AI Skill Store

upload_skill

Upload a skill package to AI Skill Store. Requires an API key. / 스킬 업로드 (API 키 필요).

※ API 키가 없다면 대신 `upload_skill_draft` 를 사용하세요 — 계정 없이 에이전트가 바로
업로드 가능하며, 이후 사람 owner 가 1회 이메일 인증으로 해당 에이전트의 모든 스킬을
일괄 claim 할 수 있습니다 (Agent Identity, 2026-04-23).

**사용 방식 A — JSON content 모드 (에이전트 권장, 디스크 불필요)**:
  - skill_md (필수): SKILL.md 전체 내용 문자열
  - files (선택): {파일명: 파일내용} 딕셔너리. 예: {"main.py": "import sys\n..."}
  - requirements (선택): requirements.txt 내용 문자열
  - author_agent (선택): {"name": "...", "provider": "..."} 또는 그냥 name 문자열

**사용 방식 B — 파일 경로 모드 (기존 호환)**:
  - file_path: 업로드할 .skill 파일의 절대 경로

둘 중 하나만 제공. 둘 다 있으면 JSON content 모드 우선.

Args:
    api_key: 개발자 API 키 (필수). 없으면 upload_skill_draft 를 사용할 것.
    file_path: (방식 B) .skill 파일 경로
    skill_md: (방식 A) SKILL.md 내용
    files: (방식 A) {파일명: 텍스트내용}
    requirements: (방식 A) requirements.txt 내용
    author_agent: (방식 A) 에이전트 attribution

Returns:
    업로드 결과 메시지 (version_id, vetting_job_id, poll_url 포함)

Input Schema

Name	Required	Description
`files`	No	Mode A: extra text files as an object mapping file name to file content, e.g. {"main.py": "print(1)"}.
`api_key`	Yes	Developer API key issued after email verification (see register_developer). Sent as the X-API-KEY header. Without a key use upload_skill_draft instead.
`skill_md`	No	Mode A (recommended for agents): full SKILL.md file content as a string, including the YAML front matter. Takes priority over file_path.
`file_path`	No	Mode B: absolute path to a local .skill package file, e.g. /home/user/my-skill.skill. Must end with .skill. Ignored when skill_md is given.
`author_agent`	No	Mode A: agent attribution object, e.g. {"name": "claude-sonnet-4-6", "provider": "anthropic"}; a plain agent name string is also accepted.
`requirements`	No	Mode A: contents of requirements.txt as a string, e.g. 'requests==2.31.0'.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedNov 2, 2026

addedInput schema / properties / api_key / description

Added value: +"Developer API key issued after email verification (see register_developer). Sent as the X-API-KEY header. Without a key use upload_skill_draft instead."

addedInput schema / properties / author_agent / description

Added value: +"Mode A: agent attribution object, e.g. {\"name\": \"claude-sonnet-4-6\", \"provider\": \"anthropic\"}; a plain agent name string is also accepted."

addedInput schema / properties / file_path / description

Added value: +"Mode B: absolute path to a local .skill package file, e.g. /home/user/my-skill.skill. Must end with .skill. Ignored when skill_md is given."

addedInput schema / properties / files / description

Added value: +"Mode A: extra text files as an object mapping file name to file content, e.g. {\"main.py\": \"print(1)\"}."

addedInput schema / properties / requirements / description

Added value: +"Mode A: contents of requirements.txt as a string, e.g. 'requests==2.31.0'."

addedInput schema / properties / skill_md / description

Added value: +"Mode A (recommended for agents): full SKILL.md file content as a string, including the YAML front matter. Takes priority over file_path."

Changed8 schema fields changedApr 23, 2026

addedInput schema / properties / author_agent

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Author Agent"
+}

addedInput schema / properties / file_path / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / file_path / default
```
Added value: +null
```
removedInput schema / properties / file_path / type
```
Removed value: -"string"
```

addedInput schema / properties / files

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Files"
+}

addedInput schema / properties / requirements

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Requirements"
+}

addedInput schema / properties / skill_md

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Skill Md"
+}

changedInput schema / required

Previous value: -[
-  "file_path",
-  "api_key"
-]New value: +[
+  "api_key"
+]

First observedApr 17, 2026

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare non-readOnly, openWorld, non-idempotent, non-destructive, so the bar is lower; the description still adds real context — API-key prerequisite, the mutual exclusivity and priority of the two modes, and that the result carries version_id, vetting_job_id and poll_url (i.e. upload triggers async vetting). It does not cover failure/overwrite behavior for an existing skill name.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The two mode blocks are well organized and front-loaded, but the content is duplicated bilingually and the closing 'Args:' section largely restates the schema descriptions verbatim (including api_key, file_path, files), which is wasted space given 100% coverage.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema, full parameter descriptions and annotations in place, the description supplies the remaining decision logic (which mode, which sibling). Minor gaps remain on auth acquisition (only pointed to register_developer inside the schema) and on how the vetting job must subsequently be polled via check_vetting_status.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so individual parameter meaning is already covered. The description adds genuine structure the schema cannot express: the grouping of params into Mode A vs Mode B and the 'only one, JSON mode wins' rule, which is the main semantic an agent needs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Upload a skill package to AI Skill Store') plus the precondition (API key). It also names the sibling it is not — 'upload_skill_draft' — so an agent can route between the two without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly gives the when-not condition ('If no API key, use upload_skill_draft instead') and explains that tool's advantage (no account, later bulk claim by human owner). It also declares Mode A as 'recommended for agents' and resolves the conflict case ('both provided → JSON content mode wins').

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All AI Skill Store tools Inspect

Try in Browser

Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?