SkillFeeder › 全部 Skill › Agent工具链 › latent-briefing

在多智能体间共享压缩的推理状态,避免重复传上下文和 summarization 损失

latent-briefing

latent-briefing 是 SkillFeeder 收录的Agent Skill,来自 GitHub 仓库 muratcankoylan/Agent-Skills-for-Context-Engineering,★ 18,321。在多智能体间共享压缩的推理状态,避免重复传上下文和 summarization 损失。适合构建分层多智能体系统的开发者。场景是Agent工具链 · Agent运行时。能做的事包括用表示层而非文本层共享记忆、减少每个 worker 的 token 开销、保留 orchestrator 的完整推理轨迹。打开 GitHub 自行安装。

打开 GitHub

仓库
muratcankoylan/Agent-Skills-for-Context-Engineering
仓库星标
★ 18,321
场景
Agent工具链 · Agent运行时
适合
构建分层多智能体系统的开发者
类型
Skill

能做什么

原文简介

This skill should be used when the user asks to \"share memory between agents\", \"KV cache compaction for multi-agent\", \"orchestrator worker context\", \"latent briefing\", \"reduce worker tokens\", \"cross-agent memory without summarization\", or discusses Attention Matching compaction, recursive language models with workers, or token explosion in hierarchical agents.

同场景推荐