COLLEAGUE.SKILL：透過專家知識蒸餾實現自動化AI技能生成

摘要

大语言模型智能体越来越被期望不仅能完成孤立的任务，还能承载人类专业知识、判断力和互动风格的有限表征。构建此类基于角色的智能体仍然困难，因为与个人或角色相关的可操作知识通常嵌入在异质痕迹中，而非以清晰的指令形式存在。现有的记忆与人设系统虽能捕获这些证据的片段，而技能框架则提供了可移植的封装格式；然而，目前尚无一个端到端的工作流来将这些痕迹提炼为可审查、可修正且可被智能体使用的技能。我们提出了一种自动化痕迹到技能的提炼系统，通过专家知识蒸馏生成基于角色的AI技能。给定目标人物或角色的素材，COLLEAGUE.SKILL会生成一个带版本的技能包，包含两个协同轨道：一个能力轨道，涵盖实践、心理模型和决策启发式；另一个是有界行为轨道，涵盖沟通风格、交互规则和修正历史。该技能包可被审查、调用、通过自然语言反馈进行更新、回滚、跨智能体主机安装，并可选择性地进行受控分发。我们描述了开源系统中实现的制品契约、生成工作流、修正生命周期、部署界面和领域预设。截至撰写时，公共仓库已获得约18.5k颗GitHub星标；技能展示列表包含来自165位贡献者的215个技能，各技能卡累计获得超过10万颗星标。该系统展示了如何将基于角色的技能表示为可移植、可修正的包，而非不透明的提示或隐藏的记忆。

English

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.