bmad-brainstorming

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

Quality

75%

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 ./skills/bmad-brainstorming/SKILL.md

Quality

Content

83%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 tightly written, highly actionable orchestration guide: concrete commands with flags, a numbered activation flow with fallbacks, clear phase handoffs, and disciplined one-level-deep progressive disclosure to real bundle files. Its only soft spot is slightly lighter explicit validation/feedback-loop framing for risky operations, which keeps workflow clarity just short of perfect.

Dimension	Reasoning	Score
Conciseness	The body is dense and directive with little concept padding — it assumes Claude's competence and avoids explaining brainstorming fundamentals — though a few sentences (e.g. the Overview's 'far more and far better ideas... no rush to finish') could be trimmed without losing instruction.	4 / 5
Actionability	It supplies copy-paste-ready commands with exact flags and arguments (resolve_customization.py, memlog.py init/append/set, brain.py html/list) plus a ready spoken prompt to the user, covering the common session flows concretely.	5 / 5
Workflow Clarity	Activation is a clearly numbered sequence with an explicit fallback ('On failure... use a subagent'), and phases (Run a Session → Choosing Techniques → Converging → Wrap-Up) are well sequenced with handoffs; however validation/checkpoint feedback loops are lighter than the rubric's 5-anchor expects, capping it at 4.	4 / 5
Progressive Disclosure	SKILL.md is an overview that one-level-deep references real, well-signaled bundle files (references/mode-*.md, headless.md, converge.md, finalize.md, resume.md, in-chat-techniques.md) and scripts/assets; each is loaded only when its phase runs, and the referenced files all exist in the bundle.	5 / 5
	Total	18 / 20 Passed

Description

66%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 third-person, concise, and cleanly pairs a clear 'what' with explicit quoted trigger phrases for the 'when'. It is strong on trigger quality and completeness but only moderately specific, since it lists one action rather than enumerating the creative techniques the body actually supports.

Suggestions

Name one or two concrete technique families (e.g. '...using diverse creative techniques like reframing, constraint-flipping, and inventive flow') to lift specificity beyond a single named action.

Broaden the trigger clause with synonyms users say ('help me brainstorm', 'help me ideate', 'I'm stuck', 'help me think outside the box') to improve trigger term coverage and reduce miss-fires.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ('Facilitate a brainstorming session') plus a method ('diverse creative techniques'), but offers no enumeration of the techniques or specific capabilities — comprehensive coverage is absent.	3 / 5
Completeness	Explicitly answers both 'what' (facilitate a brainstorming session using diverse creative techniques) and 'when' (Use when the user says 'help me brainstorm' or 'help me ideate'); the 'when' is concrete via quoted triggers but offers only two trigger phrases.	4 / 5
Trigger Term Quality	Includes natural user phrasing ('help me brainstorm', 'help me ideate') that users would genuinely say; 'brainstorm' is the canonical term, though common synonyms like 'ideas', 'stuck', 'think outside the box' are missing.	4 / 5
Distinctiveness Conflict Risk	The 'help me brainstorm' / 'help me ideate' triggers carve a distinct niche unlikely to fire for unrelated skills, though the broad word 'brainstorming' could minorly overlap with general ideation or planning skills.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Commit: 0a00053

Reviewed: 3 days 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.