Choosing Swarm Patterns

Choosing Swarm Patterns is an AI Engineering skill for Claude Code, published by AgentWorkforce in relay.

801 stars64 forkson AgentWorkforce/relayAdded 2026/08/23+1% in starsRepository updated 2026/08/22

agentagent-collaborationagent-communicationagent-skillsagentic-aiagentsheadlessorchestrationorchestration-systemsreal-timeslack

Install in seconds

Install Choosing Swarm Patterns

Copy Choosing Swarm Patterns into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/AgentWorkforce/relay/tree/main/.claude/skills/choosing-swarm-patterns ~/.claude/skills/choosing-swarm-patterns

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/AgentWorkforce/relay.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .claude/skills/choosing-swarm-patterns/SKILL.md in AgentWorkforce/relay
Installs to: ~/.claude/skills/choosing-swarm-patterns
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Choosing Swarm Patterns does

Choosing Swarm Patterns helps you pick the right Agent Relay orchestration pattern for coordinating multiple AI agents. Use it to choose and configure YAML or builder-based workflows for fan-out, pipeline, hub-spoke, consensus, mesh, handoff, cascade, dag, debate, and hierarchical patterns.

Choosing Swarm Patterns is cataloged under AI Engineering on DirSkills. Choosing Swarm Patterns comes from a repository tagged agent, agent-collaboration, agent-communication, agent-skills and agentic-ai.

Documentation

README

Excerpt

Choosing Swarm Patterns

Overview

The Agent Relay workflow engine (@relayflows/core) supports 24 swarm patterns via a single swarm.pattern field. Patterns are configured declaratively in YAML or programmatically via the workflow() fluent builder — there are no standalone fanOut(...) / hubAndSpoke(...) helpers. Pick the simplest pattern that solves the problem; add complexity only when the system proves it's insufficient.

Two ways to run a pattern

1. YAML (portable):

import { runWorkflow } from '@relayflows/core';

const run = await runWorkflow('workflows/feature-dev.yaml', {
  vars: { task: 'Add OAuth login' },
});

2. Fluent builder (programmatic):

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Choosing Swarm Patterns

What else does AgentWorkforce publish alongside Choosing Swarm Patterns?
Choosing Swarm Patterns is one of 25 skills that DirSkills catalogs from AgentWorkforce/relay, the repository it ships in. Its siblings there include Agent Relay, Agent Relay and Animation Review. Each one is a separate skill with its own page in this directory, installs the same way Choosing Swarm Patterns does, and is maintained by AgentWorkforce in that same repository. The rest of the collection is listed on the AgentWorkforce/relay page.
How does Choosing Swarm Patterns compare to other AI Engineering skills?
Choosing Swarm Patterns ranks #1605 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Choosing Swarm Patterns against them. Open each page to compare what they document and how they install.