skills.rest
miticojo
miticojoCOMMUNITY
Explore all skills by this author →
𝕏@miticojoGitHub

adk-skill

Develop AI agents with Google's Agent Development Kit across Python, Java, Go, and TypeScript.

18|3|Updated Feb 8, 2026
Search Tags:#agent development#multi-agent systems#adk#agentic ai#google adk#llm agents
One-click install
npx skills add https://github.com/miticojo/adk-skill --skill adk-skill
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: adk-skill
Source: https://github.com/miticojo/adk-skill/tree/main/adk-skill
Command: npx skills add https://github.com/miticojo/adk-skill --skill adk-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides comprehensive guidance and examples for building sophisticated single-agent and multi-agent AI systems using Google's Agent Development Kit (ADK).

Core Features & Use Cases

  • Agent Development: Learn to create various agent types (LlmAgent, SequentialAgent, ParallelAgent, LoopAgent).
  • Tool Integration: Implement custom Python functions, AgentTools, and MCP tools.
  • Advanced Patterns: Master multi-agent orchestration, callbacks, state management, and structured output.
  • Use Case: You need to build a multi-agent system where one agent researches a topic, another writes a report, and a third publishes it to different channels. This Skill guides you through setting up such a workflow.

Quick Start

Use the adk-skill to learn how to create a SequentialAgent with two sub-agents.

Frequently Asked Questions about adk-skill

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

FAQPage Schema
How do I build a multi-agent system using Google ADK?▼

Build a multi-agent system in Google ADK by orchestrating specialized agents like SequentialAgent or ParallelAgent. You can configure workflows where distinct agents handle research, report writing, and publishing, managing state and callbacks across the pipeline.

What types of agents can I create with Google's Agent Development Kit?▼

Google's Agent Development Kit supports creating LlmAgent, SequentialAgent, ParallelAgent, and LoopAgent. These types allow you to structure single-agent tasks or complex multi-agent orchestration workflows with structured output.

Does Google ADK support Python, Java, Go, and TypeScript for agent development?▼

Yes, Google ADK supports agent development across Python, Java, Go, and TypeScript. This allows you to implement AI agents, integrate custom tools, and deploy multi-agent systems within your preferred programming language environment.

How do I integrate custom tools and MCP tools into LLM agents?▼

Integrate custom tools into LLM agents by implementing custom Python functions, AgentTools, or MCP tools. Google ADK allows you to bind these tools to your agents, enabling them to execute external logic and interact with other systems during orchestration.

What is the best way to manage state and callbacks in multi-agent orchestration?▼

Manage state and callbacks in multi-agent orchestration by utilizing Google ADK's built-in state management features. This ensures data persistence and contextual execution across SequentialAgent and ParallelAgent workflows, maintaining structured output throughout.

Related Skills

Explore More Software Engineering Skills→
ironkid90ironkid90

google-agents-cli-adk-code

Provide Python API patterns and code examples for Google ADK agent development.

Community
Intermediate
mozilor-technologiesmozilor-technologies

start-feature-fix-agent

Automate root-cause debugging and fix implementation for workflow issues.

Official
Advanced
koralliskorallis
90

mcp-builder

Build Model Context Protocol servers and tools using the @modelcontextprotocol/sdk.

Community
Intermediate
the-perfect-developerthe-perfect-developer
11

google-adk

Automate building, orchestrating, and evaluating LLM-powered agents with Google ADK.

Community
Advanced