motherduck-explore

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Explore MotherDuck Data

探索MotherDuck数据

Use this skill when you need to discover what databases, tables, and columns exist in a MotherDuck account; preview and sample data; understand schemas and data types; find shared databases; or search the data catalog.

当你需要了解MotherDuck账户中存在的数据库、表和列；预览并采样数据；理解模式和数据类型；查找共享数据库；或搜索数据目录时，使用此技能。

Prerequisites

前提条件

Establish a MotherDuck connection first via
```
motherduck-connect
```
.

首先通过
```
motherduck-connect
```
建立MotherDuck连接。

Default Posture

默认操作准则

Explore top-down: databases, then tables/views, then columns, then statistics, then sample rows.
Use fully qualified table names once more than one database is attached.
Check shared databases before concluding that data is unavailable.
Use MCP exploration tools when available because they return structured results faster than ad hoc SQL.
Return a concise schema map with table grain, join keys, date columns, and likely measures before moving into modeling or dashboard work.

自上而下探索：先数据库，再表/视图，接着列，然后统计信息，最后示例行。
当连接多个数据库时，使用完全限定的表名。
在判定数据不可用之前，先检查共享数据库。
若有可用的MCP探索工具，请使用它们，因为它们返回结构化结果的速度比临时SQL更快。
在进入建模或仪表板工作之前，返回包含表粒度、连接键、日期列和可能的度量指标的简明模式图。

Workflow

工作流程

List databases in scope.
List tables and views in the target database.
Inspect columns, types, nullability, and comments before writing queries.
Run
```
SUMMARIZE
```
on important tables to understand ranges, cardinality, and null rates.
Preview rows, capture grain and join assumptions, and only then move into analytical SQL or modeling work.

列出范围内的数据库。
列出目标数据库中的表和视图。
在编写查询之前，检查列、类型、可空性和注释。
对重要表运行
```
SUMMARIZE
```
以了解范围、基数和空值率。
预览行，记录粒度和连接假设，之后再进入分析型SQL或建模工作。

Open Next

后续参考

```
references/EXPLORATION_PLAYBOOK.md
```
for the full SQL workflow, share discovery patterns, MCP tool guidance, and common exploration mistakes

```
references/EXPLORATION_PLAYBOOK.md
```
包含完整的SQL工作流程、共享发现模式、MCP工具指南以及常见的探索错误