jeremylongshore/tons-of-skills-marketplace / plugins/ai-ml/jeremy-genkit-pro/skills/genkit-production-expert
genkit-production-expert
VerifiedBuild 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.
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/googleaifor 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
- 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
- Initialize the project structure with appropriate config files (
tsconfig.json,genkit.config.ts, or equivalent) - Install Genkit core, provider plugins, and schema validation dependencies
- Define input/output schemas using Zod, Pydantic, or Go structs to enforce type safety at runtime
- Implement the Genkit flow using
ai.defineFlow()with model configuration, temperature tuning, and token limits - Add tool definitions using
ai.defineTool()with scoped schemas for each external capability the flow requires - For RAG flows: implement a retriever using
ai.defineRetriever()with embedding generation (text-embedding-gecko) and vector database integration - Configure error handling for safety blocks (
SAFETY_BLOCK), quota exceeded (QUOTA_EXCEEDED), and provider timeouts - Enable OpenTelemetry tracing with custom span attributes for cost and latency tracking
- Test locally using the Genkit Developer UI, then deploy to Firebase Functions or Cloud Run with auto-scaling configuration
See references/how-it-works.md for the phased workflow and references/production-best-practices-applied.md for the production checklist.
Output
- Complete Genkit flow implementation with typed schemas and model bindings
- Tool definitions with Zod/Pydantic-validated inputs and outputs
- Retriever configuration for RAG flows (embeddings, vector search, context injection)
- Deployment configuration: Firebase Functions (
firebase.json) or Cloud Run service YAML - Monitoring setup: OpenTelemetry tracing, Firebase Console integration, alert policies
- Cost optimization report: model selection rationale, token usage estimates, caching strategy
Error Handling
| Error | Cause | Solution |
|---|---|---|
SAFETY_BLOCK response | Model safety filters triggered on input or output | Review prompt content; adjust safety settings; add input sanitization before generation |
QUOTA_EXCEEDED | API rate limit or daily token quota reached | Implement exponential backoff with jitter; request quota increase; cache repeated prompts |
| Schema validation failure | Runtime input does not match Zod/Pydantic schema | Add descriptive error messages to schema; validate inputs before calling ai.generate() |
| Retriever returns empty results | Vector database query found no matches above similarity threshold | Lower similarity threshold; verify embeddings are indexed; check embedding model version match |
| Deployment timeout | Cold start exceeds Firebase Functions 60s limit | Increase memory allocation; use Cloud Run for long-running flows; enable min instances > 0 |
See references/errors.md for additional error scenarios.
Examples
Scenario 1: Question-Answering Flow -- Create a Genkit flow using Gemini 2.5 Flash with Zod input/output schemas. Set temperature to 0.3 for factual responses. Deploy to Firebase Functions with token usage monitoring. Expected latency: under 2 seconds per query.
Scenario 2: RAG Document Search -- Implement a retriever with text-embedding-gecko embeddings connected to Firestore vector search. Build a RAG flow that retrieves top-5 relevant documents, injects them as context, and generates grounded answers with source citations. Include context caching for repeated queries.
Scenario 3: Multi-Tool Agent -- Define weather and calendar tools with typed schemas. Create an agent flow that routes user queries to appropriate tools, handles multi-turn conversations, and traces each tool execution for debugging. Deploy to Cloud Run with auto-scaling (2-10 instances).
See references/workflow-examples.md for complete code examples.
Resources
- Firebase Genkit Documentation -- flows, tools, retrievers, deployment
- Genkit GitHub Repository -- source code and examples
- Zod Schema Library -- TypeScript schema validation
- OpenTelemetry for Node.js -- tracing and observability
- Gemini model selection guide: Flash for throughput, Pro for reasoning quality
- Context caching and token optimization strategies for cost management
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |