google-agents-cli-adk-code

google/agents-cli

Quick reference for ADK Python API patterns, tools, callbacks, and agent code examples.

What is google-agents-cli-adk-code?

Use this skill when writing agent code, defining tools, managing state, or building multi-agent systems with the Google Agent Development Kit (ADK). It provides cheatsheets for common patterns and links to detailed references. Do not use for project creation (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).

Reference core ADK API: Agent, tools, callbacks, plugins, and state management
Define tool functions and integrate them into agents
Build multi-agent systems with SequentialAgent, ParallelAgent, and LoopAgent
Access graph-based Workflow API (ADK 2.0) for explicit topology control
Inspect installed ADK package source code for exact signatures and symbols
Link to comprehensive docs index and detailed references

How to install google-agents-cli-adk-code

npx skills add https://github.com/google/agents-cli --skill google-agents-cli-adk-code

Prerequisites

agents-cli installed via uv tool install google-agents-cli
Project scaffolded with agents-cli scaffold create or agents-cli scaffold enhance
agents-cli info showing valid project config

Claude Code

Cursor

Windsurf

Cline

How to use google-agents-cli-adk-code

1.Verify project is scaffolded by running agents-cli info
2.Consult references/adk-python.md for core Agent, tools, callbacks, and state patterns
3.Consult references/adk-workflows.md if you need graph-based topology
4.Use the quick reference code examples as templates for your agent definition
5.For detailed API signatures, inspect the installed ADK package source code
6.Fetch https://adk.dev/llms.txt for the docs index and link to specific pages as needed

Use cases

Good for

Writing a basic agent with tools and custom instructions
Adding new tool functions to an existing agent
Implementing callbacks for agent lifecycle events
Building multi-agent orchestration patterns
Managing agent state and artifacts across interactions

Who it's for

Python developers building agents with ADK
Backend engineers implementing multi-agent systems
AI engineers designing agent orchestration patterns
Developers extending agents with custom tools and callbacks

google-agents-cli-adk-code FAQ

When should I use this skill vs. google-agents-cli-scaffold?

Use this skill to write and modify agent code after a project is scaffolded. Use google-agents-cli-scaffold to create new projects or enhance existing ones.

What languages does ADK support?

Python is currently supported. Support for other languages is coming soon.

How do I add a tool to my agent?

Define a Python function with a docstring, then pass it in the tools list when creating an Agent: Agent(name='my_agent', tools=[my_function]).

What is the difference between ADK Python API and Workflow API?

ADK Python API is the default for most agents and covers Agent, tools, callbacks, and state. Workflow API (ADK 2.0) is graph-based and better for explicit topology, fan-out/fan-in, and parallel processing.

Where do I find exact API signatures and symbols?

Inspect the installed ADK package source code directly, or fetch https://adk.dev/llms.txt for the docs index and WebFetch specific pages.

Full instructions (SKILL.md)

Source of truth, from google/agents-cli.

name: google-agents-cli-adk-code description: > 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", or needs ADK (Agent Development Kit) Python API patterns and code examples. Part of the Google ADK skills suite. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, and state management. Do NOT use for creating new projects (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy). metadata: author: Google license: Apache-2.0 version: 0.6.1 requires: bins: - agents-cli install: "uv tool install google-agents-cli"

ADK Code Reference

Before using this skill, activate /google-agents-cli-workflow first — it contains the required development phases and scaffolding steps.

Prerequisites

Run agents-cli info — if it shows project config, skip to the reference below
If no project exists: run agents-cli scaffold create <name>
If user has existing code: run agents-cli scaffold enhance .

Do NOT write agent code until a project is scaffolded.

Python only for now. This reference currently covers the Python ADK SDK. Support for other languages is coming soon.

Quick Reference — Most Common Patterns

from google.adk.agents import Agent

def get_weather(city: str) -> dict:
    """Get current weather for a city."""
    return {"city": city, "temp": "22°C", "condition": "sunny"}

root_agent = Agent(
    name="my_agent",
    model="gemini-flash-latest",
    instruction="You are a helpful assistant that ...",
    tools=[get_weather],
)

References

The first two are cheatsheets for common patterns; for broad or deep knowledge, go to the source (docs index or installed package).

Reference	When to read
`references/adk-python.md`	Core ADK API: `Agent`, tools, callbacks, plugins, state, artifacts, multi-agent systems, `SequentialAgent` / `ParallelAgent` / `LoopAgent`, custom `BaseAgent`, A2A protocol, A2UI. Default for most agents.
`references/adk-workflows.md`	Graph-based Workflow API (ADK 2.0): nodes, edges, fan-out/fan-in, HITL, parallel processing. Use when you need explicit graph topology.
`curl https://adk.dev/llms.txt`	Docs index (every page title + URL). Fetch it, then `WebFetch` the specific page for anything beyond the cheatsheets.
Installed ADK package	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 with agents-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