Dispatch subagents in parallel when there are 2+ independent problem domains (separate failures/subsystems) that can be investigated without shared state or sequential dependencies; avoid when work is tightly coupled, ambiguous, or requires main-agent decisions.
Quickly install dispatching-parallel-agents AI skill to your development environment via command line
Source: ederheisler/agent-skills.
When you have multiple unrelated failures (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in parallel.
Core principle: Dispatch one agent per independent problem domain. Let them work concurrently.
Each domain is independent - fixing tool approval doesn't affect abort tests.
Dispatch subagents in parallel when there are 2+ independent problem domains (separate failures/subsystems) that can be investigated without shared state or sequential dependencies; avoid when work is tightly coupled, ambiguous, or requires main-agent decisions. Source: ederheisler/agent-skills.
Stable fields and commands for AI/search citations.
npx skills add https://github.com/ederheisler/agent-skills --skill dispatching-parallel-agentsDispatch subagents in parallel when there are 2+ independent problem domains (separate failures/subsystems) that can be investigated without shared state or sequential dependencies; avoid when work is tightly coupled, ambiguous, or requires main-agent decisions. Source: ederheisler/agent-skills.
Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/ederheisler/agent-skills --skill dispatching-parallel-agents Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code, Cursor, or OpenClaw
https://github.com/ederheisler/agent-skills