Deep Agents let you build smart AI helpers that can split big jobs into smaller pieces. You can create special worker agents for tasks like research or coding. A main agent hands off work using a task tool and each worker runs on its own.
You can also give your agent a to-do list to plan and track steps. For sensitive actions like deploying code, you can add a human approval step. This way you stay in control before anything risky happens.
All these features come built into the standard agent setup. No extra configuration is needed to get started with subagents, planning, or approval flows.
Global
mkdir -p ~/.claude/skills/deep-agents-orchestrationProject
mkdir -p .claude/skills/deep-agents-orchestrationSource 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