/gaia-advanced-elicitation

What it does

/gaia-advanced-elicitation runs a deep requirements elicitation session using structured questioning techniques. It helps you explore requirements gaps, validate assumptions, and discover unstated needs using methods like 5 Whys, Socratic Method, User Story Mapping, MoSCoW, Kano Model, Jobs-to-be-Done, Assumption Mapping, and Stakeholder Mapping.

When to use it

• You suspect there are requirements gaps or unstated assumptions in your product definition.
• You want to use structured elicitation techniques to discover needs that brainstorming or market research did not surface.
• You want to validate assumptions before committing them to a PRD.

Prerequisites

None required. Results improve if upstream research artifacts (brainstorm, market research, domain research, technical research) are available -- the command loads and summarizes them automatically.

Orchestration mode

When /gaia-advanced-elicitation 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-advanced-elicitation skill declares orchestration_class: heavy-procedural in its SKILL.md frontmatter. Heavy-procedural 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-advanced-elicitation

/gaia-advanced-elicitation user onboarding flow

What it does step by step

1. Context gathering Loads upstream research artifacts if available. Summarizes key themes, then asks: what area to explore, who are the key stakeholders, and which gaps or assumptions to validate.
2. Method selection Presents the eight available elicitation methods with descriptions. Asks you to choose, or recommends 2-3 methods based on your context.

   Method	Best for
   5 Whys	Understanding root motivations and problems
   Socratic Method	Challenging assumptions and uncovering gaps
   User Story Mapping	Understanding workflows and user needs
   MoSCoW	Prioritizing features and requirements
   Kano Model	Feature prioritization and delight factors
   Jobs-to-be-Done	Understanding true user motivations
   Assumption Mapping	Risk identification and validation planning
   Stakeholder Mapping	Ensuring comprehensive requirements coverage

3. Elicitation execution For each selected method, runs the structured questioning flow and documents all requirements discovered.
4. Requirements synthesis Consolidates requirements across methods, removes duplicates, resolves conflicts, and categorizes each as functional, non-functional, constraint, or assumption. Tags each with source method and confidence level.
5. Generate output Writes the elicitation report: context, methods used, discovered requirements, assumptions log, gaps identified, and next steps.

Inputs

Outputs

Example session

> /gaia-advanced-elicitation user onboarding flow

Loading upstream context...
  Found: brainstorm-taskflow.md, market-research.md
  Key themes: task automation, team workflows, mid-market SaaS

What area to explore deeper?
> User onboarding -- we suspect it's underspecified.

Key stakeholders?
> End users, team admins, IT administrators

Which methods? (or let me recommend)
> recommend

Recommended: Stakeholder Mapping + User Story Mapping + 5 Whys

--- Stakeholder Mapping ---
  Identified 3 stakeholder groups with distinct needs...

--- User Story Mapping ---
  Mapped 8-step onboarding journey...
  Discovered: no story covers team-admin bulk invite flow

--- 5 Whys ---
  Root cause: onboarding friction comes from SSO config, not UI...

Requirements Synthesis:
  8 functional, 3 non-functional, 2 constraints, 4 assumptions
  3 gaps identified for further exploration

Report written to:
  .gaia/artifacts/planning-artifacts/elicitation-report-2026-05-07.md

What to run next

• /gaia-create-prd -- create a PRD from the elicited requirements.
• /gaia-product-brief -- if a product brief is needed first.

Troubleshooting

Session feels too long

Select fewer methods. For a focused session, one or two methods is sufficient. The 5 Whys method is the shortest (5 questions).

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.

Related commands