CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bmad

Answers BMad questions and recommends the next skill from what is installed. Use when the user asks bmad for help, what to do next or where to start; to set up, update, repair, doctor, migrate or check the status of the installation, or add modules; or to see or change the active initiative.

Quality

91%

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

SKILL.md
Quality
Evals
Security

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-built dispatcher skill: lean body, executable commands, clean one-level-deep references that all exist in the bundle, and a clear action-vs-help routing split. The only notable gaps are the unspecified discovery of active skills folders and slightly ambiguous handling of mixed action-plus-question requests.

Suggestions

Add a brief instruction for how to determine which skills folders are active (e.g., a flag on knowledge.py or a host-provided list) so the help procedure is fully self-contained.

Clarify the routing for mixed requests that contain both an action and a question, e.g., "handle the action first via its reference, then follow Help and conversation for the question."

DimensionReasoningScore

Conciseness

Lean ~27-line body with no over-explanation of known concepts; the persona paragraph is functional instruction rather than padding, and it explicitly tells Claude to skip sections that don't apply ("loading the help then only fills context"). Every token earns its place.

5 / 5

Actionability

Provides the exact executable command "uv run {skill-root}/scripts/knowledge.py --content" with "--root <folder>" and exact per-action file mappings (e.g., "references/setup.md" for setup/update/repair). Not 5: "each skills folder the host has active" depends on host state with no step for discovering it; not 3: the commands are concrete and executable, not pseudocode.

4 / 5

Workflow Clarity

Clear routing — three named actions each mapped to a reference file, everything else a 2-step numbered help procedure — plus a comeback loop ("If the user later asks a question or wants advice, come back and follow it"). Not 5: mixed action+question requests fall in a gray zone between the two sections ("When the request is only one of these actions"), leaving the dispatch order implicit.

4 / 5

Progressive Disclosure

Verified against the actual bundle: all four referenced files exist, references are one level deep, and each has a clear when-to-load trigger (setup, migrate, initiative, help). The body is a lean overview that defers all detail to reference files and invokes scripts by exact path. Not 4: navigation is unambiguous with no organization gaps.

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 description: third-person, concrete, and comprehensive, with an explicit "Use when" clause covering help, maintenance, migration, and initiative triggers. Trigger coverage is good though not exhaustive of natural synonyms.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — "Answers BMad questions and recommends the next skill", "set up, update, repair, doctor, migrate", "check the status of the installation", "add modules", "see or change the active initiative" — with comprehensive coverage of the skill's functions. Not 4: coverage is comprehensive rather than having minor gaps.

5 / 5

Completeness

Explicitly answers both what ("Answers BMad questions and recommends the next skill from what is installed") and when ("Use when the user asks bmad for help, what to do next or where to start; to set up, update, repair, doctor, migrate...") with concrete trigger phrases, matching the anchor-5 structure.

5 / 5

Trigger Term Quality

Good natural keyword coverage — "asks bmad for help", "what to do next", "where to start", "set up", "update", "repair", "doctor", "add modules" — phrases a user would naturally say. Not 5: a few natural variations (e.g., "install", "configure", "continue my project") are missing.

4 / 5

Distinctiveness Conflict Risk

Every trigger is anchored on "bmad" or BMad-specific concepts (modules, initiatives, installation status), giving a clear niche with minimal conflict risk against unrelated skills. Not 4: even closely related skills would not collide on these triggers.

5 / 5

Total

19

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

bmad-code-org/BMAD-METHOD

Path

skills/bmad/SKILL.md

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.