Execute use when deploying Genkit applications to production with Terraform. Trigger with phrases like "deploy genkit terraform", "provision genkit infrastructure", "firebase functions terraform", "cloud run deployment", or "genkit production infrastructure". Provisions Firebase Functions, Cloud Run services, GKE clusters, monitoring dashboards, and CI/CD for AI workflows.
SkillScore36Maintained
Automatic
◆DevOps & SRE packdevopsdeploymentterraform
Last verified 8/30/2026
What it changes
Passed 8 of 22 test cases with the skill, and 6 of 22 without it.
Without skill27%
With skill36%
Checks it passed that the model alone missed
The observability configuration monitors model token usage.
The configuration uses a GCS backend for remote state storage.
The HCL files contain a backend block pointing to a GCS bucket.
2 fixed6 passed either way14 still failing0 broke
Pass-rate lift
+9 pp
Tokens
+12%
Agent turns
0%
Response time
-10%
Model gemini-3.6-flashMeasured 8/30/2026v18 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 2
Prompt
Generate Terraform code to deploy a Genkit backend on Firebase Cloud Functions. We want local execution state avoided by using cloud state, along with latency and token telemetry dashboards.
What was checked, without and with the skill
Checked
Without skill
With skill
The HCL files contain a backend block pointing to a GCS bucket.
Missed
Passed
The observability definitions include telemetry tracking for token usage.
Passed
Passed
case-09 · gemini-3.6-flash · 8/30/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md49 lines7 filesincludes scripts
Genkit Infra Expert
Overview
Deploy Genkit applications to production with Terraform (Firebase Functions, Cloud Run, or GKE) with secure secrets handling and observability. Use this skill to choose a target, generate the Terraform baseline, wire up Secret Manager, and provide a validation checklist for your Genkit flows.
Prerequisites
Before using this skill, ensure:
Google Cloud project with Firebase enabled
Terraform 1.0+ installed
gcloud and firebase CLI authenticated
Genkit application built and containerized
API keys for Gemini or other AI models
Understanding of Genkit flows and deployment options
Instructions
Choose Deployment Target: Firebase Functions, Cloud Run, or GKE
Configure Terraform Backend: Set up remote state in GCS