Google Agent ADK Guide

ADK Code Reference

by google · Apache-2.0 license · ★ 6,046 on GitHub

ADK Code Reference cover

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…

---
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: 1.8.0
  requires:
    bins:

Overview

Activate /google-agents-cli-workflow first for required development phases and scaffolding steps.

Manual install (npx, ZIP)
Claude Codenpx skills add google/agents-cli --skill google-agents-cli-adk-code -g -a claude-code
Claude Code (degit)npx degit google/agents-cli/skills/google-agents-cli-adk-code#main ~/.claude/skills/google-agents-cli-adk-code
Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md4.3 KB
Read SKILL.md here
google/main1 file shown
SKILL.md
Show the full text74 lines

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.

  1. Verify project: run agents-cli info (proceed if config exists).
  2. New project: run agents-cli scaffold create <name> — add --agent adk_go for Go.
  3. 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).
  • /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
1---
2name: google-agents-cli-adk-code
3description: >
4 This skill should be used when the user wants to "write agent code",
5 "build an agent with ADK", "add a tool", "create a callback", "define an agent",
6 "use state management" — in a project that needs ADK (Agent Development Kit) API
7 patterns and code examples.
8 It provides a quick reference for agent types, tool definitions, orchestration
9 patterns, callbacks, state management, the graph Workflow API, and reference
10 recipes to study.
11 Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment
12 (use google-agents-cli-deploy).
13metadata:
14 author: Google
15 license: Apache-2.0
16 version: 1.8.0
17 requires:
18 bins:
19 - agents-cli
20 install: "uv tool install google-agents-cli"
21---
22 
23# ADK Code Reference
24 
25Activate `/google-agents-cli-workflow` first for required development phases and scaffolding steps.
26 
27## 1. Study Recipes (No Project Needed)
28 
29**Python — read the topic index in `references/samples.md` before answering "how do I build X".**
30Worked implementations exist for: sandboxed/per-user code execution, agent-loadable `SKILL.md`
31skills, cross-session memory, approval gates before risky actions, tool guardrails, per-user
32credentials, and scheduled/event-driven runs.
33 
34**Go — read the upstream [`examples/`](https://github.com/google/adk-go/tree/main/examples).**
35clone the repo and read the one matching the capability you need before implementing it.
36 
37## 2. Prerequisites for Writing Code
38 
39Do NOT write agent code until a project is scaffolded.
40 
411. Verify project: run `agents-cli info` (proceed if config exists).
422. New project: run `agents-cli scaffold create <name>` — add `--agent adk_go` for Go.
433. Existing code: run `agents-cli scaffold enhance .`.
44 
45## Quick Reference — Most Common Patterns
46 
47See `references/adk-python.md` and `references/adk-go.md` for Python and Go code examples, respectively.
48 
49---
50 
51## References
52 
53Use the cheatsheets for common patterns. For deep knowledge, fetch the docs index or inspect the
54installed package.
55 
56| Reference | Language | When to read |
57|------|------|-------------|
58| `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. |
59| `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. |
60| `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. |
61| `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. |
62| `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. |
63| `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. |
64| [`examples/`](https://github.com/google/adk-go/tree/main/examples) | Go | Runnable upstream programs — the closest thing to a recipe catalog for Go. |
65| `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. |
66| Installed ADK package | Python | Exact signatures and symbols — inspect the source (see "Inspecting ADK Source Code" in `references/adk-python.md`). |
67 
68## Related Skills
69 
70- `/google-agents-cli-workflow` — Development workflow, coding guidelines, and operational rules
71- `/google-agents-cli-scaffold` — Project creation and enhancement with `agents-cli scaffold create` / `scaffold enhance`
72- `/google-agents-cli-eval` — Evaluation methodology, dataset schema, and the eval-fix loop
73- `/google-agents-cli-deploy` — Deployment targets, CI/CD pipelines, and production workflows
74 
View all files on GitHub →

Details

License
Apache-2.0
Stars on the repo
★ 6,046
Checked
Source
google/agents-cli ↗
Creator
google · 7 listings
View creator

