发表机构
SylphAI; The University of Texas at Austin（西尔菲人工智能公司; 德克萨斯大学奥斯汀分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对当前智能体技能安装模式下触发槽位稀缺的问题，提出@skills开放协议，分离技能的内容、持久化与自动触发功能，无需安装即可使用技能，通过Git管理实现灵活适配，搭配免费技能 hub 提供搜索等功能，减少安装、提升使用效率。
AI 中文摘要
当前共有56804个公开智能体技能，各团队还会编写更多私有技能。主流交付模式为安装：技能安装后，其描述会保留在系统提示词中，争夺不足100个可靠触发槽位。这使得长尾技能缺乏实用使用路径，且迫使团队自身的剧本也争夺相同的稀缺空间。我们发现安装包含三个可分离的功能：内容、持久化和自动触发，仅最后一个需要提示词驻留。因此我们提出@skills，一个将三者分离的开放协议。路径可指向任何技能、子树或集合，读取技能即可使用，无需安装或驻留。操作会将副本在同一路径下存入项目的Git跟踪树中，用于适配和所有权。操作添加一行.gitignore样式的内容，这是唯一需要提示词驻留的元素。目录即菜单，使包成为普通目录而非全有或全无的单元。该协议不需要清单、锁文件或注册，此http URL保持不变。@skills是可添加的，作为可安装包交付，通过单个指令文件将任何能读取文件和运行命令的智能体转变为客户端。其开放规范在此https URL，AdaL CLI已实现该协议在此https URL。由于路径能很好地指向技能但无法找到它们，该协议搭配一个免费 hub 在此https URL，用于语料库范围的搜索和排名、无仓库托管、私有和团队集合，以及单屏幕创作。该 hub 是可选的：gh:和本地路径无需它即可解析，已索引的GitHub技能保留其gh:标识。少安装，多使用。
英文摘要
There are 56,804 public agent skills today, and teams write many more privately. The dominant delivery model is installation: once installed, a skill's description remains in the system prompt, competing for fewer than 100 reliable trigger slots. This leaves the long tail with no practical path to use and forces teams' own playbooks to compete for the same scarce space. We observe that installation bundles three separable functions: content, persistence, and automatic triggering. Only the last requires prompt residency. We therefore propose @skills, an open protocol that separates them. A path addresses any skill, subtree, or collection, and reading a skill is sufficient to use it, so nothing is installed or made resident. The operation vendors a copy at the same path into a project's Git-tracked tree for adaptation and ownership. The operation adds one .gitignore-style line, the only element that costs prompt residency. A directory is a menu, making bundles ordinary directories rather than all-or-nothing units. The protocol requires no manifest, lockfile, or registration, and SKILL.md remains unchanged. @skills is additive, ships as an installable package, and turns any agent that can read files and run commands into a client through a single instruction file. Its open specification is at https://github.com/SylphAI-Inc/atskills and it is implemented in the AdaL CLI at https://adalagent.ai . Because paths address skills well but cannot find them, the protocol is paired with a free hub at https://atskills.one for corpus-wide search and ranking, repository-free hosting, private and team collections, and one-screen authoring. The hub is optional: gh: and local paths resolve without it, and indexed GitHub skills retain their gh: identities. Install less, use more.
Comments7 pages main, 23 pages in total with appendix, 6 figures
