Build production-ready AI workflows using Firebase Genkit. Use when creating flows, tool-calling agents, RAG pipelines, multi-agent systems, or deploying AI to Firebase/Cloud Run. Supports TypeScript, Go, and Python with Gemini, OpenAI, Anthropic, Ollama, and Vertex AI plugins.
90
88%
Does it follow best practices?
Impact
92%
1.13xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Flow definitions with Zod schemas and null output handling
Zod input schema
100%
100%
Zod output schema
100%
100%
ai.defineFlow usage
100%
100%
Null output guard
100%
100%
No hardcoded API keys
100%
100%
Env var API key
100%
100%
Correct model reference
0%
100%
ESM module type
0%
100%
Correct package names
100%
100%
genkit start with command
100%
100%
inputSchema and outputSchema on flow
100%
100%
Tool-calling agent with ai.run() tracing
ai.defineTool name field
100%
100%
ai.defineTool description field
100%
100%
Tool inputSchema
100%
100%
Tool outputSchema
100%
100%
Async tool handlers
100%
100%
Tools array in generate
100%
100%
returnToolRequests false
0%
0%
ai.run() for custom steps
0%
100%
Agent wrapped in defineFlow
100%
100%
Flow Zod schemas
100%
55%
No hardcoded API keys
100%
100%
Null output guard
0%
0%
GENKIT_ENV=dev documentation
0%
60%
Streaming flows and multi-agent pipeline separation
streamSchema defined
100%
100%
sendChunk usage
90%
100%
generateStream used
37%
75%
Separate specialist subflows
100%
100%
Orchestrator delegates to subflows
100%
100%
Dotprompt file created
100%
100%
Dotprompt YAML frontmatter
100%
100%
Dotprompt loaded in code
100%
100%
Flow Zod schemas
100%
100%
No hardcoded API keys
100%
100%
genkit start with command
100%
100%
Null output guard
40%
100%
c033769
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.