genkit-production-expert

name	genkit-production-expert
description	Build production Firebase Genkit applications including RAG systems, multi-step flows, and tool calling for Node.js/Python/Go. Deploy to Firebase Functions or Cloud Run with AI monitoring. Use when asked to "create genkit flow" or "implement RAG". Trigger with relevant phrases based on skill purpose.
allowed-tools	Read, Write, Edit, Grep, Glob, Bash(cmd:*)
version	2.1.0
author	Jeremy Longshore <[e-mail]>
license	MIT
effort	medium
compatible-with	claude-code, codex, openclaw
tags	["ai","deployment","monitoring","python"]

Genkit Production Expert

Overview

Build production-grade Firebase Genkit applications including RAG systems, multi-step flows, and tool-calling agents for Node.js, Python, and Go. This skill covers the full lifecycle from project scaffolding and schema validation through flow implementation, local testing with the Genkit Developer UI, and deployment to Firebase Functions or Cloud Run with AI monitoring and OpenTelemetry tracing.

Prerequisites

• Node.js 18+ (TypeScript), Python 3.10+ (Python), or Go 1.21+ (Go) runtime
• Genkit CLI and core packages (npm install genkit @genkit-ai/googleai for TypeScript)
• Google Cloud project with Vertex AI API enabled for Gemini model access
• Firebase CLI for Firebase Functions deployments (npm install -g firebase-tools)
• Zod (TypeScript), Pydantic (Python), or Go structs for input/output schema validation
• Environment variables configured for API keys (never hardcoded; use Secret Manager)

Instructions

1. Analyze the requirements to determine target language, flow complexity (simple, multi-step, or RAG), model selection (Gemini 2.5 Flash vs Pro), and deployment target
2. Initialize the project structure with appropriate config files (tsconfig.json, genkit.config.ts, or equivalent)
3. Install Genkit core, provider plugins, and schema validation dependencies
4. Define input/output schemas using Zod, Pydantic, or Go structs to enforce type safety at runtime
5. Implement the Genkit flow using ai.defineFlow() with model configuration, temperature tuning, and token limits
6. Add tool definitions using ai.defineTool() with scoped schemas for each external capability the flow requires
7. For RAG flows: implement a retriever using ai.defineRetriever() with embedding generation (text-embedding-gecko) and vector database integration
8. Configure error handling for safety blocks (SAFETY_BLOCK), quota exceeded (QUOTA_EXCEEDED), and provider timeouts
9. Enable OpenTelemetry tracing with custom span attributes for cost and latency tracking
10. Test locally using the Genkit Developer UI, then deploy to Firebase Functions or Cloud Run with auto-scaling configuration

See ${CLAUDE_SKILL_DIR}/references/how-it-works.md for the phased workflow and ${CLAUDE_SKILL_DIR}/references/production-best-practices-applied.md for the production checklist.

Output

• Complete Genkit flow implementation with typed schemas and model bindings