状态：选秀 版本：0.2.0 发布日期：2026-01-17 更新日期：2026-03-12

目录

1. 摘要
2. 更新日志
3. 术语
4. 问题
5. 解决方案
6. URI结构
7. 技能目录内容
8. 渐进披露
9. 发现索引
10. 完整性与验证
11. 档案分发
12. 示例
13. HTTP 考虑因素
14. 客户端实现
15. 安全考量
16. 与现有规范的关系
17. 参考文献

摘要

本文档定义了一种机制，用于使用 RFC 8615 中规定的 .well-known URI 路径前缀来发现代理技能。技能目前分散在 GitHub 仓库、文档网站及其他来源中。一个知名的 URI 为代理和工具提供了一个可预测的位置，帮助他们发现组织或项目发布的技能。

更新日志

v0.2.0

• 将知名的URI从/.well-known/skills/重命名为/.well-known/agent-skills/
• 用 $schema URI（https://schemas.agentskills.io/discovery/0.2.0/schema.json）替换 version 字段

Agent Skills Discovery via Well-Known URIs

Status: Draft Version: 0.2.0 Published Date: 2026-01-17 Updated Date: 2026-03-12

Table of Contents

1. Abstract
2. Changelog
3. Terminology
4. Problem
5. Solution
6. URI Structure
7. Skill Directory Contents
8. Progressive Disclosure
9. Discovery Index
10. Integrity and Verification
11. Archive Distribution
12. Examples
13. HTTP Considerations
14. Client Implementation
15. Security Considerations
16. Relationship to Existing Specifications
17. References

Abstract

This document defines a mechanism for discovering Agent Skills using the .well-known URI path prefix as specified in RFC 8615. Skills are currently scattered across GitHub repositories, documentation sites, and other sources. A well-known URI provides a predictable location for agents and tools to discover skills published by an organization or project.

Changelog

v0.2.0

• rename well-known URI from /.well-known/skills/ to /.well-known/agent-skills/
• replace version field with $schema URI (https://schemas.agentskills.io/discovery/0.2.0/schema.json)
• replace files array and package object with a flat single-artifact model: each skill entry now has type ("skill-md" or "archive"), url, and digest
• digest is now the SHA-256 of the single artifact (not a manifest-derived skill-level digest)
• add archive safety guidance: path traversal, symlinks, decompression bombs
• add URL resolution semantics per RFC 3986
• add RFC 2119 / RFC 8174 keyword conventions
• strengthen script execution guidance — clients SHALL NOT execute scripts by default
• add “Integrity and Verification” section
• add “Archive Distribution” section
• add backward-compatibility guidance for v0.1.0 clients

v0.1.0

• initial draft

Terminology

The key words “MUST”, “MUST NOT”, “REQUIRED”, “SHALL”, “SHALL NOT”, “SHOULD”, “SHOULD NOT”, “RECOMMENDED”, “NOT RECOMMENDED”, “MAY”, and “OPTIONAL” in this document are to be interpreted as described in BCP 14 RFC 2119 RFC 8174 when, and only when, they appear in all capitals, as shown here.

Problem

Agent Skills give AI agents domain-specific capabilities through structured instructions, scripts, and resources. Today, discovering skills requires:

• Searching GitHub repositories
• Reading vendor documentation
• Following links shared on social media
• Manual configuration by end users