Bmad Brainstorm logo

Bmad Brainstorm

Community
aj-geddes
bmad-brainstorm

Facilitates structured ideation sessions using proven brainstorming techniques (SCAMPER, SWOT, 5 Whys, Mind Mapping, Six Thinking Hats, Reverse Brainstorming, Starbursting, Brainwriting). Produces a brainstorming-report.md of organized ideas and actionable insights. Operates in three intents: Create (new session), Update (add techniques or deepen coverage), Validate (confirm insights align with project goals). Use when the user says: "brainstorm", "ideate", "generate ideas", "explore options", "SCAMPER", "SWOT analysis", "mind map", "Six Thinking Hats", "5 Whys", "creative session", "what if we", "let's explore", "think through possibilities", "find alternatives", or "problem-solve". This skill PLANS only — it never writes application code or runs tests.

Overview

Publisheraj-geddes
Repositoryclaude-code-bmad-skills
Skill namebmad-brainstorm
Stars
492
Forks
77
Bundled files
3
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by aj-geddes on GitHub. Read the source before you install it.

Installation

Install the Bmad Brainstorm AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/aj-geddes/claude-code-bmad-skills/tree/main/bmad-planning-orchestrator/skills/bmad-brainstorm
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/aj-geddes/claude-code-bmad-skills.git /tmp/claude-code-bmad-skills
mkdir -p .claude/skills
cp -r /tmp/claude-code-bmad-skills/bmad-planning-orchestrator/skills/bmad-brainstorm .claude/skills/bmad-brainstorm
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bmad Brainstorm in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Bmad Brainstorm on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Bmad Brainstorm is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

BMAD Brainstorm

Structured ideation harness for the BMAD planning lifecycle. Produces a brainstorming-report.md of organized ideas and insights ready to feed downstream planning skills (product-brief, PRD, architecture).

Three Intents

Ask the user which intent applies — or infer from context:

IntentWhen to use
CreateNew brainstorming session on a topic or problem
UpdateAdd techniques, deepen coverage, or incorporate new constraints
ValidateConfirm generated insights align with project goals or decision-log

Technique Menu

TechniqueBest ForApprox Time
5 WhysRoot cause analysis10-15 min
SCAMPERFeature ideation & creative variations20-30 min
Mind MappingIdea organization & hierarchy15-20 min
Reverse BrainstormingRisk and failure-mode identification15-20 min
Six Thinking HatsMulti-perspective evaluation30-45 min
StarburstingQuestion exploration (Who/What/When/Where/Why/How)20-30 min
SWOT AnalysisStrategic positioning30-45 min
BrainwritingSilent parallel idea generation15-20 min

Technique Selection Guide

  • Exploring a problem? → 5 Whys, then Starbursting
  • Generating features or solutions? → SCAMPER, Mind Mapping
  • Assessing risk or failure modes? → Reverse Brainstorming, Six Thinking Hats (Black Hat)
  • Strategic planning or positioning? → SWOT, Six Thinking Hats (full cycle)
  • Need parallel idea volume? → Brainwriting

Session Workflow

Use TodoWrite to track each step.

  1. Gather context — Ask: topic/problem, relevant constraints, which BMAD track is active
  2. Read project context — Load bmad-output/project-context.md and bmad-output/decision-log.md if present
  3. Select techniques — Choose 2-4 complementary techniques; confirm with user
  4. Execute sessions — Apply each technique systematically (diverge first, do not filter)
  5. Organize ideas — Categorize all generated ideas; label Impact (H/M/L) and Feasibility (H/M/L)
  6. Extract insights — Identify top 3-5 actionable insights across all techniques
  7. Identify risks — Capture risks surfaced during ideation
  8. Produce report — Fill templates/brainstorm-session.template.md; save to output folder
  9. Update decision-log — Record key decisions or directions confirmed during the session
  10. Recommend next steps — Which BMAD skill to engage next

Script Utilities

Generate SCAMPER prompts for a specific topic:

bash
bash "${CLAUDE_PLUGIN_ROOT}/skills/bmad-brainstorm/scripts/scamper-prompts.sh" "your topic"

Generate a SWOT analysis scaffold:

bash
bash "${CLAUDE_PLUGIN_ROOT}/skills/bmad-brainstorm/scripts/swot-template.sh" "your subject" > bmad-output/swot-draft.md

Output Artifacts

All artifacts go under the user-configured output folder (default bmad-output/).

