3

Total

8

/

12

Passed

Description

82%

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 concise, well-structured description that clearly answers what and when with natural trigger phrases. It is held back from a top score by methodology-level rather than concrete action phrasing and trigger terms that overlap with generic code-review skills.

DimensionReasoningScore

Specificity

Names the domain ("code review") and methodology ("parallel review layers", "structured triage") but describes approach rather than listing multiple concrete actions, matching the "names domain and some actions, not comprehensive" anchor.

2 / 3

Completeness

It states what the skill does ("Adversarial code review using parallel review layers and structured triage") and when to use it ("Use when the user says ..."), clearly answering both what and when with explicit triggers.

3 / 3

Trigger Term Quality

The explicit triggers "run code review" and "review this code" are natural phrases a user would actually say, giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

The "adversarial ... parallel review layers ... structured triage" framing carves a niche, but the trigger phrases "run code review" / "review this code" are generic enough to overlap with any general code-review skill.

2 / 3

Total

10

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
bmad-code-org/BMAD-METHOD
Reviewed

Table of Contents

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.