AI Skill Store

search_skills

Read-onlyIdempotent

Search skills on AI Skill Store. Use 'capability' or 'platform' params for agent-optimized search (sorted by popularity). Returns skill name, description, downloads, rating, and trust level. / AI Skill Store에서 스킬 검색.
capability나 platform을 지정하면 에이전트 최적화 검색(인기순 정렬)을 사용합니다.

Args:
    query: 검색 키워드 (스킬 이름 또는 설명). 비워두면 전체 목록.
    capability: 능력 태그로 검색 (예: web_search, text_summarization, code_generation)
    platform: 특정 플랫폼 호환 스킬만 (OpenClaw, ClaudeCode, ClaudeCodeAgentSkill, Cursor, GeminiCLI, CodexCLI)
    min_trust: 최소 신뢰 등급 (verified > community > sandbox)
    category: 카테고리 필터 (에이전트 검색 미사용 시에만 적용)
    sort: 정렬 기준 (에이전트 검색 미사용 시에만: newest | downloads | rating)
    limit: 결과 수 (기본 20, 최대 50)

Returns:
    스킬 목록 문자열

Input Schema

Name	Required	Description	Default
`sort`	No	Sort order, one of: newest \| downloads \| rating. Applied only when capability/platform/min_trust are NOT used.	newest
`limit`	No	Maximum number of results, 1-50 (agent search caps at 50). Default 20.
`query`	No	Free-text keyword matched against skill name and description, e.g. 'pdf summarizer'. Empty string lists all skills.
`category`	No	Category filter, e.g. 'Development' or 'Data Processing' (see list_categories). Applied only when capability/platform/min_trust are NOT used.
`platform`	No	Only return skills compatible with this platform. One of: OpenClaw \| ClaudeCode \| ClaudeCodeAgentSkill \| CodexCLI \| Cursor \| GeminiCLI \| CustomAgent.
`min_trust`	No	Minimum trust level, one of: verified \| community \| sandbox (verified is the highest). Empty means no filter.
`capability`	No	Capability tag for agent-optimized search (sorted by popularity), e.g. web_search, text_summarization, code_generation.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedNov 2, 2026

addedInput schema / properties / capability / description

Added value: +"Capability tag for agent-optimized search (sorted by popularity), e.g. web_search, text_summarization, code_generation."

addedInput schema / properties / category / description

Added value: +"Category filter, e.g. 'Development' or 'Data Processing' (see list_categories). Applied only when capability/platform/min_trust are NOT used."

addedInput schema / properties / limit / description

Added value: +"Maximum number of results, 1-50 (agent search caps at 50). Default 20."

addedInput schema / properties / min_trust / description

Added value: +"Minimum trust level, one of: verified | community | sandbox (verified is the highest). Empty means no filter."

addedInput schema / properties / platform / description

Added value: +"Only return skills compatible with this platform. One of: OpenClaw | ClaudeCode | ClaudeCodeAgentSkill | CodexCLI | Cursor | GeminiCLI | CustomAgent."

addedInput schema / properties / query / description

Added value: +"Free-text keyword matched against skill name and description, e.g. 'pdf summarizer'. Empty string lists all skills."

addedInput schema / properties / sort / description

Added value: +"Sort order, one of: newest | downloads | rating. Applied only when capability/platform/min_trust are NOT used."

First observedApr 17, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnlyHint/idempotentHint/openWorldHint, so the safety bar is covered. The description adds behavior beyond that: agent-mode results are sorted by popularity, and the sort/category filters are silently ignored in that mode — a non-obvious trait worth knowing. It does not cover pagination or empty-result behavior.

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 English/Korean bilingual duplication roughly doubles the length without adding information, and the Args block repeats the input schema almost verbatim. The core mode-selection rule is front-loaded, which saves it from a lower score, but there is clear redundancy.

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?

For a 7-parameter, all-optional search tool with a full output schema and read-only annotations, the description covers modes, filtering precedence, and trust ordering adequately. Nothing critical for correct invocation is missing, though the unused-parameter behavior could be stated more bluntly.

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

Parameters3/5

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

Schema coverage is 100%, so every parameter is already documented with examples and defaults in the schema. The description's Args block largely restates that content, adding only the trust ordering hint (verified > community > sandbox). Baseline 3 is appropriate when the schema does the heavy lifting.

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

Purpose4/5

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

States a specific verb+resource ("Search skills on AI Skill Store") and explains the two search modes and their ordering semantics. It doesn't explicitly contrast with siblings like get_skill (single-skill fetch) or list_categories, so the differentiation is implicit rather than stated.

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?

Gives real routing guidance: use 'capability' or 'platform' for agent-optimized popularity-sorted search, and notes that category/sort apply only when capability/platform/min_trust are NOT used — a genuine mutual-exclusion rule. It stops short of naming sibling tools or when to prefer get_skill over a search.

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?