Build smart AI agents that can think and act on their own. These agents use tools and memory to complete tasks. They can also work together in groups. You will learn to design safe and reliable systems.
This skill covers how to plan tasks, handle errors, and keep agents under control. It shows when to let agents work alone and when they need help. The focus is on making agents that fail clearly instead of silently.
You will master patterns like the ReAct loop and supervisor pattern. These help you build agents that can handle complex jobs. You will also learn to avoid common problems like endless loops.
Global
mkdir -p ~/.claude/skills/ai-agents-architectProject
mkdir -p .claude/skills/ai-agents-architectSource 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