GCP
Stack Pack.

GCP coverage focused on where Google leads: AI/ML, distributed SQL, and serverless containers. Vertex AI Agent Builder, Cloud Run jobs, Spanner + AlloyDB, BigQuery + BigLake + Dataform, Pub/Sub, GKE Autopilot, Gemini in production — opinionated about when each fits.

Why it's in the catalog. GCP has fewer services than AWS but stronger defaults for AI and data. The pack covers eight roles; the front-end / mobile / QA / vertical roles defer to general knowledge because GCP's frontier hasn't shifted there.

Headline products and features the pack carries opinions on. Each lives as its own canonical page under stacks/gcp/<product>.md in the etyb-skills repo — currency-stamped, sourced, opinionated.

• Vertex AI Agent Builder
• Gemini API
• Cloud Run (jobs + services)
• GKE Autopilot
• Spanner
• AlloyDB
• BigQuery + BigLake
• Dataform
• Pub/Sub
• Cloud Functions Gen 2
• Anthos

When /etyb routes a request to one of these roles AND the GCP pack is in play, the role's reference is composed with the platform-flavored knowledge from this stack. Same role, sharper answer.

• › system-architect
• › backend-architect
• › database-architect
• › devops-engineer
• › security-engineer
• › sre-engineer
• › ai-ml-engineer
• › saas-architect

The three things on GCP that a 2024-cutoff model is most likely to get wrong — and that this pack reflects.

• Vertex AI Agent Builder: production agent runtime with grounding, function calling, and evals
• Spanner now competes with Aurora DSQL at the global-SQL tier
• BigQuery + BigLake unify warehouse + lakehouse access patterns

The GCP pack comes with /etyb — one install, every pack ready to go. The overlay loads automatically when the work calls for it.

$ npx skills add e-t-y-b/etyb-skills

See the full install guide for Claude Code plugin and manual routes.