data-context-extractor

To document data warehouse tribal knowledge, you can use a bootstrap mode to discover schemas, disambiguate entities, and define metrics, generating a comprehensive data analysis skill with reference files for new analysts.

Extracting domain-specific metric definitions from BigQuery or Snowflake involves targeted discovery sessions with data analysts to identify common query patterns and schema relationships, systematically documenting the results for ongoing updates.

Yes, you can update existing data analysis skills using an iteration mode that adds context about new domains, metrics, or terminology through targeted discovery and documentation without overwriting previous knowledge.

Creating a data analysis skill for Snowflake schema discovery requires guiding users through key questions about entities and metrics, systematically extracting domain-specific knowledge to generate initial reference files.

Disambiguating entities in a data warehouse is necessary to resolve conflicting terminology across different teams, ensuring that metric definitions and common query patterns remain accurate and consistent for analysis.

No, the data context extraction process requires no external dependencies, operating autonomously through internal scripts and reference files to document data warehouse knowledge.