01 · 英文原文 · 授权全文收录
Agent Skills 是什么:官方概览
完整收录标准维护者的介绍,含技能文件夹、加载过程与适用客户端;附中文译文。
- 原作者:
- Agent Skills 项目贡献者
- 核对日期:
- 2026 年 10 月 17 日
核验范围
原仓库 README 与官方概览、格式规范对照核验;已确认文档 CC BY 4.0 许可。
这是概念原文。客户端支持范围以各产品当前说明为准,未测试所有客户端。
中文译文
中文译文由作舟整理,代码保持原样;原文完整保留在下方。 排版与相对链接已转换,未执行原文中的代码;交叉核验补充另列。转载与译文遵循 CC BY 4.0,不代表原作者为本站背书。
Agent Skills
为 AI Agent 提供新能力和专业知识的标准化方式。
什么是 Agent Skills?
Agent Skills 是一种轻量、开放的格式,用来通过专业知识和工作流程扩展 AI Agent 的能力。
一个技能的核心是包含 SKILL.md 文件的文件夹。这个文件至少包含 name 和 description 元信息,以及说明如何完成特定任务的指令。技能还可以包含脚本、参考资料、模板和其他资源。
my-skill/
├── SKILL.md # 必需:元信息和指令
├── scripts/ # 可选:可执行代码
├── references/ # 可选:文档
├── assets/ # 可选:模板和资源
└── ... # 其他文件或目录
为什么使用 Agent Skills?
Agent 的能力在不断提高,但通常缺少可靠完成实际工作所需的上下文。技能把流程知识以及公司、团队和用户特定的上下文打包为可移植、可进行版本管理的文件夹,供 Agent 按需加载。这可以提供:
- 领域知识:把法律审查流程、数据分析流程、演示文稿格式等专业知识保存为可重复使用的指令和资源。
- 可重复的工作流程:把多步骤任务变成一致、可审查的流程。
- 跨产品复用:创建一个技能,在兼容技能格式的 Agent 中使用。
Agent Skills 如何工作?
Agent 通过“渐进式披露”分三个阶段加载技能:
- 发现:启动时,只加载每个可用技能的名称和描述,以判断它可能在什么时候有用。
- 激活:任务与技能描述匹配时,把完整的
SKILL.md指令读入上下文。 - 执行:按照指令操作,必要时执行附带代码或加载引用的文件。
完整指令只在任务需要时加载,因此 Agent 可以保留许多技能,而不必一开始就把所有指令都放进上下文。
可以在哪里使用?
许多 AI 工具和 Agent 客户端支持 Agent Skills。可以在客户端展示页查看其中一些产品。
入门资料
开放开发
Agent Skills 格式最初由 Anthropic 开发,作为开放标准发布,随后被越来越多 Agent 产品采用。该标准欢迎更广泛生态的贡献,贡献方式见原仓库的 CONTRIBUTING.md。
许可
该仓库代码采用 Apache 2.0,文档采用 CC BY 4.0。各目录可能有更具体的说明。
查看完整英文原文
Agent Skills
A standardized way to give AI agents new capabilities and expertise.
What are Agent Skills?
Agent Skills are a lightweight, open format for extending AI agent capabilities with specialized knowledge and workflows.
At its core, a skill is a folder containing a SKILL.md file. This file includes metadata (name and description, at minimum) and instructions that tell an agent how to perform a specific task. Skills can also bundle scripts, reference materials, templates, and other resources.
my-skill/
├── SKILL.md # Required: metadata + instructions
├── scripts/ # Optional: executable code
├── references/ # Optional: documentation
├── assets/ # Optional: templates, resources
└── ... # Any additional files or directories
Why Agent Skills?
Agents are increasingly capable, but often don't have the context they need to do real work reliably. Skills solve this by packaging procedural knowledge and company-, team-, and user-specific context into portable, version-controlled folders that agents load on demand. This gives agents:
- Domain expertise: Capture specialized knowledge — from legal review processes to data analysis pipelines to presentation formatting — as reusable instructions and resources.
- Repeatable workflows: Turn multi-step tasks into consistent, auditable procedures.
- Cross-product reuse: Build a skill once and use it across any skills-compatible agent.
How do Agent Skills work?
Agents load skills through progressive disclosure, in three stages:
Discovery: At startup, agents load only the name and description of each available skill, just enough to know when it might be relevant.
Activation: When a task matches a skill's description, the agent reads the full
SKILL.mdinstructions into context.Execution: The agent follows the instructions, optionally executing bundled code or loading referenced files as needed.
Full instructions load only when a task calls for them, so agents can keep many skills on hand with only a small context footprint.
Where can I use Agent Skills?
Agent Skills are supported by a large number of AI tools and agentic clients — see the Client Showcase to explore some of them!
Getting started
- Documentation — Guides and tutorials
- Specification — Format details
- Example Skills — See what's possible
- Discord — Share what you're building!
Open development
The Agent Skills format was originally developed by Anthropic, released as an open standard, and has been adopted by a growing number of agent products. The standard is open to contributions from the broader ecosystem — see CONTRIBUTING.md for how to get involved.
License
Code in this repository is licensed under Apache 2.0. Documentation is licensed under CC-BY-4.0. See individual directories for details.
原文快照 SHA-256:7ff4a9a612ab21189aa793fd43223bd854280a122ac12ce29f5bea84d5930a1d
交叉核验补充
以下为本站核对说明,与上方原教程区分展示。
文件结构的交叉核对
规范同样要求 SKILL.md 包含 name 和 description,并说明可附带脚本、参考资料与资源。这里展示的是原文译文,不另造练习。