agent-teams

Coordinate agent teams for parallelizable tasks with inter-agent communication and shared deliverables.

11|2|Updated May 29, 2025
One-click install
npx skills add https://github.com/yulonglin/dotfiles --skill agent-teams-yulonglin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-teams
Source: https://github.com/yulonglin/dotfiles/tree/main/claude/skills/agent-teams
Command: npx skills add https://github.com/yulonglin/dotfiles --skill agent-teams-yulonglin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrates collaborative agent teams to tackle parallelizable tasks that benefit from inter-agent communication, competing hypotheses, or multi-file integration.

Core Features & Use Cases

  • Spawn and manage agent teams using Claude Code's experimental agent teams feature.
  • Define roles, file ownership, deliverables, and communication plans for coordinated collaboration.
  • Support multiple team patterns (Research, Implementation, Debugging, Review) with spawn templates and task workflows.

Quick Start

Spawn a team with a descriptive name and assign roles to teammates following the provided prompts.

Frequently Asked Questions about agent-teams

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

FAQPage Schema
How do I coordinate parallel tasks across multiple agents for inter-agent communication?

You can coordinate parallel tasks by defining spawn templates, agent roles, and file ownership to enable structured inter-agent communication and shared deliverables.

What is the best way to test competing hypotheses during complex debugging with multiple agents?

Testing competing hypotheses during debugging is handled by spawning agent teams assigned to different perspectives, using strict guardrails and task workflows to ensure deterministic collaboration.

Can I assign specific file ownership and roles to spawned agents in a multitask workflow?

Yes, you can assign specific roles and file ownership to spawned agents, defining clear deliverables and communication plans to prevent conflicts during multi-file integration.

Does Claude Code support spawning agent teams for multi-file feature development?

Claude Code supports spawning experimental agent teams for multi-file feature development, allowing you to orchestrate parallelizable tasks with defined integration steps and shared deliverables.

When should I avoid using agent teams for research and multi-file integration?

You should avoid using agent teams for tasks that are strictly sequential or lack parallelizable components, as the overhead of coordinating inter-agent communication would provide no benefit.

How do I define task workflows and integration steps for an orchestrated agent team?

You define task workflows and integration steps by applying spawn templates that specify roles, file ownership, and communication plans, ensuring deterministic collaboration under strict guardrails.