상태: 드래프트 버전: 0.2.0 게시일: 2026-01-17 업데이트 날짜: 2026-03-12

목차

1. 초록
2. 변경 기록
3. 용어
4. 문제
5. 해법
6. URI 구조
7. 스킬 디렉토리 내용
8. 점진적 공개
9. 발견 지수
10. 무결성 및 검증
11. 아카이브 배포
12. 예시
13. HTTP 고려사항
14. 클라이언트 구현
15. 보안 고려사항
16. 기존 명세와의 관계
17. 참고문헌

초록

이 문서는 RFC 8615에 명시된 .well-known URI 경로 접두사를 사용하여 에이전트 스킬을 발견하는 메커니즘을 정의합니다. 스킬은 현재 GitHub 저장소, 문서 사이트 및 기타 출처에 흩어져 있습니다. 잘 알려진 URI는 에이전트와 도구가 조직이나 프로젝트에서 공개한 스킬을 발견할 수 있는 예측 가능한 위치를 제공합니다.

변경 기록

v0.2.0

• 잘 알려진 URI의 이름을 /.well-known/skills/에서 [[T2]로 변경]
• version 필드를 $schema URI (https://schemas.agentskills.io/discovery/0.2.0/schema.json]로 대체)

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