genkit-infra-expert
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.
When & Why to Use This Skill
The Genkit Infra Expert skill is a specialized tool designed to automate the deployment of Genkit AI applications to production using Terraform. It streamlines the complex process of provisioning Google Cloud resources—including Firebase Functions, Cloud Run, and GKE clusters—while ensuring best practices for security, secret management, and observability are integrated into the AI infrastructure from the start.
Use Cases
- Production-Ready AI Deployment: Quickly transition Genkit flows from local development to scalable production environments on Google Cloud Platform using Infrastructure as Code (IaC).
- Automated Secret Management: Securely wire up Google Cloud Secret Manager to handle sensitive API keys for Gemini and other LLMs without manual configuration errors.
- AI Performance Monitoring: Automatically generate specialized dashboards to track critical metrics such as token usage, request latency, and auto-scaling performance for Genkit services.
- Standardized Infrastructure Templates: Establish a consistent Terraform baseline for AI projects, enabling teams to replicate environments across staging and production with minimal effort.
| name | genkit-infra-expert |
|---|---|
| description | | |
| allowed-tools | Read, Write, Edit, Grep, Glob, Bash(terraform:*), Bash(gcloud:*) |
| version | 1.0.0 |
| author | Jeremy Longshore <jeremy@intentsolutions.io> |
| license | MIT |
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
- Define Variables: Project ID, region, Genkit app configuration
- Provision Compute: Deploy functions or containers
- Configure Secrets: Store API keys in Secret Manager
- Set Up Monitoring: Create dashboards for token usage and latency
- Enable Auto-scaling: Configure min/max instances
- Validate Deployment: Test Genkit flows via HTTP endpoints
Output
Error Handling
See {baseDir}/references/errors.md for comprehensive error handling.
Examples
See {baseDir}/references/examples.md for detailed examples.
Resources
- Genkit Deployment: https://genkit.dev/docs/deployment
- Firebase Terraform: https://registry.terraform.io/providers/hashicorp/google/latest
- Genkit examples in {baseDir}/genkit-examples/