adk-fundamentals

Scaffold ADK agent projects with uv and Vertex AI configuration.

2|1|Updated Jan 31, 2026
One-click install
npx skills add https://github.com/Agentient/vibekit --skill adk-fundamentals
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: adk-fundamentals
Source: https://github.com/Agentient/vibekit/tree/main/plugins/adk-tools/skills/adk-fundamentals
Command: npx skills add https://github.com/Agentient/vibekit --skill adk-fundamentals

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

ADK fundamentals provide developers with a solid starting point for building Agent Development Kit-based agents, covering environment setup, project structure, and core scaffolding.

Core Features & Use Cases

  • Environment bootstrap: Python 3.13 compatibility, uv-based project initialization, and Vertex AI readiness.
  • Canonical patterns: guidance on LlmAgent vs WorkflowAgent, session state, and memory integration.
  • Scaffolding and tooling: sample project layout and tooling considerations for ADK projects.

Quick Start

Create a new ADK agent project using uv, then install google-adk and configure Vertex AI as described.

Frequently Asked Questions about adk-fundamentals

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

FAQPage Schema
How do I set up an ADK agent project in Vertex AI?

To set up an ADK agent project in Vertex AI, initialize your environment using uv for project bootstrapping, ensure Python 3.13 compatibility, and install google-adk. This scaffolding provides the canonical project structure needed for robust agent development.

When should I use LlmAgent versus WorkflowAgent for ADK agents?

Use LlmAgent versus WorkflowAgent based on your ADK agent's core interaction logic. LlmAgent handles direct language model responses, while WorkflowAgent orchestrates multi-step processes, with canonical patterns guiding their specific session state and memory integration usage.

Does ADK scaffolding require Python 3.13 and uv?

Yes, ADK scaffolding requires Python 3.13 and uv for environment bootstrap. This specific setup ensures Vertex AI readiness and provides the standard project layout required for proper tool integration and dependency management.

What is the best way to structure tools in an ADK agent project?

The best way to structure tools in an ADK agent project is by following the canonical scaffolding patterns provided. This sample project layout establishes proper tooling considerations and tool integration patterns directly compatible with Vertex AI workflows.

Can I use ADK fundamentals for existing agent architecture onboarding?

Yes, you can use ADK fundamentals for existing agent architecture onboarding. It provides guidance on canonical agent structures, session state, and memory integration, applying foundational patterns across typical Vertex AI workflows for new and existing projects.

Why do I need environment bootstrap for ADK-based agents?

Environment bootstrap for ADK-based agents is needed to establish Vertex AI readiness and Python 3.13 compatibility. It automates foundational setup using uv, ensuring your project meets the canonical structure required for proper tool integration.