自动化执行 Google BigQuery 查询、数据集探索与元数据检索分析
复制安装指令,让 AI 自动完成配置 · 推荐新手
请帮我安装 askskill 上的 "googlebigquery-automation" 技能: 1. 下载 https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/googlebigquery-automation/SKILL.md 2. 保存为 ~/.claude/skills/googlebigquery-automation/SKILL.md 3. 装好后重载技能,告诉我可以用了
Run SQL queries, explore database schemas, and analyze datasets through the Metabase integration using Rube MCP (Composio).
Toolkit docs: composio.dev/toolkits/googlebigquery
RUBE_MANAGE_CONNECTIONS with toolkit metabaseRUBE_SEARCH_TOOLS first to get current tool schemasGet Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
RUBE_SEARCH_TOOLS respondsRUBE_MANAGE_CONNECTIONS with toolkit metabaseNote: BigQuery data is accessed through Metabase, a business intelligence tool that connects to BigQuery as a data source. The tools below execute queries and retrieve metadata through Metabase's API.
Use METABASE_POST_API_DATASET with type native to execute raw SQL queries against your BigQuery database.
Tool: METABASE_POST_API_DATASET
Parameters:
- database (required): Metabase database ID (integer)
- type (required): "native" for SQL queries
- native (required): Object with "query" string
- query: Raw SQL string (e.g., "SELECT * FROM users LIMIT 10")
- template_tags: Parameterized query variables (optional)
- constraints: { "max-results": 1000 } (optional)
Use METABASE_POST_API_DATASET with type query for Metabase Query Language queries with built-in aggregation and filtering.
Tool: METABASE_POST_API_DATASET
Parameters:
- database (required): Metabase database ID
- type (required): "query" for MBQL
- query (required): Object with:
- source-table: Table ID (integer)
- aggregation: e.g., [["count"]] or [["sum", ["field", 5, null]]]
- breakout: Group-by fields
- filter: Filter conditions
- limit: Max rows
- order-by: Sort fields
Use METABASE_POST_API_DATASET_QUERY_METADATA to retrieve metadata about databases, tables, and fields available for querying.
Tool: METABASE_POST_API_DATASET_QUERY_METADATA
Parameters:
- database (required): Metabase database ID
- type (required): "query" or "native"
- query (required): Query object (e.g., {"source-table": 1})
Use METABASE_POST_API_DATASET_NATIVE to convert an MBQL query into its native SQL representation.
Tool: METABASE_POST_API_DATASET_NATIVE
Parameters:
- database (required): Metabase database ID
- type (required): "native"
- native (required): Object with "query" and optional "template_tags"
- parameters: Query parameter values (optional)
Use METABASE_GET_API_DATABASE to discover all database connections configured in Metabase.
Tool: METABASE_GET_API_DATABASE
Description: Retrieves a list of all Database instances configured in Metabase.
Note: Call RUBE_SEARCH_TOOLS to get the full schema for this tool.
Use METABASE_GET_API_DATABASE_ID_METADATA to retrieve complete table and field information for a specific database.
Tool: METABASE_GET_API_DATABASE_ID_METADATA
Description: Retrieves complete metadata for a specific database including
all tables and fields.
Note: Call RUBE_SEARCH_TOOLS to get the full schema for this tool.
METABASE_GET_API_DATABASE to find database IDs, then METABASE_GET_API_DATABASE_ID_METADATA to explore tables and fields, then METABASE_POST_API_DATASET to run queries.…
通过 Rube MCP 自动执行 Jobnimbus 任务与流程操作,提升业务处理效率。
通过 Rube MCP 自动执行 BigML 相关任务与机器学习工作流。