Similar skills

See all →
Skillshadcn/uishadcn-ui/ui · by shadcn-uiManages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".★ 124k GitHub starsSkillLive Visual EditorBuilderIO/skills · by BuilderIOOpen and collaboratively edit a running local app in Design, with shared fallback previews and source handoff. Use when the user asks to inspect, share, or edit a real local app in Design.★ 4.5k GitHub starsSkillClaude Mods TemplatesDannyMac180/skills · by DannyMac180Patterns, cost review and ready templates for Claude Mods (Claude Code plugins whose behaviour is a function-hooks module). Adds what the built-in mod authoring does not: proven designs (fork-check-draw, tool + ledger, mode registry, artifact-backed state), prompt-cache and token-cost review, a vetting pass for someone else's mod, and rules for mods that compose. USE WHEN: build a mod, make a claude mod, mod templates, quiz me after each turn, assumptions tool / register_assumption, supervisor that checks the turn, next-steps check, mode selector / mode registry, effort by domain, model router that keeps the cache, prompt cache cost of a mod, what does this mod cost per turn, review or vet someone's mod before installing, mods that work together, Kanban artifact as shared project state. NOT FOR: classic shell-command hooks in settings.json (PreToolUse etc.), a plain skill or slash command, MCP server authoring, or looking up the hooks API itself (use the engine's plugin-authoring guidance and generated types).★ 535 GitHub starsSkillHook Variant A/B GeneratorOotto-AI/claude-content-skills · by Ootto-AIGenerates two genuinely distinct hook variants for the same reel so you can post-test which opening actually wins. Use when the user says "give me two hooks to test", "A/B this hook", "which opening should I use", "hook variants".★ 139 GitHub starsSkillPhysics-Based UI Motiondiip3sh/feel · by diip3shBuild UI interactions whose motion comes from a physical model instead of durations and easing curves. Turn a feel described in words ("a toggle that feels heavy", "a drawer with a magnetic snap", "a card you throw into a corner", "a knob with heavy detents", "a sticky slider") into a production component driven by mass, stiffness, damping and force fields (magnets, friction, walls), on a line, in a plane or around a dial, plus a test rig that plots position, velocity and the force field, overlays the model's prediction on the measured motion, and exports the same spring to Framer Motion, react-spring, SwiftUI, Compose or CSS linear(). Use this whenever someone asks for an animation, transition, spring, gesture, drag, flick, snap points, bottom sheet, toggle, slider, carousel or any micro-interaction that should "feel" a certain way, or wants to tune or explain a spring, even if they never say "physics".★ 48 GitHub starsSkillHTML Artifact Builderanthropics/skills · by anthropicsSuite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.★ 178k GitHub stars

More from google

SkillSnowflake to BigQuery Translatorgoogle/skills · by googleTranslates Snowflake dbt SQL models to Standardized BigQuery SQL. Handles SQL compilation, Jinja macro placeholder masking, BigQuery Translation Service migration workflows, AST-based config transformations, explicit type casting, JSON extraction standardization, and deduplication. Use when migrating Snowflake dbt pipelines or models to Google Cloud BigQuery. Don't use for generic BigQuery queries or non-Snowflake SQL migrations.★ 20.9k GitHub starsSkillGemini Agent API Guidegoogle/skills · by googleGuides the usage of Gemini Interactions API on Gemini Enterprise Agent Platform. Use when the user wants to use the stateful, server-managed Interactions API for multi-turn conversations, background execution, streaming, structured output, and function calling on the Agent Platform.★ 20.9k GitHub starsSkillGKE Golden Path Validatorgoogle/skills · by googleProvides GKE golden path configuration defaults, production readiness checklists, and cluster default patterns. Use when designing GKE clusters, verifying GKE production readiness, or checking configurations against GKE defaults. Don't use for setting up workload autoscaling specifically (use gke-workload-scaling instead).★ 20.9k GitHub starsSkillGoogle Agent Deployment Guidegoogle/agents-cli · by googleThis skill should be used when the user wants to "deploy an agent", deploy my ADK agent", "set up CI/CD", "configure secrets", troubleshoot a deployment", or needs guidance on Agent Runtime, Cloud Run, or GKE deployment targets, or binding an agent to an Agent Gateway. Covers deployment workflows, service accounts, rollback, and production infrastructure. Applies to any framework agents-cli deploys (ADK, LangChain, ...). Part of the agents-cli skills suite. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), evaluation (use google-agents-cli-eval), or project scaffolding (use google-agents-cli-scaffold).★ 6.2k GitHub starsSkillGoogle Cloud Cost Optimizergoogle/skills · by googleEvaluates Google Cloud workloads for cost efficiency and FinOps alignment using the Google Cloud Well-Architected Framework Cost Optimization pillar. Use when the user asks to analyze Google Cloud spend, reduce cloud bills, rightsize resources (for example, Compute, GKE, Storage, Databases), evaluate discount options (for example, CUDs, SUDs, Spot VMs), or eliminate idle capacity. Do not use for standalone product pricing lookups or non-cost architecture design.★ 20.9k GitHub starsSkillCloud Spanner Assistantgoogle/skills · by googleAssists in provisioning instances and databases, designing performant schemas, and querying data in Spanner. Use when designing primary keys, writing SQL queries or client library code, or diagnosing performance issues.★ 20.9k GitHub stars