Do I need to manually write the documentation files?

No, the extractor uses Bootstrap and Iteration modes to automatically generate and update SKILL.md and reference files based on conversational input and schema exploration.

Can I update an existing skill after it's been created?

Yes, the Iteration Mode allows you to load an existing skill and add context for new domains, missing metrics, or undocumented table relationships.

What databases does the Data Context Extractor support?

It supports major data warehouses including BigQuery, Snowflake, Redshift, PostgreSQL, and Databricks by leveraging available MCP tools.

How does it handle 'tribal knowledge' that isn't in the database?

It asks targeted questions about entity disambiguation, primary identifiers, and common analyst mistakes to capture logic that isn't evident in raw table schemas.

Is this a standalone data analysis tool?

It is a meta-skill designed to generate a specialized 'data-analyst' skill tailored to your company's specific data environment for Claude to use in future sessions.

Data Context Extractor

Name: Data Context Extractor
Author: lilbom32

bylilbom32

0•

数据科学与机器学习

Automates the creation of company-specific data analysis skills by extracting domain knowledge and schema context from analysts.

Data Context Extractor is a specialized meta-skill designed to bridge the gap between raw data warehouses and Claude's ability to provide accurate business insights. It works by interviewing analysts to capture 'tribal knowledge'—such as complex metric definitions, entity relationships, and common query pitfalls—that isn't found in standard schema documentation. Whether bootstrapping a new project or iterating on an existing setup, it generates a structured knowledge base including SKILL.md and detailed reference files, enabling Claude to write expert-level SQL and navigate specific business logic with high precision.

主要功能

01Generates structured reference files for domain-specific context and documentation

02Bootstrap mode for rapid initial setup of data analysis environments

03Automated schema discovery for BigQuery, Snowflake, Redshift, and PostgreSQL

04Guided interview workflow to capture entity relationships and metrics

050 GitHub stars

06Iteration mode for refining existing skills with new domains or updated business logic

使用场景

01Documenting internal tribal knowledge regarding SQL query patterns and metrics

02Onboarding Claude to a complex corporate data warehouse with custom business logic

03Standardizing data analysis across different departments like Marketing, Finance, and Product

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add lilbom32/ketnoitrithuc data-context-extractor

For use in Claude.ai and ChatGPT

主要功能

01Generates structured reference files for domain-specific context and documentation

02Bootstrap mode for rapid initial setup of data analysis environments

03Automated schema discovery for BigQuery, Snowflake, Redshift, and PostgreSQL

04Guided interview workflow to capture entity relationships and metrics

050 GitHub stars

06Iteration mode for refining existing skills with new domains or updated business logic

使用场景

01Documenting internal tribal knowledge regarding SQL query patterns and metrics

02Onboarding Claude to a complex corporate data warehouse with custom business logic

03Standardizing data analysis across different departments like Marketing, Finance, and Product