google-agents-cli-adk-code
google/agents-cli
Quick reference for ADK agent code patterns, tools, callbacks, and state management.
What is google-agents-cli-adk-code?
This skill provides code examples and API reference for building agents with Google's Agent Development Kit (ADK) in Python or Go. Use it when writing agent logic, defining tools, implementing callbacks, managing state, or studying reference recipes—after scaffolding a project.
- Access topic-indexed recipe catalog for common agent capabilities (sandboxed execution, skills, memory, approval gates, guardrails)
- Reference core ADK APIs: Agent types, tool definitions, callbacks, plugins, state management, and artifacts
- Study graph-based Workflow API for explicit topology (fan-out/fan-in, HITL, parallel processing)
- Learn live and voice agent patterns with Runner.run_live, speech config, and VAD
- Inspect multi-agent orchestration: SequentialAgent, ParallelAgent, LoopAgent, and custom agents
- Access Go examples from upstream repository and Python cheatsheets for quick implementation
How to install google-agents-cli-adk-code
npx skills add https://github.com/google/agents-cli --skill google-agents-cli-adk-code- agents-cli installed via uv tool install google-agents-cli
- Project scaffolded with agents-cli scaffold create or agents-cli scaffold enhance
- Activate /google-agents-cli-workflow skill for development workflow context
How to use google-agents-cli-adk-code
- 1.Run agents-cli info to verify your project configuration exists
- 2.Read references/samples.md (Python) or examples/ (Go) to find a recipe matching your capability
- 3.Consult the appropriate cheatsheet: adk-python.md, adk-go.md, adk-python-workflows.md, or adk-go-workflows.md
- 4.For live/voice agents, reference adk-python-live.md for Runner.run_live and speech config
- 5.Inspect the installed ADK package source or fetch curl https://adk.dev/llms.txt for deeper API documentation
Use cases
- Building a Python agent with custom tools and state management by referencing adk-python.md
- Implementing a graph-based workflow with fan-out/fan-in logic using the Workflow API
- Creating a live voice agent with speech configuration and session management
- Studying a reference recipe to add approval gates or per-user credentials to an existing agent
- Comparing sequential vs. parallel agent patterns to choose the right orchestration for your use case
- Backend engineers building AI agents with ADK in Python or Go
- Agent developers implementing multi-agent systems or complex orchestration patterns
- Developers adding tools, callbacks, or state management to existing agents
- Teams evaluating agent patterns before writing production code
google-agents-cli-adk-code FAQ
Use this skill to write and reference agent code patterns. Use google-agents-cli-scaffold to create or enhance a project structure before you start coding.
Core ADK (adk-python.md, adk-go.md) covers Agent, tools, callbacks, and state for most agents. Workflow API (adk-python-workflows.md, adk-go-workflows.md) provides explicit graph topology for complex fan-out/fan-in and HITL patterns.
Clone https://github.com/google/adk-go and read the examples/ directory. Each example demonstrates a specific capability you can study and adapt.
Read references/adk-python-live.md for Runner.run_live, speech_config, VAD, and session limits. Go does not have a separate live reference yet.
Fetch curl https://adk.dev/llms.txt to get the docs index, then use WebFetch to retrieve specific pages. You can also inspect the installed ADK package source directly.
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" — 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). metadata: author: Google license: Apache-2.0 version: 1.7.0 requires: bins: - agents-cli install: "uv tool install google-agents-cli"
ADK Code Reference
Activate /google-agents-cli-workflow first for required development phases and scaffolding steps.
1. Study Recipes (No Project Needed)
Python — read the topic index in references/samples.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). - New project: run
agents-cli scaffold create <name>— add--agent adk_gofor Go. - 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/samples.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
Related skills
More from google/agents-cli and the wider catalog.
google-agents-cli-deploy
Deploy agents to Agent Runtime, Cloud Run, or GKE with agents-cli.
google-agents-cli-eval
Evaluate and optimize AI agents with dataset generation, metrics, and failure analysis.
google-agents-cli-observability
Set up tracing, logging, and monitoring for deployed agents with Cloud Trace, BigQuery analytics, and third-party integrations.
google-agents-cli-publish
Publish and register agents with Gemini Enterprise via Agent-to-Agent or ADK modes.
google-agents-cli-scaffold
Scaffold new agent projects and add deployment, CI/CD, and infrastructure to existing ones.
google-agents-cli-workflow
CLI toolkit for building, evaluating, and deploying agents on Google Cloud with the Agent Development Kit.