googlebigquery-automation
Automate Google BigQuery tasks via Rube MCP (Composio): run SQL queries, explore datasets and metadata, execute MBQL queries via Metabase integration. Always search tools first for current schemas.
Best use case
googlebigquery-automation is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Automate Google BigQuery tasks via Rube MCP (Composio): run SQL queries, explore datasets and metadata, execute MBQL queries via Metabase integration. Always search tools first for current schemas.
Teams using googlebigquery-automation should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/googlebigquery-automation/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How googlebigquery-automation Compares
| Feature / Agent | googlebigquery-automation | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Automate Google BigQuery tasks via Rube MCP (Composio): run SQL queries, explore datasets and metadata, execute MBQL queries via Metabase integration. Always search tools first for current schemas.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Google BigQuery Automation via Rube MCP
Run SQL queries, explore database schemas, and analyze datasets through the Metabase integration using Rube MCP (Composio).
**Toolkit docs**: [composio.dev/toolkits/googlebigquery](https://composio.dev/toolkits/googlebigquery)
## Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `metabase`
- A Metabase instance connected to your BigQuery data source
- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas
## Setup
**Get 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.
1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `metabase`
3. If connection is not ACTIVE, follow the returned auth link to complete setup
4. Confirm connection status shows ACTIVE before running any workflows
> **Note**: 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.
## Core Workflows
### 1. Run a Native SQL Query
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)
```
### 2. Run a Structured MBQL Query
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
```
### 3. Get Query Metadata
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})
```
### 4. Convert Query to Native SQL
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)
```
### 5. List Available Databases
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.
```
### 6. Get Database Schema Metadata
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.
```
## Common Patterns
- **Discover then query**: Use `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.
- **SQL-first approach**: Use `METABASE_POST_API_DATASET` with `type: "native"` and write standard SQL queries for maximum flexibility.
- **Parameterized queries**: Use `template_tags` in native queries for safe parameterization (e.g., `SELECT * FROM users WHERE id = {{user_id}}`).
- **Schema exploration**: Use `METABASE_POST_API_DATASET_QUERY_METADATA` to understand table structures before building complex queries.
- **Get parameter values**: Use `METABASE_POST_API_DATASET_PARAMETER_VALUES` to retrieve possible values for filter dropdowns.
## Known Pitfalls
- The `database` parameter is a Metabase-internal **integer ID**, not the BigQuery project or dataset name. Use `METABASE_GET_API_DATABASE` to find valid database IDs first.
- `source-table` in MBQL queries is also a Metabase-internal integer, not the BigQuery table name. Discover table IDs via metadata tools.
- Native SQL queries use BigQuery SQL dialect (Standard SQL). Ensure your syntax is BigQuery-compatible.
- `max-results` in constraints defaults can limit returned rows. Set explicitly for large result sets.
- Responses from `METABASE_POST_API_DATASET` contain results nested under `data` -- parse carefully as the structure may be deeply nested.
- Metabase field IDs used in MBQL `aggregation`, `breakout`, and `filter` arrays must be integers obtained from metadata responses.
## Quick Reference
| Action | Tool | Key Parameters |
|--------|------|----------------|
| Run SQL query | `METABASE_POST_API_DATASET` | `database`, `type: "native"`, `native.query` |
| Run MBQL query | `METABASE_POST_API_DATASET` | `database`, `type: "query"`, `query` |
| Get query metadata | `METABASE_POST_API_DATASET_QUERY_METADATA` | `database`, `type`, `query` |
| Convert to SQL | `METABASE_POST_API_DATASET_NATIVE` | `database`, `type`, `native` |
| Get parameter values | `METABASE_POST_API_DATASET_PARAMETER_VALUES` | `parameter`, `field_ids` |
| List databases | `METABASE_GET_API_DATABASE` | (see full schema via RUBE_SEARCH_TOOLS) |
| Get database metadata | `METABASE_GET_API_DATABASE_ID_METADATA` | (see full schema via RUBE_SEARCH_TOOLS) |
---
*Powered by [Composio](https://composio.dev)*Related Skills
google-sheets-automation
Google Sheets Automation - Auto-activating skill for Business Automation. Triggers on: google sheets automation, google sheets automation Part of the Business Automation skill category.
playwright-automation-fill-in-form
Automate filling in a form using Playwright MCP
deployment-automation
Automate application deployment to cloud platforms and servers. Use when setting up CI/CD pipelines, deploying to Docker/Kubernetes, or configuring cloud infrastructure. Handles GitHub Actions, Docker, Kubernetes, AWS, Vercel, and deployment best practices.
zoom-automation
Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.
zoho-crm-automation
Automate Zoho CRM tasks via Rube MCP (Composio): create/update records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.
zendesk-automation
Automate Zendesk tasks via Rube MCP (Composio): tickets, users, organizations, replies. Always search tools first for current schemas.
youtube-automation
Automate YouTube tasks via Rube MCP (Composio): upload videos, manage playlists, search content, get analytics, and handle comments. Always search tools first for current schemas.
wrike-automation
Automate Wrike project management via Rube MCP (Composio): create tasks/folders, manage projects, assign work, and track progress. Always search tools first for current schemas.
workflow-automation
Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off. This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation. Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility
whatsapp-automation
Automate WhatsApp Business tasks via Rube MCP (Composio): send messages, manage templates, upload media, and handle contacts. Always search tools first for current schemas.
webflow-automation
Automate Webflow CMS collections, site publishing, page management, asset uploads, and ecommerce orders via Rube MCP (Composio). Always search tools first for current schemas.
vercel-automation
Automate Vercel tasks via Rube MCP (Composio): manage deployments, domains, DNS, env vars, projects, and teams. Always search tools first for current schemas.