Google Adk

ALWAYS use this skill for any question involving Google ADK (Agent Development Kit). This includes: building or configuring agents (LlmAgent, SequentialAgent, LoopAgent, ParallelAgent, custom BaseAgent), writing function tools or connecting MCP/OpenAPI tools, managing sessions/state/memory, multi-agent routing and pipelines, before/after callbacks, streaming with Gemini Live API (run_live, LiveRequestQueue), deploying to Cloud Run or Vertex AI Agent Engine, evaluating agent behavior, A2A protocol, context caching/compression, grounding with Google Search. Trigger on any mention of 'adk', 'goog

9 starsAI, LLMs & Agents Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add milistu/agent-skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add milistu/agent-skills --skill google-adk
Manual install
git clone --depth 1 https://github.com/milistu/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/google-adk ~/.claude/skills/google-adk

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Google ADK

Comprehensive reference for Google's Agent Development Kit. Use this skill when:
- Creating or configuring any ADK agent (`LlmAgent`, `SequentialAgent`, `LoopAgent`, `ParallelAgent`, custom agents)
- Wiring tools to agents (function tools, built-in tools, MCP, OpenAPI, tool authentication)
- Managing sessions, state, and memory
- Building multi-agent systems or agent pipelines
- Integrating the Gemini Live API or building streaming agents
- Deploying agents to Cloud Run, GKE, or Vertex AI Agent Engine
- Evaluating agent behavior or writing agent tests
- Using the A2A (Agent-to-Agent) protocol for inter-agent communication
- Configuring callbacks, grounding, context caching, or observability

## How to Use This Skill

1. Identify the task from the Quick Reference table below
2. Load the concept reference file (prose, architecture, API parameters)
3. If you need runnable code, also load the matching language sidecar: `filename-python.md`, `filename-typescript.md`, `filename-go.md`, or `filename-java.md`

**Language sidecar files exist for these 10 high-complexity references** — load them alongside the parent when you need code examples:

| Parent file | Python sidecar | TS sidecar | Go sidecar | Java sidecar |
|---|---|---|---|---|
| `agents/llm-agents.md` | `agents/llm-agents-python.md` | `agents/llm-agents-typescript.md` | `agents/llm-agents-go.md` | `agents/llm-agents-java.md` |
Read the full skill on GitHub

Details

Skill name
google-adk
Path
skills/google-adk/SKILL.md
Repo updated
27 July 2026

FAQ

What does the Google Adk skill do?

ALWAYS use this skill for any question involving Google ADK (Agent Development Kit). This includes: building or configuring agents (LlmAgent, SequentialAgent, LoopAgent, ParallelAgent, custom BaseAgent), writing function tools or connecting MCP/OpenAPI tools, managing sessions/state/memory, multi-agent routing and pipelines, before/after callbacks, streaming with Gemini Live API (run_live, LiveRequestQueue), deploying to Cloud Run or Vertex AI Agent Engine, evaluating agent behavior, A2A protocol, context caching/compression, grounding with Google Search. Trigger on any mention of 'adk', 'goog

How do I install the Google Adk skill?

Claude Code plugin: /plugin marketplace add milistu/agent-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Google Adk popular?

It lives in milistu/agent-skills, which has 9 GitHub stars and 0 forks.

Related skills

Apple Human Interface Guidelines

9

milistu/agent-skills

Apple Human Interface Guidelines (HIG) reference for designing iOS, iPadOS, macOS, tvOS, visionOS, watchOS apps. Covers UI components, layout, accessibility, typography, navigation, inputs, and platform technologies. Use when designing Apple platform UIs, reviewing SwiftUI/UIKit patterns, or applying HIG design principles to any app.

Frontend & Design

Challenge Me

9

milistu/agent-skills

Direct technical advisor mode for counting/estimation and architecture/design

Software Development

Conventional Comments

9

milistu/agent-skills

Format review comments following the Conventional Comments standard. Use when writing code review comments, PR feedback, RFC reviews, peer reviews, or when the user asks for help with review comments.

Git & Code Review

Interpreter

5

stagentic/stagentic-promptbook

PlantUML activity diagram interpreter for stagentic-promptbook skills. Loaded by skills that include `Load the stagentic-promptbook:interpreter skill` in their body. Not a general PlantUML interpreter — defines the stagentic-promptbook keyword set.

AI, LLMs & Agents

Decisions Demo

5

stagentic/stagentic-promptbook

A small demo of the stagentic-promptbook interpreter — helps the user pick between a few options when they can't decide. Trigger on "Stagentic, help me pick", "Stagentic, decide for me", or "Stagentic, pick one".

AI, LLMs & Agents

No AI Slop

6

nehasu19/job-radar

Write like a sharp human professional, not a chatbot. Use whenever drafting or editing text someone will send or publish as their own — resumes, CVs, cover letters, LinkedIn posts, emails, bios, application answers, reports. Strips generic filler, buzzwords, inflated claims and tell-tale AI phrasing, and keeps only content that is specific, true and relevant to the reader.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.