google-agents-cli-adk-code
🎯SkillA reference skill that helps your AI assistant write agent code with Google's ADK, a toolkit for building AI agents. It gives ready-made patterns and examples in Python and Go.
Installation
npx skills add google/agents-cli --skill google-agents-cli-adk-codeRun it in a terminal; it asks which AI coding tools to install it for (Claude Code, Codex, Cursor and more).
Uses skills.sh · Node.js 22.20+
After installing
Ask for related work and the agent uses it on its own, or call it yourself.
/google-agents-cli-adk-codeInstall by hand
Copy the whole skill folder from GitHub to the place below. Copying only SKILL.md can leave out files the skill uses.
Open the skill folder →- This project
.claude/skills/google-agents-cli-adk-code/ - All projects
~/.claude/skills/google-agents-cli-adk-code/
These paths are for Claude Code. For other tools, the command above puts it in the right place.
What this skill does
Overview
This skill gives your coding assistant code patterns and examples for ADK (Agent Development Kit), Google's toolkit for building AI agents in Python or Go. It covers agent types, tools, callbacks (code that runs at set points during an agent's work), state (information the agent keeps while it works) and the graph Workflow API (a way to connect steps like a flowchart). Before writing agent code, it checks for a project with agents-cli info, so it needs the agents-cli tool installed.
Key Features
- Find a worked Python example in
references/recipes.md, such as safe code execution, memory across sessions or approval before risky actions. - Look up core Python and Go patterns in
references/adk-python.mdandreferences/adk-go.md. - Build step-by-step graph workflows with branches and parallel steps using the Workflow API guides.
- Build real-time voice agents with help from
references/adk-python-live.md. - Follow links to the ADK docs index and the official Go
examples/when you need more detail.
Who is this for?
It fits developers who build AI agents with ADK and want their assistant to follow the real API. To create a new project or deploy it, use the separate google-agents-cli-scaffold and google-agents-cli-deploy skills.
Summarized by AI from this skill's SKILL.md. Suggest a better one
SKILL.md
View on GitHub →This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).
ADK Code Reference
Activate /google-agents-cli-workflow first.
1. Study Recipes (No Project Needed)
Python — read the topic index in references/recipes.md before answering "how do I build X".
Worked implementations exist for: sandboxed/per-user code execution, agent-loadable SKILL.md
skills, cross-session memory, approval gates before risky actions, tool guardrails, per-user
credentials, and scheduled/event-driven runs.
Go — read the upstream examples/.
clone the repo and read the one matching the capability you need before implementing it.
2. Prerequisites for Writing Code
Do NOT write agent code until a project is scaffolded.
- Verify project: run
agents-cli info(proceed if config exists). - No project: load
/google-agents-cli-workflowand agree the spec with the user (its Phase 0) before you scaffold. - Existing code: run
agents-cli scaffold enhance ..
Quick Reference — Most Common Patterns
See references/adk-python.md and references/adk-go.md for Python and Go code examples, respectively.
References
Use the cheatsheets for common patterns. For deep knowledge, fetch the docs index or inspect the installed package.
| Reference | Language | When to read |
|---|---|---|
references/recipes.md | Python | Topic-indexed catalog of ADK reference recipes. Read in workflow Phase 1 — before scaffolding and before writing code — maps a capability to the recipe that implements it. |
references/adk-python.md | Python | Core ADK API: Agent, tools, callbacks, plugins, state, artifacts, multi-agent systems, SequentialAgent / ParallelAgent / LoopAgent, custom BaseAgent, ManagedAgent (server-hosted first-party agents), A2A protocol, A2UI. Default for most agents. |
references/adk-python-workflows.md | Python | Graph-based Workflow API (ADK Python 2.0): nodes, edges, fan-out/fan-in, HITL, parallel processing. Use when you need explicit graph topology. |
references/adk-python-live.md | Python | Live and voice agents: Runner.run_live, LiveRequestQueue, model and regional availability, voice/speech_config, VAD, session limits, /run_live serving. Use for real-time voice or video agents. |
references/adk-go.md | Go | Core ADK Go API: llmagent, tools, callbacks, plugins, state, artifacts, multi-agent systems, sequential/parallel/loop agents, custom agents, the runner, serving over HTTP, A2A protocol, and ambient triggers. Default for most agents. |
references/adk-go-workflows.md | Go | Graph-based Workflow API: nodes, edges, fan-out/fan-in, HITL, parallel processing. Use when you need explicit graph topology. |
examples/ | Go | Runnable upstream programs — the closest thing to a recipe catalog for Go. |
curl https://adk.dev/llms.txt | Python | Docs index (every page title + URL). Fetch it, then WebFetch the specific page for anything beyond the cheatsheets. |
| Installed ADK package | Python | Exact signatures and symbols — inspect the source (see "Inspecting ADK Source Code" in references/adk-python.md). |
Related Skills
/google-agents-cli-workflow— Development workflow, coding guidelines, and operational rules/google-agents-cli-scaffold— Project creation and enhancement withagents-cli scaffold create/scaffold enhance/google-agents-cli-eval— Evaluation methodology, dataset schema, and the eval-fix loop/google-agents-cli-deploy— Deployment targets, CI/CD pipelines, and production workflows
More from this repository3
A guide skill that helps you deploy an AI agent built with agents-cli, so it runs online on Google Cloud. It helps you choose where to run the agent and walks you through each deploy step.
The starting skill for building AI agents on Google Cloud with agents-cli. It guides your coding assistant step by step, from planning the agent to building, testing, deploying and monitoring it.
A guide that helps you watch and debug AI agents you deployed on Google Cloud by setting up tracing, logging and analytics. It also covers outside tools such as AgentOps, Phoenix and MLflow.