Dispatching Parallel Agents
obra/superpowersWhen you have many different problems to fix at once, you can send each one to a separate expert helper. Each helper works on its own problem without needing to know about the others. This way you fix everything much faster.
These helpers are called agents. You give each agent a clear job and the specific details they need. They never look at your whole conversation history. They just focus on their one task. You stay free to coordinate everything.
This approach works best when the problems are truly independent. For example, three different test files failing for different reasons. Each agent can fix one file. You save time by having them work at the same time.
Add Dispatching Parallel Agents skill to your workflow
Global
mkdir -p ~/.claude/skills/dispatching-parallel-agentsProject
mkdir -p .claude/skills/dispatching-parallel-agentsSource Repository
More AI & Agent Building Claude Code Skills
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