search by anthropics/knowledge-work-plugins
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill search如果你看到不熟悉的占位符或需要检查连接了哪些工具,请参阅 CONNECTORS.md。
通过单一查询在所有已连接的 MCP 源中进行搜索。分解用户的问题,并行执行搜索,并综合结果。
在搜索之前,确定哪些 MCP 源可用。尝试从可用工具列表中识别已连接的工具。常见源包括:
如果没有连接任何 MCP 源:
要跨工具搜索,您需要至少连接一个源。
请检查您的 MCP 设置以添加 ~~chat、~~email、~~cloud storage 或其他工具。
支持的源:~~chat、~~email、~~cloud storage、~~project tracker、~~CRM、~~knowledge base,
以及任何其他 MCP 连接的服务。
分析搜索查询以理解:
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
from: — 按发件人/作者筛选in: — 按频道、文件夹或位置筛选after: — 仅在此日期之后的结果before: — 仅在此日期之前的结果type: — 按内容类型筛选(消息、电子邮件、文档、线程、文件)针对每个可用源,使用该源的原生搜索语法创建有针对性的子查询:
~~chat:
from: 映射到发件人,in: 映射到频道/房间,日期映射到时间范围过滤器~~email:
from: 映射到发件人,日期映射到时间范围过滤器type: 映射到附件过滤器或主题行搜索(视情况而定)~~cloud storage:
~~project tracker:
~~CRM:
~~knowledge base:
在所有可用源上同时运行所有子查询。不要等待一个源完成再搜索另一个。
对于每个源:
去重:
排序因素:
将响应格式化为综合答案,而不是原始结果列表:
对于事实/决策查询:
[对问题的直接回答]
来源:
- [来源 1:简要描述] (~~chat, #频道, 日期)
- [来源 2:简要描述] (~~email, 来自 某人, 日期)
- [来源 3:简要描述] (~~cloud storage, 文档名称, 最后修改时间)
对于探索性查询("关于 X 我们知道什么"):
[综合所有来源信息的摘要]
在以下位置找到:
- ~~chat:Y 个频道中的 X 条相关消息
- ~~email:X 个相关线程
- ~~cloud storage:X 个相关文档
- [其他适用来源]
关键来源:
- [最重要的来源,附带链接/引用]
- [第二重要的来源]
对于"查找"查询(寻找特定事物):
[他们正在寻找的事物,附带直接引用]
还找到:
- [来自其他来源的相关项目]
模糊查询: 如果查询可能有多重含义,在搜索前提出一个澄清问题:
"API 重新设计"可能指几件事。您是在寻找:
1. REST API v2 重新设计(Project Aurora)
2. 内部 SDK API 变更
3. 其他内容?
无结果:
我在[已搜索的源列表]中找不到任何匹配"[查询]"的内容。
请尝试:
- 更宽泛的术语(例如,"数据库" 而不是 "PostgreSQL 迁移")
- 不同的时间范围(当前搜索[时间范围])
- 检查相关源是否已连接(当前搜索:[源列表])
部分结果(某些源失败):
[来自成功源的结果]
注意:在此次搜索中我无法访问[失败的源]。
以上结果仅来自[成功的源]。
每周安装次数
191
代码仓库
GitHub 星标数
10.3K
首次出现
11 天前
安全审计
安装于
gemini-cli182
opencode182
codex181
cursor181
amp180
cline180
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Search across all connected MCP sources in a single query. Decompose the user's question, run parallel searches, and synthesize results.
Before searching, determine which MCP sources are available. Attempt to identify connected tools from the available tool list. Common sources:
If no MCP sources are connected:
To search across your tools, you'll need to connect at least one source.
Check your MCP settings to add ~~chat, ~~email, ~~cloud storage, or other tools.
Supported sources: ~~chat, ~~email, ~~cloud storage, ~~project tracker, ~~CRM, ~~knowledge base,
and any other MCP-connected service.
Analyze the search query to understand:
from: — Filter by sender/authorin: — Filter by channel, folder, or locationafter: — Only results after this datebefore: — Only results before this datetype: — Filter by content type (message, email, doc, thread, file)For each available source, create a targeted sub-query using that source's native search syntax:
~~chat:
from: maps to sender, in: maps to channel/room, dates map to time range filters~~email:
from: maps to sender, dates map to time range filterstype: to attachment filters or subject-line searches as appropriate~~cloud storage:
~~project tracker:
~~CRM:
~~knowledge base:
Run all sub-queries simultaneously across available sources. Do not wait for one source before searching another.
For each source:
Deduplication:
Ranking factors:
Format the response as a synthesized answer, not a raw list of results:
For factual/decision queries:
[Direct answer to the question]
Sources:
- [Source 1: brief description] (~~chat, #channel, date)
- [Source 2: brief description] (~~email, from person, date)
- [Source 3: brief description] (~~cloud storage, doc name, last modified)
For exploratory queries ("what do we know about X"):
[Synthesized summary combining information from all sources]
Found across:
- ~~chat: X relevant messages in Y channels
- ~~email: X relevant threads
- ~~cloud storage: X related documents
- [Other sources as applicable]
Key sources:
- [Most important source with link/reference]
- [Second most important source]
For "find" queries (looking for a specific thing):
[The thing they're looking for, with direct reference]
Also found:
- [Related items from other sources]
Ambiguous queries: If the query could mean multiple things, ask one clarifying question before searching:
"API redesign" could refer to a few things. Are you looking for:
1. The REST API v2 redesign (Project Aurora)
2. The internal SDK API changes
3. Something else?
No results:
I couldn't find anything matching "[query]" across [list of sources searched].
Try:
- Broader terms (e.g., "database" instead of "PostgreSQL migration")
- Different time range (currently searching [time range])
- Checking if the relevant source is connected (currently searching: [sources])
Partial results (some sources failed):
[Results from successful sources]
Note: I couldn't reach [failed source(s)] during this search.
Results above are from [successful sources] only.
Weekly Installs
191
Repository
GitHub Stars
10.3K
First Seen
11 days ago
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
gemini-cli182
opencode182
codex181
cursor181
amp180
cline180
通过 LiteLLM 代理让 Claude Code 对接 GitHub Copilot 运行 | 高级变通方案指南
31,600 周安装