From yuque-group
Searches group Yuque knowledge bases using natural language queries, extracts keywords, retrieves relevant docs via yuque-mcp tools, and summarizes answers with key points and source links. For team repository Q&A.
npx claudepluginhub yuque/yuque-pluginThis skill uses the workspace's default tool permissions.
Search across group Yuque knowledge bases using natural language, read relevant documents, and synthesize a clear answer with references. Scoped to team/group repositories.
Searches group Yuque knowledge bases with natural language queries, retrieves relevant docs via yuque-mcp tools, and summarizes answers with key points and source links. For team repository queries.
Searches personal Yuque knowledge bases with natural language queries, retrieves relevant documents via yuque-mcp tools, and synthesizes summarized answers with key points and source links. Useful for querying user's own docs.
Searches Confluence, Jira, and internal docs for company systems, terminology, processes, deployment, authentication, infrastructure, and technical concepts with parallel cited results.
Share bugs, ideas, or general feedback.
Search across group Yuque knowledge bases using natural language, read relevant documents, and synthesize a clear answer with references. Scoped to team/group repositories.
All tools are from the yuque-mcp server:
yuque_list_repos — List group knowledge bases to determine search scopeyuque_search — Search documents by keywordyuque_get_doc — Read full document content by slug/idFirst, get the list of group knowledge bases to understand the search scope:
Tool: yuque_list_repos
Parameters:
login: "<group_login>"
type: "group"
If the user hasn't specified a group login, ask: "请告诉我团队的语雀团队标识(group login),我来搜索团队知识库。"
From the user's natural language query, extract 1-3 concise Chinese keywords. Yuque search works best with short, specific terms.
Examples:
部署流程API 规范技术评审Call yuque_search with the extracted keywords:
Tool: yuque_search
Parameters:
query: "<keywords>"
type: "doc"
If the search returns no results:
From the search results, select the top 3-5 most relevant documents based on:
Filter out results that don't belong to the team's knowledge bases.
For each selected document, fetch the full content:
Tool: yuque_get_doc
Parameters:
repo_id: "<namespace>" # e.g., "my-team/tech-docs" (from search result's book.namespace)
doc_id: "<slug>" # e.g., "api-spec" (from search result's target.slug)
Note: The search result contains nested data. Extract these key fields:
target.slug → use as doc_idtarget.book.namespace → use as repo_idtarget.title → document titletarget.updated_at → last update timeRead up to 3 documents. If the first document fully answers the question, you may skip the rest.
Compose the answer in the following format:
## 回答
[直接回答用户的问题,2-4 句话,简洁明了]
## 关键要点
- **要点 1**:[从文档中提取的关键信息]
- **要点 2**:[从文档中提取的关键信息]
- **要点 3**:[从文档中提取的关键信息]
## 参考文档
1. [文档标题](文档链接) — 来自「知识库名称」,更新于 YYYY-MM-DD
2. [文档标题](文档链接) — 来自「知识库名称」,更新于 YYYY-MM-DD
> blockquotessmart-search skill in the yuque-personal plugin| Situation | Action |
|---|---|
yuque_list_repos fails | Check if group login is correct and group Token is configured |
yuque_search returns empty | Try alternative keywords, then inform user |
yuque_get_doc fails (404) | Skip this doc, note it may have been deleted |
yuque_get_doc fails (403) | Tell user they may lack permission; check group Token scope |
| API timeout | Retry once, then inform user of connectivity issue |
| Too many results | Focus on top 3 by relevance, mention there are more results available |
| Team Token not configured | Inform user that group search requires a team-level Token |