FileDescription
bmad-output/brainstorming-report.mdPrimary output — organized ideas + insights
bmad-output/decision-log.mdAppend key decisions made during session
bmad-output/swot-draft.mdOptional SWOT scaffold (from script)

Use templates/brainstorm-session.template.md for the report structure.

Subagent Strategy

For sessions covering multiple techniques in parallel, fan out one agent per technique.

Pattern: Fan-Out Ideation
Agents: 2-6 parallel (one per selected technique)

AgentTaskOutput
Agent 1Apply SCAMPER to generate feature variationsbmad-output/brainstorm-scamper.md
Agent 2Build Mind Map to organize ideas hierarchicallybmad-output/brainstorm-mindmap.md
Agent 3Reverse Brainstorming — identify failure modesbmad-output/brainstorm-risks.md
Agent 4Six Thinking Hats — multi-perspective analysisbmad-output/brainstorm-hats.md
Agent 5Starbursting — Who/What/When/Where/Why/Howbmad-output/brainstorm-questions.md
Agent 6SWOT Analysis — strategic positioningbmad-output/brainstorm-swot.md

Coordination:

  1. Write brainstorming objective to bmad-output/brainstorm-objective.md
  2. Select 2-6 techniques; launch one agent per technique with context path
  3. Each agent generates 10-20 ideas/insights using its assigned technique
  4. Main context synthesizes all outputs into bmad-output/brainstorming-report.md
  5. Extract top 3-5 actionable insights; append decisions to bmad-output/decision-log.md

Example subagent prompt:

Task: Apply SCAMPER technique
Context: Read bmad-output/brainstorm-objective.md for topic and constraints
Output: Write 15-20 creative variations to bmad-output/brainstorm-scamper.md

Apply each SCAMPER letter systematically. Generate 2-4 ideas per letter.
For each idea: one-sentence description, potential value, innovation level
(incremental / breakthrough). Conclude with your top 3 most promising ideas.
Do not implement anything — ideation output only.

BMAD Fidelity Notes

  • This skill feeds Phase 1 (Analysis) and Phase 2 (Planning). Insights flow into the product-brief and PRD skills.
  • Insights that become commitments must be logged in bmad-output/decision-log.md.
  • This skill does not produce stories. It produces raw insight material that upstream skills (product-manager, system-architect) refine into epics and stories.
  • Scale-adaptive tracks apply: Quick Flow sessions may use 1-2 techniques; Enterprise sessions should apply 4-6 for comprehensive coverage.

Guiding Principles

  1. Diverge before converging — generate volume first; filter later
  2. Structured over freeform — every technique has a defined process; follow it
  3. Document everything — capture all ideas; even "bad" ones can spark breakthroughs
  4. Quantify insights — numbers make insights actionable (market size, feature counts)
  5. Cross-pollinate — consider how other industries or domains solve the same problem
  6. No implementation — this skill plans; it never writes code or runs tests

Part of the BMAD Planning & Orchestrator plugin — a Claude Code harness for the BMAD Method by the BMAD Code Organization (https://github.com/bmad-code-org/BMAD-METHOD). Implements the spirit of bmad-brainstorming. All methodology credit belongs to the BMAD Code Organization.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Bmad Brainstorm AI skill do?

Facilitates structured ideation sessions using proven brainstorming techniques (SCAMPER, SWOT, 5 Whys, Mind Mapping, Six Thinking Hats, Reverse Brainstorming, Starbursting, Brainwriting). Produces a brainstorming-report.md of organized ideas and actionable insights. Operates in three intents: Create (new session), Update (add techniques or deepen coverage), Validate (confirm insights align with project goals). Use when the user says: "brainstorm", "ideate", "generate ideas", "explore options", "SCAMPER", "SWOT analysis", "mind map", "Six Thinking Hats", "5 Whys", "creative session", "what i...

Why use Bmad Brainstorm on TypingMind?

Because you install it once and use it with any model. Bmad Brainstorm is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Bmad Brainstorm in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/aj-geddes/claude-code-bmad-skills/tree/main/bmad-planning-orchestrator/skills/bmad-brainstorm. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Bmad Brainstorm?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Bmad Brainstorm?

As many as you like. As long as a model supports skills, you can use Bmad Brainstorm with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Bmad Brainstorm AI skill free?

It is published on GitHub by aj-geddes. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