Skip to content
Get packs

Genkit Go Developer

Build AI features, agents, flows and tools in Go using the Genkit SDK

Source Download skill
Repository
google/skills
Stars
21,782
Licence
Apache-2.0
Files
15 files

What it does

Teaches an AI coding agent how to build AI-powered applications in the Go programming language with Genkit, Google's AI toolkit. Once installed, the agent knows how to set up Genkit, call language models from several providers through one interface, stream responses, call tools, define flows (server endpoints), and build conversational agents with sessions, approvals and background tasks. It also explains how to run apps through the Genkit CLI so their AI calls can be traced and inspected.

Great for

  • Go developers adding generative AI features such as chat, summarization or tool-using assistants to a backend service
  • Teams building multi-turn agents that need saved sessions, human approval steps or background tasks
  • Developers who want to inspect model calls and tool use through Genkit traces during development

Skip it if

  • Developers working in JavaScript, Python or Dart, since this skill covers only the Go SDK
  • Simple one-off API calls where a plain model SDK is enough, as the skill steers conversational work toward its experimental agent API
  • Production agent systems that must be stable: the agent API is marked experimental and may change

Try asking

  • “Create a Go service with a Genkit flow that generates a joke about a topic and serve it over HTTP”
  • “Build a multi-turn customer support agent in Go with saved sessions and a human approval step before refunds”
  • “Add a tool-calling feature to my existing Go app using Genkit and Gemini”
  • “Set up the Genkit CLI so I can see traces of every model call my Go program makes”
Step-by-step guide: how to use Genkit Go DeveloperInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 15 original files, the Apache-2.0 licence and an attribution note.

    developing-genkit-go.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip developing-genkit-go.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip developing-genkit-go.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give the agent your Go module and the provider you want to use, so it picks the right plugin and model name
  • Run the app with the Genkit CLI prefix (genkit start -- go run .) when you want traces, and remember that genkit start keeps running until you stop it
  • Keep API keys in environment variables or a secrets manager rather than in code the agent writes

What's inside

  • references/a2ui.md
  • references/agents-artifacts.md
  • references/agents-background.md
  • references/agents-branching.md
  • references/agents-custom.md
  • references/agents-deployment.md
  • references/agents-human-in-the-loop.md
  • references/agents-multi-agent.md
  • references/agents-sessions.md
  • references/agents-state.md
  • references/agents.md
  • references/flows-and-http.md
  • references/generation.md
  • references/getting-started.md
  • SKILL.md

Redistributed unmodified from google/skills under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.