/gaia-design-thinking

user-facing
Category:
Creative & Collaboration
Lifecycle phase:
Any
Arguments:
[design challenge]

What it does

/gaia-design-thinking guides a human-centered design session through the five-phase Stanford d.school pipeline: Empathize, Define, Ideate, Prototype, and Test. Each phase is facilitated by the design-thinking coach (Lyra) and produces structured output that feeds the next phase.

When to use it

  • You need to deeply understand user needs before building a solution -- the Empathize phase prevents building the wrong thing.
  • You want to generate a broad set of ideas (at least 10) and narrow down to the most promising ones with low-fidelity prototypes.
  • You are stuck on a design challenge and want a structured framework to move from empathy to testable prototypes.

Prerequisites

  • No strict prerequisites. Works best when planning artifacts exist for context.

Orchestration mode

When /gaia-design-thinking 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.

This warning is shown once per session.
────────────────────────────────────────────────────────────────────────────

Why Mode B is better for this command

The /gaia-design-thinking 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-design-thinking Improve hotel check-in experience

What it does step by step

  1. Empathize Collects user insights, pain points, and context through empathy mapping.
  2. Define Synthesizes empathy data into a Point of View statement defining the core problem.
  3. Ideate Generates at least 10 ideas addressing the defined problem.
  4. Prototype Describes low-fidelity prototypes for the top ideas.
  5. Test Defines how to test prototypes with real users and what to measure.
  6. Generate artifact Writes all phase outputs to .gaia/artifacts/creative-artifacts/design-thinking-{date}.md.

Inputs

InputSourceDescription
topicCommand argument (optional)The topic or challenge. If omitted, the command asks.

Outputs

OutputLocationDescription
Creative artifact.gaia/artifacts/creative-artifacts/The session output document.

Example session

> /gaia-design-thinking Improve hotel check-in experience

Phase 1: Empathize
  Pain points: long wait times, language barriers...

Phase 2: Define
  PoV: Tired travelers need a frictionless check-in...

Phase 3: Ideate
  12 ideas generated, ranked by feasibility.

Phase 4: Prototype -- mobile self-check-in concept.
Phase 5: Test plan defined.

Written to .gaia/artifacts/creative-artifacts/design-thinking-2026-05-07.md

What to run next

  • /gaia-create-ux -- translate design thinking insights into a full UX design specification.
  • /gaia-product-brief -- formalize the top ideas into a product brief for downstream planning.

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_TEAMS returns 1 (not empty)
  • .gaia/config/project-config.yaml contains:
    orchestration:
      mode: team

If either is missing the framework silently uses Mode A and re-emits the warning each session.