genkit-infra-expert
について
このClaudeスキルは、開発者がTerraformを使用してGenkit AIアプリケーションの本番インフラストラクチャをプロビジョニングするのを支援します。Firebase Functions、Cloud Run、GKEへのデプロイを統合モニタリングおよびCI/CDと共に処理します。本番環境でGenkitワークフローのインフラストラクチャをデプロイまたは管理する必要がある場合にご利用ください。
クイックインストール
Claude Code
推奨/plugin add https://github.com/jeremylongshore/claude-code-plugins-plusgit clone https://github.com/jeremylongshore/claude-code-plugins-plus.git ~/.claude/skills/genkit-infra-expertこのコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします
ドキュメント
What This Skill Does
Expert in provisioning production infrastructure for Firebase Genkit applications using Terraform. Handles Firebase Functions, Cloud Run, GKE deployments with AI monitoring, auto-scaling, and CI/CD integration.
When This Skill Activates
Triggers: "deploy genkit with terraform", "provision genkit infrastructure", "firebase functions terraform", "cloud run deployment terraform", "genkit production infrastructure"
Core Terraform Modules
Firebase Functions Deployment
resource "google_cloudfunctions2_function" "genkit_function" {
name = "genkit-ai-flow"
location = var.region
build_config {
runtime = "nodejs20"
entry_point = "genkitFlow"
source {
storage_source {
bucket = google_storage_bucket.genkit_source.name
object = google_storage_bucket_object.genkit_code.name
}
}
}
service_config {
max_instance_count = 100
available_memory = "512Mi"
timeout_seconds = 300
environment_variables = {
GOOGLE_API_KEY = var.gemini_api_key
ENABLE_AI_MONITORING = "true"
}
}
}
Cloud Run for Genkit
resource "google_cloud_run_v2_service" "genkit_service" {
name = "genkit-api"
location = var.region
template {
scaling {
min_instance_count = 1
max_instance_count = 10
}
containers {
image = "gcr.io/${var.project_id}/genkit-app:latest"
resources {
limits = {
cpu = "2"
memory = "1Gi"
}
}
env {
name = "GOOGLE_API_KEY"
value_source {
secret_key_ref {
secret = google_secret_manager_secret.gemini_key.id
version = "latest"
}
}
}
}
}
traffic {
type = "TRAFFIC_TARGET_ALLOCATION_TYPE_LATEST"
percent = 100
}
}
AI Monitoring Integration
resource "google_monitoring_dashboard" "genkit_dashboard" {
dashboard_json = jsonencode({
displayName = "Genkit AI Monitoring"
mosaicLayout = {
columns = 12
tiles = [
{
width = 6
height = 4
widget = {
title = "Token Consumption"
xyChart = {
dataSets = [{
timeSeriesQuery = {
timeSeriesFilter = {
filter = "resource.type=\"cloud_function\" AND metric.type=\"genkit.ai/token_usage\""
}
}
}]
}
}
},
{
width = 6
height = 4
widget = {
title = "Latency"
xyChart = {
dataSets = [{
timeSeriesQuery = {
timeSeriesFilter = {
filter = "resource.type=\"cloud_function\" AND metric.type=\"genkit.ai/latency\""
}
}
}]
}
}
}
]
}
})
}
Tool Permissions
Read, Write, Edit, Grep, Glob, Bash - Full infrastructure provisioning
References
- Genkit Deployment: https://genkit.dev/docs/deployment
- Firebase Terraform: https://registry.terraform.io/providers/hashicorp/google/latest/docs/resources/cloudfunctions2_function
GitHub リポジトリ
関連スキル
content-collections
メタThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
evaluating-llms-harness
テストThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
sglang
メタSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
cloudflare-turnstile
メタThis skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.
