team

Coordinate multiple Claude Code agents to execute and verify a shared task graph.

Updated Apr 17, 2026
One-click install
npx skills add https://github.com/dropsyoon/oh-my-claudecode --skill team-dropsyoon
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: team
Source: https://github.com/dropsyoon/oh-my-claudecode/tree/main/skills/team
Command: npx skills add https://github.com/dropsyoon/oh-my-claudecode --skill team-dropsyoon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of breaking down a large, multi-step task into coordinated parallel work, so you can get faster, more reliable results than a single agent can produce.

Core Features & Use Cases

  • N-agent orchestration with native team tools: Spawns coordinated teammates on a shared task graph with dependencies.
  • Staged pipeline with verification gates: Runs plan → PRD → exec → verify → fix loop until completion or bounded failure.
  • Specialist routing and hybrid worker support: Uses stage-appropriate agent roles, and optionally routes parts of work to codex/gemini CLI workers for one-shot execution.

Use case example: you need to fix and verify all TypeScript errors across a repo, then produce follow-up documentation and reviews; this Skill decomposes the work into file-scoped tasks, runs them in parallel, verifies, and iterates fixes when verification fails.

Quick Start

Run the team skill to execute a parallel task plan by sending: /oh-my-claudecode:team 5:executor "fix all TypeScript errors across the project".

Frequently Asked Questions about team

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

FAQPage Schema
How do I run parallel agents to fix all TypeScript errors across a repository?

Run parallel execution by spawning N coordinated agents on a shared task graph, decomposing the objective into file-scoped tasks, executing them concurrently, and iteratively fixing failures through a bounded verification loop.

What is agent orchestration for multi-step task decomposition?

Agent orchestration coordinates multiple Claude Code agents to decompose, execute, verify, and iteratively fix a shared task graph, enabling dependency-aware parallel execution for complex multi-step objectives.

Can I use hybrid worker routing to execute tasks with codex or gemini CLI?

Yes, multi-agent orchestration supports specialist routing and hybrid worker configurations, allowing you to optionally route specific workloads to codex or gemini CLI workers for one-shot execution.

How does the staged pipeline handle code verification and fix loops?

The staged pipeline handles code verification by running a plan, PRD, execution, and verification sequence, enforcing completion gates, and managing bounded fix loops until the task succeeds or hits a failure threshold.

What are the limitations of using a multi-agent team workflow for large refactors?

A limitation of multi-agent team workflows is bounded failure; if iterative fix loops cannot resolve verification failures within set limits, the task halts, making it less suited for unbounded or unpredictable architecture work.