agent-teams-playbook
Agent Teams Playbook provides a structured 6-stage workflow for coordinating multiple agents across different runtime platforms. It handles task planning, capability discovery, team assembly, parallel execution, and result aggregation—with built-in quality gates and cross-platform adaptation for Claude Code, Codex, OpenClaw, and Cursor.
Agent Teams Playbook orchestrates parallel agent collaboration across multiple platforms with a standardized 6-stage workflow.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-18
Agent Teams Playbook orchestrates parallel agent collaboration across multiple platforms with a standardized 6-stage workflow. Agent Teams Playbook provides a structured 6-stage workflow for coordinating multiple agents across different runtime platforms. It handles task planning, capability discovery, team assembly, parallel execution, and result aggregation—with built-in quality gates and cross-platform adaptation for Claude Code, Codex, OpenClaw, and Cursor.
Use it when
- Agent Teams Playbook enables cross-platform agent orchestration across Claude Code, Codex, OpenClaw, and Cursor.
- Agent Teams Playbook coordinates parallel agents through its structured execution stage.
Verify before relying
Read SKILL.md below before installing (13 files). Open directory: indexed for reading, not audited.
Install
KimYx0207/Kim_Service/agent-teams-playbook · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How to create agent teams with the Agent Teams Playbook?
Agent Teams Playbook guides you through a 6-stage workflow to set up multi-agent teams. Start by defining your task and discovering agent capabilities across Claude Code, Codex, OpenClaw, and Cursor. The playbook then helps you assemble the right team composition, orchestrate parallel execution, aggregate results, and apply quality gates throughout. Each stage includes adaptive logic to match agent skills to task requirements.
What platforms does Agent Teams Playbook support for orchestration?
Agent Teams Playbook enables cross-platform agent orchestration across Claude Code, Codex, OpenClaw, and Cursor. The framework abstracts platform differences so you can coordinate agents regardless of their runtime environment. This multi-platform approach lets you leverage specialized capabilities from each system while maintaining unified team governance and quality standards.
How does Agent Teams Playbook handle parallel agent coordination?
Agent Teams Playbook coordinates parallel agents through its structured execution stage, which distributes tasks across team members simultaneously. The framework manages task dependencies, monitors execution progress, and synchronizes results. Built-in quality gates validate outputs before aggregation, ensuring reliable parallel execution without bottlenecks or coordination failures.
What's the difference between subagent and agent team models?
Agent Teams Playbook helps you choose between collaboration models: subagents operate hierarchically under a parent agent, while agent teams operate as peer networks with distributed decision-making. The playbook provides guidance on when each model suits your workflow—subagents for sequential delegation, agent teams for parallel complex tasks requiring diverse expertise.
How does Agent Teams Playbook implement quality gates?
Agent Teams Playbook embeds quality gates at multiple workflow stages: capability validation during discovery, team composition review before assembly, execution monitoring during parallel work, and result verification before aggregation. These governance checkpoints ensure agent outputs meet standards and catch issues early, maintaining reliability across multi-agent workflows.
What best practices does Agent Teams Playbook teach for adaptive team formation?
Agent Teams Playbook covers adaptive team formation through skill discovery and dynamic delegation. It teaches how to assess agent capabilities, match them to task requirements, and adjust team composition based on real-time performance. The playbook emphasizes continuous learning from execution outcomes to improve future team assembly decisions.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Agent Teams 编排手册
作为 Agent Teams 协调器，你的职责包括：明确每个角色的职责边界、把控执行过程、对最终产品质量负责。
> 核心理解（铁律）：Agent Teams 是"并行处理 + 结果汇总"模式，不是扩大单个 agent 的上下文窗口。每个 teammate 是独立的执行单元，拥有独立上下文，可以并行处理大量信息，但最终需要将结果汇总压缩后返回主会话。
(truncated - see the full file via the links below)
File tree — 13 files
skills/agent-teams-playbook/.gitattributes
skills/agent-teams-playbook/.gitignore
skills/agent-teams-playbook/CHANGELOG.md
skills/agent-teams-playbook/LICENSE
skills/agent-teams-playbook/NOTICE
skills/agent-teams-playbook/README.md
skills/agent-teams-playbook/README_EN.md
skills/agent-teams-playbook/SKILL.md
skills/agent-teams-playbook/images/二维码基础款.png
skills/agent-teams-playbook/images/微信.jpg
skills/agent-teams-playbook/images/支付宝.jpg
skills/agent-teams-playbook/scripts/install.sh
skills/agent-teams-playbook/tests/runtime-contracts.test.mjs
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Set up multi-agent teams for parallel task execution and coordination”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Review Swarm runs four specialized read-only agents in parallel to examine a git diff or file scope for behavioral regressions, security risks, performance issues, and coverage gaps. The main agent then filters and ranks findings by severity, delivering only high-signal issues with a clear fix path—no file edits or automated fixes applied.
Teams Management provides REST API endpoints for setting up collaborative workspaces within XActions. Create teams, invite members with specific roles (owner, admin, editor, viewer), and manage permissions across your automation projects. Teams share operation quotas and enforce role-based access at the API level.
This skill extends Telegram integration to support agent teams, giving each subagent its own bot identity in group conversations. Pool bots are dynamically assigned and renamed to match agent roles, letting users see exactly which team member is responding. Requires prior Telegram configuration via /add-telegram.
Add Telegram Swarm extends your Telegram setup to support agent teams, where each subagent gets its own bot identity in the group. Messages from different agents appear from different bots, making it clear who's speaking. Requires prior Telegram configuration via the base skill.
Skill Generator is a meta-skill that creates new Claude Code skills from user specifications, supporting both sequential (fixed-order phases) and autonomous (dynamic routing) execution patterns. It scaffolds complete skill packages including directory structure, phase files, specifications, and templates while enforcing design standards.
Worktrunk is a CLI that streamlines git worktree management, making it as straightforward as branching. Launch multiple AI agents in parallel across isolated branches, each with its own environment, and automate setup through hooks for dev servers, databases, and dependencies. Features include LLM-generated commit messages, Claude Code integration, and Zellij support for seamless agent handoffs.
More skills agents-mcp (MIT)