You can process many tasks at once with a swarm. Each task is one unit of work. The swarm creates a table and sends each row to a separate subagent. The results are merged back automatically.
This is useful for classifying text, extracting data, or labeling items. You do not need to write complex code for batching. The swarm handles the parallel work for you.
You can also retry only the failed tasks. Just filter by the missing result column. This saves time and effort.
Global
mkdir -p ~/.claude/skills/swarmProject
mkdir -p .claude/skills/swarmSource 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