Dispatching Parallel Agents

Use when facing 2+ independent problems with no shared state — e.g., unrelated test failures in different subsystems, multiple independent bug investigations, parallel research tasks. Dispatch one focused subagent per domain instead of investigating sequentially.

rocm Updated 550 repo stars

File contents

rocm/rocm-systems commit 99646b70fb

Frequently asked questions

npx get-skill add rocm/dispatching-parallel-agents