home / AI Agents & MCP / Dispatching Parallel Agents Skill by @obra

Dispatching Parallel Agents Skill by @obra

FREE

github stars★ 3,07,678updatedJul 2026repo@obra

activity (commits, last 6 months)

6mo ago0

this month0

$git clone https://github.com/obra/superpowers

The skill is the skills/dispatching-parallel-agents folder inside that repository. Copy it into the folder your agent loads skills from; check your agent's documentation for where that is.

about Dispatching Parallel Agents Skill by @obra

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.

our take

Tells an agent when and how to split work across several agents at once: identify independent domains, then create a focused task for each. It applies when two or more tasks share no state and have no sequence between them.

when to use it

You have several unrelated bugs or tasks to work on
You want faster progress on work that can run in parallel
You want each agent given a narrow, self-contained brief

before you install

Do not use it for tasks that touch the same files or depend on each other
Review the combined results, since parallel agents can make conflicting changes

what's inside

The original SKILL.md is organised into these sections:

Overview
When to Use
The Pattern
1. Identify Independent Domains
2. Create Focused Agent Tasks
3. Dispatch in Parallel
4. Review and Integrate
Agent Prompt Structure
Common Mistakes
When NOT to Use
Real Example from Session
Verification

source and license

Written and maintained by @obra. It is published under the MIT license, which allows reuse with attribution. SkillDirectory does not claim authorship: this page adds our own review and links back to the original, and the skill's text belongs to its author.

View the full SKILL.md on GitHub ↗

Read the opening of the original SKILL.md

# Dispatching Parallel Agents

## Overview

You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.

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.

## When to Use

```dot
digraph when_to_use {
    "Multiple failures?" [shape=diamond];
    "Are they independent?" [shape=diamond];
    "Single agent investigates all" [shape=box];
    "One agent per problem domain" [shape=box];
    "Can they work in parallel?" [shape=diamond];
…

Excerpt only, quoted from the author's repository. Open the repository for the complete file.

↓ download .zip