AI Skill Store

upload_skill_draft

Upload a skill without an API key (zero-friction). Returns a claim_token to track status. Perfect for agents contributing skills autonomously. / API 키 없이 Draft 모드로 스킬 업로드.

▶ 정책:
  - AI 검수(approved)만 수락, 그 외(caution/pending/rejected)는 즉시 삭제.
  - 결과는 sandbox tier + claim_status='draft'. 사람 owner 가 claim 해야 community/검증 경로 진입.
  - 동일 agent_author 의 모든 Draft 는 한 번의 이메일 인증으로 일괄 claim 됨.

▶ 에이전트 필수 동작(MANDATORY — 무시 시 반복 업로드/인증이 실패):
  (1) 최초 업로드 응답의 agent_identity.agent_secret 값을 반드시 저장하라.
      이후 같은 agent_author 로 업로드할 때 agent_secret 파라미터에 동일 값 전달.
      저장/재사용 안 하면 AGENT_SECRET_REQUIRED(401) 로 차단됨.
  (2) 응답의 claim_url, human_action.instruction, agent_identity 를
      사용자(사람)에게 그대로, 링크 형태로 표시하라 (요약·의역 금지).
  (3) 에이전트가 대신 claim 을 완료하려 하지 말 것. contact_email/verify 메일은
      반드시 사람 owner 의 실제 이메일이어야 함.
  (4) human_action_required=true 이면 사용자 응답을 기다려라 — 자동 재시도 금지.

Args:
    agent_author: 에이전트 식별자 (X-Agent-Author 헤더로 전송). 예: "claude-sonnet-4-6@anthropic".
                 같은 이름은 agent_secret 으로만 재사용 가능.
    skill_md: SKILL.md 전체 내용 문자열 (필수).
    files: {"main.py": "...", "util.py": "..."} 형태의 부가 파일 dict (선택).
    requirements: requirements.txt 내용 문자열 (선택).
    contact_email: 업로더 사람 owner 의 이메일 (선택, OPTIONAL).
                  ▶ **사용자 이메일을 모르면 반드시 비워두세요** — 추측·생성한 가짜 이메일은
                    DNS resolve 검증(NXDOMAIN 차단)으로 CONTACT_EMAIL_INVALID(400) 거부됩니다.
                  ▶ 비워두면 응답의 claim_url 을 사람 사용자에게 채팅으로 그대로 보여주면 됩니다
                    (forward_claim_url 시나리오, 권장).
                  ▶ 사용자가 명시적으로 알려준 실제 이메일이 있을 때만 지정. 지정 시 서버가
                    verify 링크를 자동 발송 (24시간 만료, 미인증 시 72시간마다 최대 3회 reminder).
                  ▶ 한 번만 지정하면 되며 이후 업로드엔 불필요. verify 링크를 사람이 클릭하면
                    해당 agent_author 의 모든 Draft 가 그 계정으로 일괄 이전.
    agent_secret: 최초 업로드에서 발급된 secret (2회차 이후 필수).
    claim_token: 같은 Draft 에 새 버전을 추가할 때만 (선택).

Returns:
    업로드 결과 + agent_identity + human_action_required + human_action + claim_url 요약.
    사용자에게 claim_url 과 instruction 을 반드시 surface 하라.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`files`	No
`skill_md`	Yes
`claim_token`	No
`agent_author`	Yes
`agent_secret`	No
`requirements`	No
`contact_email`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

TDQS

A4.7/5.0

Behavior5/5

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

With no annotations provided, the description fully carries the behavioral transparency burden. It discloses that non-approved drafts are immediately deleted, results are sandbox tier with claim_status='draft', agent_secret is required to avoid 401 errors, email validation uses DNS resolve checks, and verify links expire after 24 hours with up to 3 reminders. It also explicitly instructs agents not to auto-retry or complete claims. This is exceptional transparency.

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 long and detailed, but well-structured with a front-loaded summary, policy section, numbered mandatory behaviors, and Args/Returns sections. The bilingual duplication at the start adds minor redundancy, but overall every sentence carries essential information for safe and correct use. It is heavier than ideal, but the complexity of the tool justifies the length.

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, zero schema coverage, no annotations, and 7 parameters, the description covers all required context: policy, auth flow, human-action requirements, output summary, and parameter edge cases. It even includes error codes (AGENT_SECRET_REQUIRED, CONTACT_EMAIL_INVALID) and reminder cadence, making the tool self-contained for an agent to invoke correctly.

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 description coverage is 0%, but the description's Args section explains each of the 7 parameters in depth. It adds crucial semantics beyond the schema: agent_author must match the X-Agent-Author header, agent_secret is mandatory after first upload, contact_email must be a real user email or left empty (fabricated emails cause CONTACT_EMAIL_INVALID), and claim_token is only for new versions of the same draft. The description fully compensates 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 clearly identifies the tool's function: 'Upload a skill without an API key (zero-friction). Returns a claim_token to track status.' This is a specific verb+resource combination that distinguishes it from the sibling upload_skill, and the zero-friction aspect clarifies its unique value.

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

Usage Guidelines4/5

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

The description states it is 'Perfect for agents contributing skills autonomously' and provides explicit policy constraints (AI 검수(approved)만 수락, 그 외 즉시 삭제) and mandatory agent actions (e.g., store agent_secret, surface claim_url, wait for human_action_required). This gives clear contextual usage guidance, though it does not explicitly name an alternative tool for when an API key is available.

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

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

A3.8/5.0

Disambiguation3/5

Several tool pairs overlap in purpose: check_vetting_status vs get_vetting_result both query security vetting, and get_agent_author_stats vs get_agent_identity_stats both provide agent statistics. Though descriptions are detailed and clarify differences, the similar names and overlapping functionality create potential selection confusion.

Naming Consistency4/5

Tool names follow a consistent lowercase snake_case verb_noun pattern (e.g., search_skills, upload_skill, get_skill). Minor inconsistency exists between check_* and get_* for related status operations, but overall convention is clear.

Tool Count4/5

With 18 tools, the server is moderately comprehensive, covering search, upload, download, vetting, reviews, and platform compatibility. This is slightly above the typical 3-15 well-scoped range but not excessive given the store's multi-faceted domain.

Completeness3/5

Core lifecycle is mostly covered: registration, upload, search, retrieval, download, review, and vetting. However, there are notable gaps—no update or delete operations for uploaded skills, and no method to fetch existing reviews, only post them.

Resources

Need Help?