google-adk-typescript

Build TypeScript AI agents with Google ADK agent orchestration patterns.

5|Updated Feb 4, 2026
One-click install
npx skills add https://github.com/szeyu/open-ssyok-finance --skill google-adk-typescript
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: google-adk-typescript
Source: https://github.com/szeyu/open-ssyok-finance/tree/main/.agents/skills/google-adk-typescript
Command: npx skills add https://github.com/szeyu/open-ssyok-finance --skill google-adk-typescript

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

TypeScript developers can build, evaluate, and deploy production-grade AI agents using Google's ADK, leveraging a code-first approach that coordinates LlmAgent orchestration, tooling, and deployment patterns across backends and runtimes.

Core Features & Use Cases

  • LlmAgent, SequentialAgent, ParallelAgent, LoopAgent and BaseAgent patterns for complex workflows
  • Tool integration with FunctionTool, Zod validations, and multi-tool orchestration
  • Multi-agent orchestration, state management, callbacks, and deployment options (Express, Hono, Cloud Run)

Quick Start

Create a new TypeScript project, install @google/adk, and scaffold a minimal LlmAgent example

Frequently Asked Questions about google-adk-typescript

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build multi-agent orchestration in TypeScript using Google ADK?

Build multi-agent orchestration in TypeScript using Google ADK by implementing LlmAgent, SequentialAgent, ParallelAgent, and LoopAgent patterns. You coordinate complex agent workflows with state management, callbacks, and FunctionTool integrations.

Can I deploy TypeScript AI agents built with Google ADK to Cloud Run or Hono?

Yes, TypeScript AI agents built with Google ADK support deployment via Express, Hono, or Cloud Run. You containerize the agent application and deploy it to your chosen backend runtime environment.

What's the best way to validate function tool inputs in TypeScript AI agents?

The best way to validate function tool inputs in TypeScript AI agents is using Zod validations with FunctionTool. This ensures type-safe parameters and schema enforcement for multi-tool orchestration workflows.

Do I need Node.js 20 to build production-grade AI agents with Google ADK in TypeScript?

Yes, you need Node.js 20 or higher to build production-grade AI agents with Google ADK in TypeScript. This runtime requirement supports the framework's orchestration patterns and deployment capabilities.

How does multi-agent state management work in TypeScript ADK agent workflows?

Multi-agent state management in TypeScript ADK agent workflows works by coordinating shared state across LlmAgent, SequentialAgent, and ParallelAgent instances. You use callbacks and BaseAgent patterns to manage data flow between orchestration steps.

When should I use LoopAgent instead of SequentialAgent for TypeScript AI agent orchestration?

Use LoopAgent instead of SequentialAgent for TypeScript AI agent orchestration when your workflow requires iterative processing cycles. SequentialAgent executes agents in a linear chain, while LoopAgent repeats agent execution until conditions are met.