Builds, evaluates, and deploys code-first AI agents and multi-agent systems using Google's Agent Development Kit.
The Google ADK Python skill provides expert guidance for architecting sophisticated AI systems using the open-source Agent Development Kit. It enables developers to implement diverse agent architectures, including dynamic LlmAgents and structured workflow patterns like sequential, parallel, or loop agents. With specialized support for tool integration, human-in-the-loop approval flows, and deployment to Google Cloud infrastructure like Vertex AI Agent Engine, this skill transforms Claude into a specialized co-pilot for professional agent engineering.
主な機能
01Structured workflow patterns for sequential and parallel execution
02Hierarchical multi-agent orchestration and coordination
03Deployment patterns for Vertex AI and Google Cloud Run
041 GitHub stars
05Custom tool integration with human-in-the-loop approval flows
06Systematic agent evaluation and performance testing
ユースケース
01Developing autonomous research assistants with web search and summarization capabilities
02Creating complex data processing pipelines using structured Workflow Agents
03Deploying production-grade AI agents to Vertex AI Agent Engine
