CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bmad-facilitate

Coaches the user through writing, updating or validating a document. Use when invoked by skill name only

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

90%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.

An exceptionally dense, operational skill body: exact commands, concrete output formats, and a numbered finalize checklist with explicit validation and re-validation loops. The tradeoff is prose so compressed that conditional logic in the template-selection and activation sections is hard to untangle, which costs it a point on workflow clarity and organization.

DimensionReasoningScore

Conciseness

The body is lean and operational throughout — no padding, no explanations of concepts Claude already knows, every sentence carrying instructions, commands or concrete output formats. It lands on the anchor for lean, efficient content where every token earns its place.

5 / 5

Actionability

Guidance is copy-paste ready: exact commands with flags ('uv run {project-root}/_bmad/scripts/memlog.py append --workspace {run} --type <fact|decision|...> --text "<gist>"', 'check_ids.py {run}/{id}-{slug}.md', 'render_view.py ... --layout <...> --style "..."') and concrete examples of progress lines ('PRD · 6 of 24 done · open: Non-goals, MVP scope').

5 / 5

Workflow Clarity

The sequence is clear with real validation and feedback loops — the numbered Finalize checklist, check_ids.py run with 'fix every undefined, duplicate and withdrawn hit', and rerunning it after headings move. Not a 5 because the activation and template-selection steps bury substantial conditional logic in long compound sentences, leaving minor gaps in traceability.

4 / 5

Progressive Disclosure

The bundle is real and one level deep — references/guidance-planning.md, rubric-general.md, rubric-planning.md and scripts/check_ids.py, render_view.py all exist and are invoked by explicit path convention ('{skill-root}/references/<name>.md'). Minor gaps: the load rules for references are spread inline rather than collected at a clear navigation point, and the dense body keeps some detail (Close, Headless) inline that could live in references.

4 / 5

Total

18

/

20

Passed

Description

67%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 cleanly states what the skill does and is unusually explicit about when it fires (name invocation only), which is a strong distinctiveness mechanism. Its weaknesses are the generic 'document' object and thin keyword coverage with no synonyms or document-type terms.

Suggestions

Name the document kinds or artifacts it handles (e.g., PRDs, plans, specs) to sharpen the 'what' and add natural trigger vocabulary.

If the invocation-only trigger is intentional, keep it, but consider adding one or two content-based trigger phrases so Claude can recognize the skill when users ask to draft or validate a document without naming it.

Mention the distinguishing capability (template-driven coaching with rubric review) to further separate it from generic writing-assistant skills.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Coaches the user through writing, updating or validating a document' — comparable in structure to the anchor-4 example, but the object stays generic ('a document') and capabilities like review walking or HTML rendering are unmentioned.

4 / 5

Completeness

Both parts are present: a clear 'what' (coaching through writing/updating/validating) and an explicit 'when' ('Use when invoked by skill name only'). Not a 5 because the 'what' remains broad rather than paired with concrete content trigger phrases.

4 / 5

Trigger Term Quality

'writing', 'updating', 'validating' and 'document' are terms a user would naturally say, but there are no synonyms or document-type variations (drafting, PRD, review), matching the anchor for some relevant keywords with common variations missing.

3 / 5

Distinctiveness Conflict Risk

The 'invoked by skill name only' trigger sharply reduces conflict risk, but the broad 'document' domain would overlap document-drafting skills if the trigger guidance were ignored — mostly distinct with minor overlap risk.

4 / 5

Total

15

/

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/core-tools/bmad-facilitate/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.