team

Orchestrate parallel Claude Code workflows with independent teammates.

3|1|Updated Dec 5, 2025
One-click install
npx skills add https://github.com/trungdo9/ClauKit --skill team-trungdo9
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: team
Source: https://github.com/trungdo9/ClauKit/tree/main/skills/software/team
Command: npx skills add https://github.com/trungdo9/ClauKit --skill team-trungdo9

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires Claude Code 2.1.0 or later, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of managing complex parallel workflows by enabling teams of Claude Code teammates to work independently, share information, and coordinate their efforts efficiently.

Core Features & Use Cases

  • Parallel Workstream Execution: Run multiple Claude Code instances in parallel, each handling a different aspect of a project.
  • Persistent Context Windows: Teammates have their own context windows, task ownership, and persistent memory across sessions.
  • Use Case: For projects involving multiple teams working on different components, such as API, UI, and DB layers, this Skill allows each team to work in parallel while maintaining context and communication.

Quick Start

To create a team for parallel work on a project, use the command: /ck:team <template> <context> [flags]

Frequently Asked Questions about team

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

FAQPage Schema
How do I run parallel workflows with Claude Code teammates?

You can orchestrate Claude Code teammates to execute parallel workflows concurrently. Each teammate operates within an independent context window and maintains persistent memory across sessions for complex projects.

What is parallel workstream management for AI collaboration?

Parallel workstream management for AI coordination enables multiple Claude Code instances to work independently on different project components like API, UI, and DB layers, while sharing information and coordinating efforts efficiently.

How do I start a team for concurrent project execution?

To start a team for concurrent project execution, use the command `/ck:team <template> <context> [flags]`. This initializes parallel Claude Code instances configured with separate task ownership and persistent memory.

Do I need a specific Claude Code version to enable agent teams?

Yes, you need Claude Code 2.1.0 or later to enable agent teams. This version is required to support the independent context windows and parallel execution orchestration features.

Can I use parallel Claude Code instances for different project layers?

Yes, you can use parallel Claude Code instances for different project layers. The team Skill allows separate instances to concurrently handle API, UI, and DB layers while maintaining their own context and communication.

When should I avoid using parallel AI teammates for project coordination?

You should avoid using parallel AI teammates if your project does not require concurrent execution or if your environment lacks Claude Code 2.1.0 or later. The Skill is specifically designed for complex projects requiring independent workstreams.