CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bmad-brainstorming

Facilitate a brainstorming session using diverse creative techniques. Use when the user says 'help me brainstorm' or 'help me ideate'

Quality

89%

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

92%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 exemplary instruction-only skill: executable commands with full flags, explicitly sequenced phases with validation checkpoints and failure-recovery branches, and textbook progressive disclosure verified against the actual bundle structure. The only notable weakness is mild editorial padding and a few over-long sentences in the Framing/Overview sections.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's intelligence throughout — no concept explanations, no library tutorials — with copy-paste commands kept terse. Minor over-explanation remains (e.g. "The best sessions end with the user surprised by what came out" and several long compound sentences in Framing) that could be trimmed. Not 3 because padding is isolated, not structural.

4 / 5

Actionability

Fully executable guidance: exact invocations with all flags (`uv run {project-root}/_bmad/scripts/memlog.py init --workspace ... --field topic=...`), exact asset paths, literal message text to deliver, and concrete fallback branches for every failure mode (script not found, no active_initiative, page not opening). Placeholders are resolved by the activation commands themselves.

5 / 5

Workflow Clarity

Phases are explicitly sequenced (On Activation 1-5, Run a Session, Choosing Techniques, Converging, Resuming, Wrap-Up) with an explicit checkpoint ("confirm every entry ran before continuing") and error-recovery loops (script missing → offer setup → re-run; "never claim it opened"). Memlog writes are specified as atomic, and no destructive/batch operation lacks validation.

5 / 5

Progressive Disclosure

The SKILL.md is a true overview: each phase's detail is deferred to a real, one-level-deep reference (mode-*.md, headless.md, in-chat-techniques.md, converge.md, resume.md, finalize.md — all verified present in the bundle), loaded conditionally per phase, with explicit instructions to keep the catalog out of context ("Never pull the library whole into context"). The technique bulk lives in assets/ generated via scripts/brain.py.

5 / 5

Total

19

/

20

Passed

Description

82%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 with an explicit and natural trigger clause; its main weakness is a thin 'what' that stays at the level of generic action verbs rather than enumerating the session's concrete capabilities. Scores are held down by specificity and missing trigger synonyms, not by structure.

Suggestions

Enumerate 1-2 more concrete capabilities in the 'what' clause, e.g. 'run divergent technique batches, converge on the best ideas, and produce a synthesis' — this would lift specificity from domain-only to specific actions.

Add common trigger variations users naturally say, such as 'come up with ideas', 'generate ideas', or 'brainstorm ideas for <topic>', to broaden trigger-term coverage beyond the two quoted phrases.

DimensionReasoningScore

Specificity

"Facilitate a brainstorming session" and "using diverse creative techniques" name the domain and 1-2 actions, but the actions are generic and there is no coverage of what the session concretely involves (technique selection, converging, synthesis, resuming). Not 4 because it does not list several specific concrete actions.

3 / 5

Completeness

Clearly answers what ("Facilitate a brainstorming session using diverse creative techniques") and when with concrete trigger phrases ("Use when the user says 'help me brainstorm' or 'help me ideate'"). Matches the anchor for explicit what AND when with concrete triggers.

5 / 5

Trigger Term Quality

Includes natural phrases users would actually say, quoted verbatim ("help me brainstorm", "help me ideate"), plus "brainstorming session" as a keyword. Not 5 because common variations like "come up with ideas", "generate ideas", or "brainstorm ideas for X" are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche (brainstorming facilitation) with distinct, verbatim trigger phrases that are unlikely to fire for unrelated skills. Overlap risk with a generic ideation skill is minimal.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

bmad-code-org/BMAD-METHOD

Path

skills/bmad-brainstorming/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.