agent-teams-playbook

Orchestrate multi-agent teams across Claude Code, Codex, OpenClaw, and Cursor workflows.

160|49|Updated Feb 14, 2026
One-click install
npx skills add https://github.com/KimYx0207/agent-teams-playbook --skill agent-teams-playbook
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-teams-playbook
Source: https://github.com/KimYx0207/agent-teams-playbook/tree/main
Command: npx skills add https://github.com/KimYx0207/agent-teams-playbook --skill agent-teams-playbook

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill solves the problem of designing reliable, cross-runtime multi-agent orchestration plans that turn ambiguous “agent swarm / multi-agent collaboration” requests into an executable workflow with clear roles, skill discovery, and quality checks.

Core Features & Use Cases

  • Agent Teams Orchestration (6-Stage Workflow): Plan first, discover skills, assemble a team, run parallel work, apply quality gates, and deliver an execution report.
  • Cross-Runtime Compatibility & Degradation: Maps an abstract orchestration contract to Claude Code, Codex, OpenClaw, and Cursor, while explicitly degrading to “main-thread staged execution” when team/tool support is missing.
  • Skill Fallback Chain for Reliability: Performs local skill scanning, then searches via find-skills when available, and finally falls back to general subagents or staged execution—without skipping required stages.

Quick Start

Ask the AI to run /agent-teams-playbook to coordinate an agent team that plans, discovers the best available skills, executes in parallel, and returns a quality-gated final deliverable.

Frequently Asked Questions about agent-teams-playbook

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

FAQPage Schema
How do I orchestrate multi-agent teams for parallel task execution?

Quality gates are mandatory checkpoints in multi-agent orchestration that validate intermediate results before final delivery. They ensure parallel agent outputs meet specified standards, preventing defective work from propagating through the workflow during the results delivery stage.

Can I use multi-agent orchestration across different coding runtimes like Claude Code and Cursor?

Cross-runtime degradation activates when native multi-agent tools are unavailable in your current environment. The orchestration contract automatically falls back to main-thread staged execution, ensuring the 6-stage workflow completes reliably even without full parallel team support.

What is the best way to handle skill discovery for agent task delegation?

The skill fallback chain scans locally first, invokes find-skills when available, then degrades to general subagents or staged execution. This layered discovery guarantees task delegation proceeds even when specific specialized skills are missing from the environment.

Why does agent orchestration require a mandatory 6-stage workflow?

The 6-stage workflow prevents skipped stages, enforces robust failure handling, and guarantees explicit degradation paths. This mandatory structure transforms ambiguous swarm requests into reliable, executable collaboration strategies with clear roles and quality checks.