building-with-google-adk
Use when building AI agents with Google's Agent Development Kit (ADK). Triggers include creating ADK agents, Gemini-powered agents, multi-agent workflows, MCP integration with ADK, agent evaluation, workflow agents (Sequential/Parallel/Loop), Vertex AI deployment, or comparing OpenAI SDK with ADK. NOT when using other frameworks (OpenAI SDK, LangChain, CrewAI) or general LLM API calls.
npx skills add majiayu000/claude-skill-registry --skill building-with-google-adk --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Building with Google ADK Build production-grade AI agents using Google's Agent Development Kit. ## Quick Start ```bash # Install ADK pip install google-adk # Or with uv (recommended) uv add google-adk # Create new agent project adk create my_agent # Run locally adk run my_agent # Web UI for debugging adk web ``` --- ## Environment Configuration ### Option A: Google AI Studio (Gemini API Key) ```bash # .env GOOGLE_API_KEY=your_gemini_api_key ``` ### Option B: Vertex AI (Production) ```bash # .env GOOGLE_GENAI_USE_VERTEXAI=TRUE GOOGLE_CLOUD_PROJECT=your_project_id GOOGLE_CLOUD_LOCATION=us-central1 ``` ```bash # Authenticate with gcloud gcloud auth application-default login gcloud services enable aiplatform.googleapis.com ``` --- ## Core Architecture ``` ┌─────────────────────────────────────────────────────────────────┐ │ ADK Architecture │ ├─────────────────────────────────────────────────────────────────┤ │ │ │ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ │ │ │ LlmAgent │ │WorkflowAgent │ │ BaseAgent │ │ │ │ (AI-driven) │ │(Deterministic)│ │ (Custom) │ │ │ └──────┬───────┘ └──────┬───────┘ └──────┬───────┘ │ │ │ │ │ │ │ └──────────┬────────┴───────────────────┘ │ │ ▼ │ │ ┌─
- Quick Start
- Environment Configuration
- Option A: Google AI Studio (Gemini API Key)
- Option B: Vertex AI (Production)
- Core Architecture
- Agent Types
- 1. LlmAgent (AI-Driven Routing)
- 2. SequentialAgent (Pipeline)
- 3. ParallelAgent (Concurrent Execution)
- 4. LoopAgent (Iterative Refinement)
- Tools
- Function Tools (Custom Python Functions)
- Built-in Tools
- AgentTool (Agent as Tool)
Install ADK pip install google-adk Or with uv (recommended) uv add google-adk Create new agent project adk create my_agent Run locally adk run my_agent Web UI for debugging adk web
What does the building-with-google-adk skill do?
Use when building AI agents with Google's Agent Development Kit (ADK). Triggers include creating ADK agents, Gemini-powered agents, multi-agent workflows, MCP integration with ADK, agent evaluation, workflow agents (Sequential/Parallel/Loop), Vertex AI deployment, or comparing OpenAI SDK with ADK. NOT when using other frameworks (OpenAI SDK, LangChain, CrewAI) or general LLM API calls.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill building-with-google-adk --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.