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

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./src/core-skills/bmad-help/SKILL.md

Quality

Content

75%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.

The body is a well-organized, actionable instruction-only skill with concrete data-source paths, an exact resolver command, and explicit completion-validation guidance. It consistently earns a 4 across dimensions, held from 5 by minor trimmable notes, slightly abstract fuzzy-matching, and the absence of a true multi-step checklist.

Suggestions

Tighten the "Descriptions carry routing context" note and a few redundant phrasings to push conciseness toward anchor 5.

Specify how to fuzzy-match found output files to catalog rows (e.g., match on the `outputs` glob pattern and skill name) so the completion-detection step is fully executable.

Optionally surface the recommended ordering as a short numbered checklist in the Response Format section to give the workflow explicit per-step checkpoints.

Dimension	Reasoning	Score
Conciseness	The body is efficient and BMad-specific (CSV schema, exact paths, the resolve_config command) without padding concepts Claude already knows; only minor meta-notes like "Descriptions carry routing context" could be trimmed, so it sits at anchor 4 rather than 5.	4 / 5
Actionability	Concrete executable guidance is present (exact file path, the `uv run ... resolve_config.py` command, column-by-column CSV interpretation, response-format examples like "[PR] PRD"), but "fuzzy-match found files to catalog rows" leaves a minor execution gap, keeping it just below anchor 5.	4 / 5
Workflow Clarity	A clear sequence runs from Data Sources through CSV Interpretation to Response Format and Constraints, with an explicit validation checkpoint ("When completion cannot be determined reliably, say so and ask the user; do not recommend advancing based on file presence alone"); it is structured guidance rather than a numbered checklist with per-step checkpoints, matching anchor 4.	4 / 5
Progressive Disclosure	The skill is a self-contained single-purpose guide organized into clear sections with no external bundle files or nested references; it is well-structured and appropriately inline, fitting anchor 4 rather than the one-level-deep reference pattern of anchor 5.	4 / 5
	Total	16 / 20 Passed

Description

78%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.

The description is strong: it pairs a clear statement of capability with an explicit, natural-language "Use when" trigger list and a distinct BMad niche. It is held back only by modest action specificity and minor generic-trigger overlap.

Dimension	Reasoning	Score
Specificity	Names the BMad-navigation domain and two-to-three concrete actions ("Analyzes current state and user query to answer BMad questions or recommend the next skill(s) to use"), but the actions are not comprehensive enough to reach anchor 4.	3 / 5
Completeness	It explicitly answers both what ("Analyzes current state and user query to answer BMad questions or recommend the next skill(s)") and when ("Use when user asks for help, bmad help, what to do next, or what to start with in BMad") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases a user would actually say are present ("help", "bmad help", "what to do next", "what to start with in BMad"); good coverage but lacking synonym variety that would push it to anchor 5.	4 / 5
Distinctiveness Conflict Risk	The BMad-specific framing carves a clear niche, but the generic triggers "help" and "what to do next" create minor overlap risk with general assistance skills, keeping it just below anchor 5.	4 / 5
	Total	16 / 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-help/SKILL.md
Commit: 67d876f

Reviewed: about 21 hours 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.