dispatching-parallel-agents · obra/superpowers
Split independent tasks across parallel AI agents
Helps you break 2 or more independent problems — such as unrelated failing tests or separate subsystems — into focused tasks and dispatch them to agents that work concurrently, each with its own isolated context and clear scope.
Good for
- Fix several unrelated failing tests at once
- Investigate independent bugs across different subsystems
- Delegate separate research tasks to parallel agents
- Source repository
- obra/superpowers
- Category
- Coding
Open-source skills are maintained by their authors and listed as published, with attribution. Results depend on how well the skill fits your task and material.
A good place to start
Dispatch parallel agents to fix these three unrelated test failures, one agent per file, so they run concurrently.
Make your next great thing.
Bring a question, a file, or an idea that’s not quite there yet.