obra/superpowers@dispatching-parallel-agents

Dispatch parallel agents to investigate independent problem domains concurrently.

9|2|Updated Mar 18, 2026
One-click install
npx skills add https://github.com/AllBeingsFuture/AllBeingsFuture --skill obra-superpowers-dispatching-parallel-agents-allbeingsfuture
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: obra/superpowers@dispatching-parallel-agents
Source: https://github.com/AllBeingsFuture/AllBeingsFuture/tree/main/electron/embedded-assets/skills/superpowers-dispatching-agents
Command: npx skills add https://github.com/AllBeingsFuture/AllBeingsFuture --skill obra-superpowers-dispatching-parallel-agents-allbeingsfuture

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

When you have multiple unrelated failures or tasks, investigating them sequentially wastes time. Dispatch parallel agents to work on independent problem domains simultaneously.

Core Features & Use Cases

  • One agent per independent domain to avoid shared state.
  • Parallel investigation of separate problems to save time.
  • Pattern: Identify independent domains, create focused tasks, dispatch in parallel, review and integrate.

Quick Start

Initiate a parallel-dispatch workflow by assigning one agent per independent problem domain and monitor their combined results.

Frequently Asked Questions about obra/superpowers@dispatching-parallel-agents

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run multiple independent tasks in parallel using agents?

To run independent tasks in parallel, dispatch one agent per isolated problem domain. This enables concurrent execution of unrelated tasks, such as separate test files or subsystems, to save time.

When should I dispatch parallel agents for task management?

Dispatch parallel agents when you have multiple unrelated failures or tasks that can run without shared state. This pattern is ideal when several subsystems require separate investigation simultaneously.

What is the best way to investigate multiple unrelated test failures concurrently?

The best way to investigate unrelated test failures is to assign one agent per independent domain. This enforces parallel execution across separate problem domains and coordinates results to avoid interference.

Can I use parallel agents to work on tasks that share state?

No, parallel agents are designed for independent tasks that can run without shared state. You should only dispatch one agent per isolated domain to avoid interference and coordinate results effectively.

How do I start a parallel-dispatch workflow for separate subsystems?

Start a parallel-dispatch workflow by identifying independent domains, creating focused tasks, assigning one agent per domain, and monitoring their combined results to enable parallel execution.