team

Coordinate autonomous agents on a shared task list through plan, prd, exec, verify, and fix stages.

1|Updated Apr 6, 2026
One-click install
npx skills add https://github.com/Hyeonjun0527/yeon --skill team-hyeonjun0527
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: team
Source: https://github.com/Hyeonjun0527/yeon/tree/main/.codex/skills/team
Command: npx skills add https://github.com/Hyeonjun0527/yeon --skill team-hyeonjun0527

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrates multiple agents to collaboratively work on a single task, reducing manual coordination and ensuring consistent handoffs across stages.

Core Features & Use Cases

  • Staged team pipeline (plan, prd, exec, verify, fix) with role routing
  • Handoff documentation and resume/cancel semantics
  • State persistence with MCP tools (state_write/read) and robust recovery
  • Parallel teammate spawning with internal task tracking
  • CLI worker integration (Codex/Gemini) and native Claude teammates
  • Supports cancellation and resume for interrupted sessions

Quick Start

Create a new team for the described task and monitor its progress through the full plan-prd-exec-verify-fix lifecycle.

Frequently Asked Questions about team

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

FAQPage Schema
How do I coordinate multiple autonomous agents on a shared task list?

Multi-agent coordination on shared tasks is handled by routing work through a staged pipeline of plan, prd, exec, verify, and fix stages. This orchestrates collaborative work by decomposing tasks, assigning subtasks, and tracking dependencies across N autonomous agents.

Can I resume a multi-agent workflow if a session is interrupted?

Yes, interrupted multi-agent workflows support cancellation and resume semantics. State persistence is maintained using state_write and state_read tools, enabling robust recovery and allowing the team to pick up exactly where the collaborative task left off.

What is the best way to manage task handoffs across different development stages?

Task handoffs across development stages are managed through a structured team pipeline with role routing and documentation. This ensures consistent transitions between plan, prd, exec, verify, and fix stages while tracking progress across parallel teammates.

Does multi-agent task management work with external CLI workers like Codex or Gemini?

Multi-agent task management supports CLI worker integration with Codex and Gemini alongside native Claude teammates. This enables parallel teammate spawning and internal task tracking across mixed agent environments for collaborative software development.

How do I decompose a software development task for parallel agent execution?

Software development tasks are decomposed by creating a team and assigning subtasks to parallel agents. The lifecycle manages TeamCreate, TaskCreate, and TaskUpdate operations, orchestrating dependencies through to a clean TeamDelete upon completion.

When do I need state persistence for multi-agent coordination?

State persistence for multi-agent coordination is needed when managing long-running collaborative tasks that may require interruption recovery. It uses state_write and state_read operations to maintain workflow context and ensure robust handoffs across the plan-prd-exec-verify-fix lifecycle.