multi-agent-thinker

SKILL.md

Multi-agent architectures distribute work across multiple language model instances, each with its own context window. When designed well, this distribution enables capabilities beyond single-agent limits. When designed poorly, it introduces coordination overhead that negates benefits. The critical insight is that sub-agents exist primarily to isolate context, not to anthropomorphize role division.

Multi-agent systems address single-agent context limitations through distribution. Three dominant patterns exist: supervisor/orchestrator for centralized control, peer-to-peer/swarm for flexible handoffs, and hierarchical for layered abstraction. The critical design principle is context isolation—sub-agents exist primarily to partition context rather than to simulate organizational roles.

Effective multi-agent systems require explicit coordination protocols, consensus mechanisms that avoid sycophancy, and careful attention to failure modes including bottlenecks, divergence, and error propagation.

这项技能是解决复杂问题的“重型引擎”。 **关键触发逻辑 - 仔细阅读：** IDE 必须评估用户的请求描述来决定是否调用此技能。 **调用此技能如果：** - 请求涉及**歧义**（例如，“设计一个系统......”，“分析这个......”，“你认为......怎么样”）。 - 该请求需要在编码之前进行**推理**或**规划**（例如，架构设计、权衡分析、根本原因分析）。 - 该请求暗示**多重视角**（例如“辩论”、“批评”、“全面审查”）。 - 该请求明确要求**认知策略**（苏格拉底式提问、魔鬼代言人、事前剖析、逆向工程）。 **请勿调用 IF:** - 请求是一个简单的确定性操作（例如，“修复第 10 行中的拼写错误”、“读取文件 X”、“运行命令 Y”）。 - 该请求是针对定义良好的函数的直接代码生成，无需架构思考。 当被调用时，该技能会触发多智能体认知过程来处理复杂性。 来源：codingheader/myskills。

查看原文