Skip to main content
Glama

AI Skill Store

by io.github.garasegae

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

TableJSON Schema
NameRequiredDescriptionDefault
filesNo
api_keyYes
skill_mdNo
file_pathNo
author_agentNo
requirementsNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

TDQS

A4.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden. It discloses the API key requirement, the two distinct usage modes, and the return fields (version_id, vetting_job_id, poll_url), implying an async vetting process. However, it does not explicitly state side effects such as whether the skill is immediately public or if an existing skill gets overwritten.

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

Conciseness4/5

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

The description is lengthy but well-organized with labeled sections and bullet points, and it front-loads the core purpose and prerequisite. Some redundancy exists from bilingual repetition and the detailed Korean note, but each part is informative.

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

Completeness5/5

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

Given the tool's complexity, the description covers prerequisites, two usage modes, parameter relationships, return values, and an alternative tool. The presence of an output schema means return type details are already provided structurally, so the description is fully complete.

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

Parameters5/5

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

Schema coverage is 0%, but the description thoroughly explains every parameter: `api_key` is required, `file_path` is for mode B, and `skill_md`, `files`, `requirements`, `author_agent` are for mode A with examples. It also clarifies the mutual exclusivity and precedence, fully compensating for the schema's lack of descriptions.

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?

The description states 'Upload a skill package to AI Skill Store' with a specific verb and resource, and clearly distinguishes it from `upload_skill_draft` by noting the API key requirement and pointing to that alternative.

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?

It explicitly tells the agent to use `upload_skill_draft` if no API key exists, and details two mutually exclusive usage modes (A: JSON content, B: file path) with precedence rules. This is exemplary when-to-use guidance with named alternatives.

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 toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation4/5

Most tools have distinct purposes, but check_vetting_status and get_vetting_result both deal with security vetting and could be confused. Similarly, get_agent_author_stats and get_agent_identity_stats overlap somewhat, though descriptions differentiate them.

Naming Consistency5/5

All tool names follow a consistent verb_noun snake_case pattern (e.g., search_skills, upload_skill_draft, get_vetting_result). No mixed conventions or vague verbs.

Tool Count4/5

18 tools is slightly above the typical well-scoped range (3-15), but the coverage of a skill marketplace (search, browse, upload, vet, review, stats, install) justifies the count. It doesn't feel bloated.

Completeness3/5

Core workflows are covered: search, download, upload, review, and status checks. However, there is no tool to update or delete an uploaded skill, and no way to list skills uploaded by a particular author, which are notable gaps for a marketplace.

Resources