You can build your own AI agent from start to finish with a simple command line tool. This skill guides you through every step: planning, creating code, testing, deploying, and watching your agent work. Google's Agent Development Kit makes it easy to turn your ideas into a real agent.
Before you write any code, you first set up your project using the agents-cli tool. It adds all the needed files and rules. Then you build the agent, run tests, and send it live to the cloud. You can also see how your agent behaves after launch with built in monitoring.
This workflow works with any coding assistant like Gemini or Claude. It helps you avoid common mistakes and follow best practices for agent development. No deep technical knowledge is required to get started.
Global
mkdir -p ~/.claude/skills/google-agents-cli-workflowProject
mkdir -p .claude/skills/google-agents-cli-workflowSource 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
Skill Creatoranthropics/skills
Create, test, and improve AI agent skills with easy step-by-step guidance
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
Openclaw Secure Linux Cloudxixu-me/skills
Secure self-hosting of OpenClaw with private control and SSH tunneling