bmad-brainstorming

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

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%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.

A well-engineered, highly actionable skill body that orchestrates a multi-mode brainstorming session with concrete commands and clean one-level-deep reference structure. Minor conciseness tightening and a couple more explicit validation checkpoints would push it to the top band.

Suggestions

Tighten a few compound sentences in 'Framing' and 'Run a Session' to recover token budget without losing the operational detail.

Add an explicit validate/retry checkpoint around memlog writes (e.g., confirm the init succeeded before appending) to strengthen workflow clarity for the stateful operations.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational, assuming Claude's intelligence without explaining brainstorming concepts, but a few compound sentences and procedural prose could be tightened further.	4 / 5
Actionability	It provides copy-paste-ready executable commands (resolve_customization.py, memlog.py init/append/set, brain.py) with exact flags, plus concrete parsing rules for the pasted composer block.	5 / 5
Workflow Clarity	The session is clearly sequenced across Activation, Run a Session, Choosing Techniques, Converging, Resuming, and Wrap-Up with explicit decision branches and failure fallbacks, though explicit validate-fix-retry checkpoints are lighter.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview pointing to one-level-deep references (mode-*.md, converge.md, finalize.md, resume.md, headless.md) and assets/scripts, all of which are real bundled files, with well-signaled navigation.	5 / 5
	Total	18 / 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, third-person description that clearly pairs a concrete capability with explicit natural-language triggers. The only weakness is specificity: the capability is described as a single generic action rather than enumerating concrete techniques.

Suggestions

Replace 'using diverse creative techniques' with 1-2 named concrete actions (e.g., 'running divergent-thinking techniques like SCAMPER and lateral jumps') to lift specificity.

Add common trigger variations such as 'help me generate ideas' or 'come up with ideas' alongside the existing two phrases.

Dimension	Reasoning	Score
Specificity	It names the domain ('brainstorming session') and a concrete action ('Facilitate ... using diverse creative techniques'), but 'diverse creative techniques' is generic and only one action is listed, so coverage is not comprehensive.	3 / 5
Completeness	It explicitly answers both what ('Facilitate a brainstorming session using diverse creative techniques') and when ('Use when the user says ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	The triggers ('help me brainstorm', 'help me ideate') are natural phrases users would actually say, with a synonym included; a few common variations like 'generate ideas' or 'come up with ideas' are missing.	4 / 5
Distinctiveness Conflict Risk	The brainstorming niche and the specific trigger phrases are distinct from other skills, presenting minimal conflict risk.	5 / 5
	Total	17 / 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: src/core-skills/bmad-brainstorming/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.