COLLEAGUE.SKILL: 通过专家知识蒸馏实现自动化AI技能生成
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
AI总结：
提出一个从异构痕迹到可检查、可修正、可代理使用的技能包的自动化蒸馏系统，用于生成基于人的AI技能。
摘要：
LLM代理不仅被期望完成孤立的任务，还要承载人类专业知识、判断和互动风格的有限表示。构建这种基于人的代理仍然困难，因为与人或角色相关的可操作知识通常嵌入在异构痕迹中，而不是写成清晰的指令。现有的记忆和角色系统捕捉了这些证据的片段，而技能框架提供了可移植的打包格式；然而，没有端到端的工作流将这些痕迹蒸馏成可检查、可修正和代理可用的技能。我们提出了一个自动化的痕迹到技能蒸馏系统，通过专家知识蒸馏生成基于人的AI技能。给定目标人物或角色的材料，COLLEAGUE.SKILL 生成一个版本化的技能包，包含两个协调的轨道：一个能力轨道，用于实践、心理模型和决策启发式；一个边界行为轨道，用于沟通风格、互动规则和修正历史。该包可以被检查、调用、通过自然语言反馈更新、回滚、跨代理主机安装，并可选择性地为受控分发做准备。我们描述了开源系统中实现的人工制品契约、生成工作流、修正生命周期、部署表面和领域预设。在撰写本文时，公共仓库拥有约18.5k个GitHub星标；画廊列出了来自165位贡献者的215个技能，以及跨列出的技能卡累计超过10万个星标。该系统说明了基于人的技能如何表示为可移植、可修正的包，而不是不透明的提示或隐藏的记忆。
英文摘要：
LLM agents are increasingly expected not only to complete isolated tasks, but also to carry bounded representations of human expertise, judgment, and interaction style. Building such person-grounded agents remains difficult because actionable knowledge associated with a person or role is usually embedded in heterogeneous traces rather than written as clean instructions. Existing memory and persona systems capture fragments of this evidence, while skill frameworks provide portable packaging formats; however, there is no end-to-end workflow for distilling these traces into inspectable, correctable, and agent-usable skills. We present an automated trace-to-skill distillation system for generating person-grounded AI skills via expert knowledge distillation. Given materials from a target person or role, COLLEAGUE.SKILL produces a versioned skill package with two coordinated tracks: a capability track for practices, mental models, and decision heuristics, and a bounded behavior track for communication style, interaction rules, and correction history. The package can be inspected, invoked, updated through natural-language feedback, rolled back, installed across agent hosts, and optionally prepared for controlled distribution. We describe the artifact contract, generation workflow, correction lifecycle, deployment surface, and domain presets implemented in the open-source system. At the time of writing, the public repository has approximately 18.5k GitHub stars; the gallery lists 215 skills from 165 contributors and more than 100k cumulative stars across listed skill cards. The system illustrates how person-grounded skills can be represented as portable, correctable packages rather than opaque prompts or hidden memories.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
