Verified:GitHub

agent-delegation

Coordinate multi-agent delegation with lifecycle gates and context isolation.

154|38|Updated May 4, 2026

Search Tags:#delegation #multi-agent #orchestration #agent-coordination #context-isolation #sub-agent #lifecycle-management

One-click install

npx skills add https://github.com/kangarooking/system-prompt-skills --skill agent-delegation-kangarooking

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: agent-delegation
Source: https://github.com/kangarooking/system-prompt-skills/tree/main/agent-delegation
Command: npx skills add https://github.com/kangarooking/system-prompt-skills --skill agent-delegation-kangarooking

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

当系统提示词需要设计多代理协作架构、子代理专业化分工、代理间上下文隔离与传递机制、任务生命周期管理时调用此 Skill。适用于 AI Agent 平台、多工具编排系统、代码审查流水线、跨应用协作场景等。不适用于：单代理系统（无委派需求）、简单工具调用（无子代理概念）、纯 API 编排（无 AI 决策）。当需求聚焦于"单代理内的对话路由"而非"多代理间的任务分配"时，应该用 conversation-flow 而非本 Skill。

Core Features & Use Cases

子代理专业化：定义明确职责边界、输入输出格式与适用场景。
上下文隔离与传递：在隔离上下文中传递任务，使用简报式上下文摘要。
生命周期门控：规划 → 评审 → 执行，设置通过/驳回条件与处理流程。
输出通道隔离：内部推理/评审与最终用户可见结果分离，辅以日志策略。
跨代理协调协议：定义代理间的标准通信格式、状态信号，支持跨应用编排。
结果验证：对输出进行目标完成度、格式合规、事实一致性等多维校验，失败时支持重试或人工干预。

Quick Start

Define your multi-agent task, select specialized sub-agents, and enable the planning–review–execution lifecycle to delegate tasks safely.

Frequently Asked Questions about agent-delegation

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

FAQPage Schema

How does context isolation work in multi-agent task delegation?▼

Context isolation works by passing tasks in isolated environments using brief-style context summaries, ensuring sub-agents execute within defined boundaries while separating internal reasoning from user-visible outputs.

What is the lifecycle gate process for multi-agent task execution?▼

The lifecycle gate process enforces a planning, review, and execution sequence with defined pass or rejection conditions, ensuring sub-agent tasks meet validation criteria before proceeding to the next phase.

How do I validate multi-agent orchestration results?▼

Validate multi-agent orchestration results by checking goal completion, format compliance, and factual consistency, triggering retries or human intervention if the validation fails to meet multi-dimensional criteria.

Does multi-agent orchestration support cross-application collaboration?▼

Multi-agent orchestration supports cross-application collaboration by defining standard communication formats and status signals between agents, enabling coordinated workflows across different applications and platforms.