Automates the creation of company-specific data analysis skills by capturing tribal knowledge and schema context from analysts.
The Data Context Extractor is a meta-skill designed to bridge the gap between raw data warehouses and actionable AI insights. It guides users through a structured discovery process to capture essential tribal knowledge—such as specific KPI formulas, entity disambiguation, and data hygiene rules—that documentation often misses. By automating schema exploration and standardized documentation generation, it creates specialized Claude Code sub-skills that allow Claude to act as a deeply informed data analyst tailored to your organization's unique environment.
主要功能
010 GitHub stars
02Dialect-aware SQL pattern generation and query 'gotcha' documentation.
03Guided interview framework to capture business logic and metric definitions.
04Dual-mode operation for both initial bootstrapping and iterative knowledge updates.
05Automated schema discovery for BigQuery, Snowflake, Redshift, and Databricks.
06Standardized reference file generation for entities, metrics, and domain-specific tables.
使用场景
01Onboarding Claude Code to a complex enterprise data warehouse with undocumented relationships.
02Standardizing data query patterns and filters across a distributed engineering or analytics team.
03Building a custom AI data analyst that understands internal company terminology and KPI math.
