How do I install the Database Bigquery skill?

Run npx skillmds@latest add incidentfox/database-bigquery in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Database Bigquery safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Database Bigquery?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Database Bigquery free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Database Bigquery?

incidentfox (@incidentfox) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Database Bigquery by incidentfox — Agent Skill

Name: Database Bigquery
Author: incidentfox

File contents

BigQuery Data Warehouse

Authentication

IMPORTANT: Credentials are injected automatically by a proxy layer. Do NOT check for BIGQUERY_SERVICE_ACCOUNT_KEY in environment variables - it won't be visible to you. Just run the scripts directly; authentication is handled transparently.

Configuration environment variables you CAN check (non-secret):

BIGQUERY_PROJECT_ID - GCP project ID
BIGQUERY_DATASET - Default dataset

MANDATORY: Schema-First Investigation

List datasets and tables before writing queries.

LIST DATASETS → LIST TABLES → GET TABLE SCHEMA → QUERY

Available Scripts

All scripts are in .claude/skills/database-bigquery/scripts/

list_datasets.py - List Datasets (START HERE)

python .claude/skills/database-bigquery/scripts/list_datasets.py

list_tables.py - List Tables in Dataset

python .claude/skills/database-bigquery/scripts/list_tables.py --dataset DATASET_ID

get_table_schema.py - Table Schema Details

python .claude/skills/database-bigquery/scripts/get_table_schema.py --dataset DATASET_ID --table TABLE_ID

query.py - Run SQL Queries

python .claude/skills/database-bigquery/scripts/query.py --query "SELECT * FROM dataset.table LIMIT 10" [--dataset DEFAULT_DATASET] [--max-results 1000]

BigQuery SQL Reference

-- Standard SQL (default)
SELECT * FROM `project.dataset.table` LIMIT 10

-- Aggregate with time
SELECT DATE(timestamp), COUNT(*) as events
FROM `dataset.events`
WHERE timestamp > TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 24 HOUR)
GROUP BY 1 ORDER BY 1 DESC

-- Partitioned table query (cost-efficient)
SELECT * FROM `dataset.events`
WHERE _PARTITIONTIME >= TIMESTAMP('2026-01-01')

Investigation Workflow

Data Analysis

1. list_datasets.py (find available datasets)
2. list_tables.py --dataset <dataset> (find tables)
3. get_table_schema.py --dataset <dataset> --table <table>
4. query.py --query "SELECT ..."

---name: database-bigquerydescription: Google BigQuery data warehouse queries and schema inspection. Use when running SQL queries, listing datasets/tables, or inspecting table schemas in BigQuery.---# BigQuery Data Warehouse## Authentication**IMPORTANT**: Credentials are injected automatically by a proxy layer. Do NOT check for `BIGQUERY_SERVICE_ACCOUNT_KEY` in environment variables - it won't be visible to you. Just run the scripts directly; authentication is handled transparently.Configuration environment variables you CAN check (non-secret):- `BIGQUERY_PROJECT_ID` - GCP project ID- `BIGQUERY_DATASET` - Default dataset---## MANDATORY: Schema-First Investigation**List datasets and tables before writing queries.**```LIST DATASETS → LIST TABLES → GET TABLE SCHEMA → QUERY```## Available ScriptsAll scripts are in `.claude/skills/database-bigquery/scripts/`### list_datasets.py - List Datasets (START HERE)```bashpython .claude/skills/database-bigquery/scripts/list_datasets.py```### list_tables.py - List Tables in Dataset```bashpython .claude/skills/database-bigquery/scripts/list_tables.py --dataset DATASET_ID```### get_table_schema.py - Table Schema Details```bashpython .claude/skills/database-bigquery/scripts/get_table_schema.py --dataset DATASET_ID --table TABLE_ID```### query.py - Run SQL Queries```bashpython .claude/skills/database-bigquery/scripts/query.py --query "SELECT * FROM dataset.table LIMIT 10" [--dataset DEFAULT_DATASET] [--max-results 1000]```---## BigQuery SQL Reference```sql-- Standard SQL (default)SELECT * FROM `project.dataset.table` LIMIT 10-- Aggregate with timeSELECT DATE(timestamp), COUNT(*) as eventsFROM `dataset.events`WHERE timestamp > TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 24 HOUR)GROUP BY 1 ORDER BY 1 DESC-- Partitioned table query (cost-efficient)SELECT * FROM `dataset.events`WHERE _PARTITIONTIME >= TIMESTAMP('2026-01-01')```---## Investigation Workflow### Data Analysis```1. list_datasets.py (find available datasets)2. list_tables.py --dataset <dataset> (find tables)3. get_table_schema.py --dataset <dataset> --table <table>4. query.py --query "SELECT ..."```

Frequently asked questions

Database Bigquery