skills.rest
Mtettey29
Mtettey29COMMUNITY
Explore all skills by this author →
WebsiteGitHub

adk-agent-development

Develop ADK agents with setup, tooling, and Cloud Run deployment patterns.

Updated Apr 4, 2026
Search Tags:#gemini#state-management#adk#agent-development#cloud-run#toolbox-adk#mcp-toolbox
One-click install
npx skills add https://github.com/Mtettey29/restaurant-concierge-sdd --skill adk-agent-development
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: adk-agent-development
Source: https://github.com/Mtettey29/restaurant-concierge-sdd/tree/main/.agents/skills/adk-agent-development
Command: npx skills add https://github.com/Mtettey29/restaurant-concierge-sdd --skill adk-agent-development

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Comprehensive guide for building, developing, and deploying AI agents using Google's Agent Development Kit (ADK) with Gemini models, covering agent creation, tools, state management, persistence, deployment, and database integration via MCP Toolbox.

Core Features & Use Cases

  • Step-by-step codelab-based guidance for setting up ADK projects, creating root agents, configuring tools, and deploying to production.
  • Includes patterns for tool orchestration, sub-agents, Langchain integration, and database-backed state persistence.
  • Real-world examples and best practices across the full agent lifecycle.

Quick Start

Run adk web to interactively test a basic ADK agent after scaffolding the project.

Frequently Asked Questions about adk-agent-development

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

FAQPage Schema
How do I deploy an ADK agent to Cloud Run?▼

To deploy an ADK agent to Cloud Run, you follow production-grade deployment patterns that include scaffolding the project, wiring necessary tools, and configuring reproducible setups for Google's Agent Development Kit.

How does state management and session persistence work with ADK agents?▼

State management and session persistence for ADK agents work by integrating database-backed persistence patterns via MCP Toolbox, ensuring that agent state is maintained across interactions and sessions throughout the lifecycle.

Can I integrate Langchain tools with Google ADK agents?▼

Yes, you can integrate Langchain with Google ADK agents. The integration provides patterns for tool orchestration and sub-agent coordination, allowing you to wire external tools into your root agent configuration effectively.

What is the best way to test an ADK agent locally during development?▼

The best way to test an ADK agent locally during development is by running the 'adk web' command, which lets you interactively test your basic ADK agent immediately after scaffolding the project.

Do I need MCP Toolbox to build ADK agents with Gemini models?▼

You do not strictly need MCP Toolbox for basic creation, but it is required for database-backed state persistence and advanced tool integration when building and managing ADK agents powered by Gemini models.

Related Skills

Explore More Software Engineering Skills→
hpurihpuri

Agent Engine Python Deployer

Deploy ADK agents to Vertex AI Agent Engine and register them with Gemini Enterprise.

Community
Advanced
hq-opensourcehq-opensource
9

adk-deploy-guide

Guide ADK agent deployment to Google Cloud with Agent Engine, Cloud Run, and GKE.

Official
Advanced
zhuxiningzhuxining

mcp-builder

Build MCP servers in Python FastMCP or Node.js MCP SDK with structured schemas and error handling.

Community
Advanced
felix-howardfelix-howard

ck:google-adk-python

Create, evaluate, and deploy AI agents with the Google ADK Python toolkit.

Community
Advanced