What problem does it solve? Investigating data in Google BigQuery normally requires switching to the console or writing ad-hoc client code. This Skill lets an AI agent list datasets, enumerate tables, inspect schemas, and execute SQL queries directly through ready-made Python scripts, with credentials injected transparently by a proxy layer. ## Core Features & Use Cases - Schema-First Discovery: Enforces a list datasets → list tables → get schema → query workflow so queries are written against verified structures. - SQL Query Execution: Runs Standard SQL queries with optional default dataset and configurable max result limits, returning JSON-formatted rows and schema metadata. - Table Metadata Inspection: Reports row counts, byte sizes, column types, modes, and descriptions for any table. - Use Case: During an incident investigation, ask the agent to find which tables exist in the analytics dataset, inspect the events table schema, and query the last 24 hours of error events to correlate with an alert. ## Quick Start Ask the agent to list the available BigQuery datasets and then run a SQL query against a table you specify.