Dispatching Parallel Agents

When you've got multiple independent failures after a refactor, say three test files broken for different reasons, this lets you spin up parallel agents to fix them concurrently instead of grinding through sequentially. Each agent gets a focused scope (one test file, one subsystem), clear constraints (don't touch other code), and returns a summary of what they fixed. The key is independence: abort logic bugs have nothing to do with batch completion bugs, so why investigate them one at a time? Works great when problems are truly separate. Breaks down when failures are related or agents would step on each other editing the same files. The real win is turning three serial debugging sessions into one parallel effort.

skills.sh installs: 511
GitHub stars: 43.1K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add sickn33/antigravity-awesome-skills --skill dispatching-parallel-agents --agent claude-code

Installs into .claude/skills of the current project.

Files

Dispatching Parallel Agents

Overview

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: When current user/repository instructions authorize delegation, dispatch one agent per independent problem domain with disjoint file/resource ownership. This guide does not itself grant delegation authority or a model override.

When to Use

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];
    "Sequential agents" [shape=box];
    "Parallel dispatch" [shape=box];

SKILL.md on GitHub