/gaia-tech-research

What it does

/gaia-tech-research evaluates technologies with an objective trade-off analysis. It assesses maturity, community, licensing, ecosystem quality, and production readiness, then compares alternatives across key dimensions and provides a recommendation with clear rationale.

When to use it

• You need to choose between technology options before making architecture decisions.
• You want an objective comparison rather than advocacy for a particular stack.

Prerequisites

None required. Web access improves results but is not mandatory.

Orchestration mode

When /gaia-tech-research 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-tech-research 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-tech-research

/gaia-tech-research React vs Vue vs Svelte for our dashboard

What it does step by step

1. Technology scoping Asks: what technologies to research, use case context, and constraints (team expertise, budget, timeline).
2. Web access check Tests MCP web tool availability.
3. Technology evaluation Assesses each technology for maturity, community size, learning curve, licensing, ecosystem (libraries, tools, IDE support, documentation), and production readiness.
4. Trade-off analysis Creates a pros/cons matrix, compares alternatives across dimensions, and provides a recommendation with rationale.
5. Generate output Writes the report: technology overview, evaluation matrix, trade-off analysis, recommendation, and migration/adoption considerations.

Inputs

Outputs

Output schema

The finalize.sh checklist enforces the following H2 section names verbatim against the produced artifact at .gaia/artifacts/planning-artifacts/tech-research.md. Authors (human or sub-agent) must reproduce these headings exactly — the optional numbered/lettered outline prefix is accepted (e.g. ## 1. Technology Overview, ## 1b. Technology Overview, ## 1.2 Technology Overview), but the section name itself must match.

• ## Technology Overview
• ## Evaluation Matrix
• ## Trade-off Analysis
• ## Migration
• ## Recommendation

A missing required section causes the matching SV-NN check to FAIL with the heading name in the violation line. The heading_present() helper (shared at plugins/gaia/scripts/lib/heading-present.sh) accepts every variant listed above — so do not editorialize the section name to satisfy the gate, just use one of the documented heading forms.

Example session

> /gaia-tech-research React vs Vue vs Svelte

Technologies to research?
> React, Vue.js, Svelte

Use case?
> Admin dashboard for a SaaS product, ~50 screens

Constraints?
> Team has React experience, 3-month timeline

Evaluation Matrix:
  | Dimension       | React | Vue   | Svelte |
  |-----------------|-------|-------|--------|
  | Maturity        | 10    | 9     | 7      |
  | Community       | 10    | 8     | 6      |
  | Learning curve  | 7     | 9     | 8      |
  | Bundle size     | 6     | 8     | 10     |
  | Ecosystem       | 10    | 8     | 5      |

Recommendation: React
  Rationale: Team expertise eliminates ramp-up cost.
  Largest ecosystem for admin-dashboard components.

Report written to:
  .gaia/artifacts/planning-artifacts/technical-research.md

What to run next

• /gaia-create-arch -- feed the tech trade-off analysis into architecture design.
• /gaia-product-brief -- consolidate all research into a brief.
• /gaia-advanced-elicitation -- deeper requirements exploration.

Troubleshooting

Fewer than 2 alternatives compared

The validation requires at least 2 alternatives. Provide multiple technology options when prompted.

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