Building an AI agent with the Agent Development Kit (ADK) starts with a clear design spec. This guide shows you a step-by-step workflow from understanding the spec to deploying the final agent. Evaluation is the most important phase to make sure the agent behaves correctly.
You will learn to preserve existing code when making changes. Only modify the lines you are asked to change. The guide also includes troubleshooting tips for common issues.
Follow the phases: understand the spec, build, evaluate, and deploy. Never skip evaluation or deploy without human approval. This skill helps you create reliable ADK agents efficiently.
Global
mkdir -p ~/.claude/skills/adk-dev-guideProject
mkdir -p .claude/skills/adk-dev-guideSource Repository
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Triagemattpocock/skills
Triage issues with a state machine driven by clear roles and agent briefs
Handoffmattpocock/skills
Hand off your work to another AI agent with a clear summary
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly