/gaia-brainstorming
user-facingWhat it does
/gaia-brainstorming runs a facilitated brainstorming session using creative techniques like Mind Mapping, SCAMPER, Six Thinking Hats, Reverse Brainstorming, and more. It follows a four-phase flow: Session Setup, Technique Selection, Technique Execution, and Idea Organization. Output is a ranked, categorized idea list.
When to use it
- You want a structured ideation session using a specific technique (Mind Mapping, SCAMPER, Six Thinking Hats, Reverse Brainstorming, or others).
- You need a large volume of ideas (quantity over quality) organized, categorized, and ranked by feasibility.
- You want a standalone brainstorming session that is more technique-focused than
/gaia-brainstorm(which is more discovery-oriented).
Prerequisites
- No strict prerequisites. Works best when planning artifacts exist for context.
Orchestration mode
When /gaia-brainstorming starts in subagent mode (Mode A -- the default), the framework emits a one-shot warning to your conversation. The warning text:
────────────────────────────────────────────────────────────────────────────
GAIA orchestration: running in subagent mode (Mode A)
The skill you're invoking belongs to a class (heavy-procedural or
conversational) whose output benefits from cross-step context. Mode A
dispatches each sub-agent in its own forked context, so context may
be lossy between steps — sub-agents return summaries, not full reasoning.
For the full-fidelity experience, enable Mode B (Agent Teams):
1. Set CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 in your environment.
2. Add orchestration.mode: team to .gaia/config/project-config.yaml.
Mode B uses persistent teammates that preserve in-conversation state
across dispatches. See the orchestration contract for details.
This warning is shown once per session.
────────────────────────────────────────────────────────────────────────────
Why Mode B is better for this command
The /gaia-brainstorming skill declares orchestration_class: conversational in its SKILL.md frontmatter. Conversational skills produce output that benefits from cross-step context -- under Mode A every sub-agent dispatch runs in its own forked context and can only return a summary back to the orchestrator, losing the full reasoning trace of every prior step. Mode B uses persistent teammates that retain in-conversation state across dispatches, so each agent's contribution can build on what was said before instead of receiving only a summary.
How to enable Mode B
Both steps are required. If either is missing, the framework falls back silently to Mode A and the warning fires again on the next session.
Step 1 -- set the environment variable:
export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
Add this to your shell rc file to persist across sessions, or set it in Claude Code's settings.json.
Step 2 -- add the YAML block to .gaia/config/project-config.yaml:
orchestration:
mode: team
One-shot semantics
The warning is emitted once per Claude Code session. A marker file at _memory/checkpoints/orchestration-warning-shown.<session-id> suppresses the warning for the rest of the session. Starting a new session re-emits the warning once.
How to invoke
/gaia-brainstorming New mobile app features
What it does step by step
- Session setup Collects topic, scope, constraints, output format, and session tone.
- Technique selection Recommends 2-3 techniques with rationale and lets you choose.
- Technique execution Runs the selected technique round by round, generating 5-10 ideas per round. Quantity over quality.
- Idea organization Categorizes, ranks, and evaluates all ideas. Writes to
.gaia/artifacts/creative-artifacts/brainstorming-{date}.md.
Inputs
| Input | Source | Description |
|---|---|---|
topic | Command argument (optional) | The topic or challenge. If omitted, the command asks. |
Outputs
| Output | Location | Description |
|---|---|---|
| Creative artifact | .gaia/artifacts/creative-artifacts/ | The session output document. |
Example session
> /gaia-brainstorming New mobile app features
Setup: Broad exploration, wild ideas welcome.
Recommended techniques:
1. Mind Mapping -- broad topic exploration
2. SCAMPER -- improve existing features
> 1
Round 1: 8 ideas generated.
Round 2: 6 ideas generated.
14 ideas categorized and ranked.
Written to .gaia/artifacts/creative-artifacts/brainstorming-2026-05-07.md
What to run next
- Feed the top-ranked ideas into
/gaia-product-briefor/gaia-design-thinking. - Run
/gaia-adversarialon the top ideas to stress-test them before committing.
Troubleshooting
Topic not provided
The command asks for your topic interactively if no argument is given.
I keep seeing the GAIA orchestration warning every time I start this command
The warning is shown once per session, so if it fires again that's a new session -- not a per-skill repeat. If you want to silence it entirely, enable Mode B (full-fidelity orchestration via Agent Teams). Both of these conditions must be true:
echo $CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMSreturns1(not empty).gaia/config/project-config.yamlcontains:orchestration: mode: team
If either is missing the framework silently uses Mode A and re-emits the warning each session.