CtrlK
BlogDocsLog inGet started
Tessl Logo

bmad-help

Analyzes current state and user query to answer BMad questions or recommend the next skill(s) to use. Use when user asks for help, bmad help, what to do next, or what to start with in BMad.

68

Quality

81%

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

72%

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

A well-structured, actionable navigation skill with concrete paths, commands, and format examples, and clean progressive disclosure. The main weaknesses are minor verbosity in the Purpose/constraint lines and an implicit rather than explicitly numbered workflow with no validation checkpoints.

Suggestions

Replace the implicit section-based flow with an explicit ordered procedure (e.g., 1. Resolve config, 2. Load catalog, 3. Detect completion, 4. Pick next step, 5. Format response) so the workflow is unambiguous.

Tighten the Purpose sentence and rewrite the final Constraints bullet ('If the active module is ambiguous...') into a clear, concise instruction.

Add a light validation checkpoint (e.g., confirm the catalog CSV exists and the config resolver returned JSON before proceeding) to make the read-only flow more robust.

DimensionReasoningScore

Conciseness

The body is mostly efficient and avoids explaining known concepts, but the Purpose line and the final Constraints bullet ('retrieve all meta rows remote sources to find relevant info also to help answer their question') are wordy and could be tightened.

2 / 3

Actionability

It gives concrete executable guidance: exact catalog/config paths, an explicit resolver command, the precise CSV column schema, and copy-ready response-format examples like '[PR] PRD' and 'bmad-prd'.

3 / 3

Workflow Clarity

Sequencing is conveyed via phases, preceded-by/followed-by, required gates, and completion detection, but there is no explicit numbered procedure or validation checkpoint, so the workflow is present yet implicit.

2 / 3

Progressive Disclosure

No bundle files exist and the body is well-organized into clear sections with no nested documentation references; its only path/command mentions are live project data sources, not files to chase.

3 / 3

Total

10

/

12

Passed

Description

90%

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, complete description that covers both what the skill does and when to use it, with natural trigger terms and a distinct BMad-scoped niche. The only soft spot is specificity, where the two named actions are somewhat high-level rather than a broad enumerated list.

Suggestions

Expand specificity by enumerating a few more concrete actions (e.g., 'detect completed workflow steps, surface the next required gate, and fetch module docs to answer general questions') rather than two high-level verbs.

DimensionReasoningScore

Specificity

It names the BMad domain and two concrete actions ('Analyzes current state and user query to answer BMad questions', 'recommend the next skill(s) to use'), but the actions are high-level rather than a comprehensive list of specific concrete actions.

2 / 3

Completeness

It clearly answers both 'what' (analyze state/query to answer questions or recommend next skills) and 'when' via an explicit 'Use when' clause with concrete triggers.

3 / 3

Trigger Term Quality

The 'Use when' clause lists several natural user phrasings ('help', 'bmad help', 'what to do next', 'what to start with in BMad') that a user would realistically say.

3 / 3

Distinctiveness Conflict Risk

Everything is scoped to the BMad workflow niche with BMad-specific triggers, making it unlikely to fire for unrelated skills despite the generic words 'help' and 'next'.

3 / 3

Total

11

/

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.