You can create autonomous agents that handle complex tasks without your help. These agents run in their own space and return results to you. This guide follows official best practices from Anthropic.
The skill covers everything you need. It explains the structure of an agent file with a special header section and a text prompt. You will learn how to set triggering conditions so the agent knows when to act. The guide also shows validation rules for naming and descriptions.
With this knowledge you can build agents for code review, testing, writing docs, and more. Each agent works independently and reports back to your main conversation.
Global
mkdir -p ~/.claude/skills/create-agentProject
mkdir -p .claude/skills/create-agentSource 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