dispatching-parallel-agents

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

509 stars

Best use case

dispatching-parallel-agents is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

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

Teams using dispatching-parallel-agents should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/dispatching-parallel-agents/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/methodologies/superpowers/skills/dispatching-parallel-agents/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/dispatching-parallel-agents/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How dispatching-parallel-agents Compares

Feature / Agent	dispatching-parallel-agents	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

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

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Dispatching Parallel Agents

## Overview

One agent per independent problem domain. Let them work concurrently.

**Core principle:** Dispatch one agent per independent problem domain.

## When to Use

- 3+ test files failing with different root causes
- Multiple subsystems broken independently
- Each problem understood without context from others
- No shared state between investigations

## When NOT to Use

- Failures are related (fix one might fix others)
- Need full system state understanding
- Agents would interfere (editing same files)

## Process

1. Identify independent domains
2. Dispatch agents in parallel (ctx.parallel.all)
3. Check for conflicts between solutions
4. Run full test suite to verify integration

## Agents Used

- Process agents defined in `dispatching-parallel-agents.js`

## Tool Use

Invoke via babysitter process: `methodologies/superpowers/dispatching-parallel-agents`

Related Skills

parallel-patterns

509

from a5c-ai/babysitter

GPU parallel algorithm design patterns and implementations. Implement parallel reduction, scan/prefix sum, histogram, parallel sort algorithms, stream compaction, and work-efficient patterns optimized for specific GPU architectures.

Parallel Orchestration

509

from a5c-ai/babysitter

Coordinate multiple specialized agents across parallel work streams with quality gates and conflict resolution.

process-builder

509

from a5c-ai/babysitter

Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.

Workflow & Productivity

babysitter

509

from a5c-ai/babysitter

Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)