team

Coordinate multiple agents across plan, exec, verify, and fix stages.

Updated Mar 26, 2026
One-click install
npx skills add https://github.com/INNERJOINT/HarnessSkills --skill team-innerjoint
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: team
Source: https://github.com/INNERJOINT/HarnessSkills/tree/main/skills/team
Command: npx skills add https://github.com/INNERJOINT/HarnessSkills --skill team-innerjoint

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinates N agents to work on a shared task list using Claude Code's native team tools, enabling structured collaboration, task decomposition, and inter-agent coordination with handoffs.

Core Features & Use Cases

  • End-to-end team orchestration: plan, prd, exec, verify, and fix loops with handoffs.
  • Task creation and assignment: generate subtasks, set dependencies, and pre-assign owners.
  • Robust lifecycle management: spawn teammates, monitor progress, handle failures, resume from saved state, and perform graceful shutdown.

Quick Start

Spawn a team to decompose and execute a complex task across stages and handoffs.

Frequently Asked Questions about team

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

FAQPage Schema
How do I coordinate multiple agents on shared tasks in Claude Code?

Multi-agent coordination in Claude Code uses native team tools to manage complex tasks, enabling structured collaboration, task decomposition, and inter-agent handoffs across team-plan, team-exec, and team-verify stages.

What is the best way to decompose complex tasks for parallel execution by multiple agents?

Task decomposition for parallel execution involves generating subtasks, setting dependencies, and pre-assigning owners. This allows multiple agents to work on shared task lists concurrently with stage-based verification.

How does inter-agent communication and handoff work during multi-agent orchestration?

Inter-agent communication and handoffs work by spawning teammates, monitoring progress, and coordinating task transitions. Agents manage and complete complex tasks by passing work through structured stages like team-prd, team-exec, and team-fix.

Can I resume multi-agent task execution from a saved state after a failure?

Multi-agent task execution supports resume and cancel semantics with persistence and recovery. Robust lifecycle management handles failures by resuming from saved state and performing graceful shutdown when needed.

When do I need team orchestration for task decomposition and execution?

Team orchestration is needed when tasks require decomposition, parallel execution, and inter-agent coordination. Apply it to complex workflows that demand structured collaboration across team-plan, team-prd, team-exec, team-verify, and team-fix stages.