data-context-extractor

Extract company-specific data warehouse knowledge to generate analysis skills.

145|36|Updated Feb 26, 2026

Search Tags:#SQL #skill generation #data analysis #metadata extraction #data warehouse #tribal knowledge

Ready to run

npx skills add https://github.com/w95/awesome-claude-corporate-skills --skill data-context-extractor-w95

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-context-extractor
Source: https://github.com/w95/awesome-claude-corporate-skills/tree/main/10-data-analytics/data-context-extractor
Command: npx skills add https://github.com/w95/awesome-claude-corporate-skills --skill data-context-extractor-w95

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps create and refine data analysis skills by systematically extracting crucial, company-specific information about data warehouses, metrics, and terminology from analysts.

Core Features & Use Cases

Bootstrap Mode: Guides users through discovering schemas, asking targeted questions, and generating a new, tailored data analysis skill with reference files.
Iteration Mode: Enhances existing skills by identifying knowledge gaps and adding domain-specific context through targeted discovery and new reference files.
Use Case: A data team wants to build a comprehensive skill for their Snowflake data warehouse. They use this Skill in Bootstrap Mode, which helps them document key tables, define metrics like ARR, and capture common query patterns, resulting in a ready-to-use snowflake-data-analyst skill.

Quick Start

Use the data-context-extractor skill to create a new data analysis skill for our BigQuery warehouse.

Frequently Asked Questions about data-context-extractor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract tribal knowledge from data warehouse analysts into reusable SQL playbooks?▼

Bootstrap Mode discovers schemas and asks targeted questions to generate a new, tailored data analysis skill with reference files. It captures essential company-specific terminology, key tables, and common query patterns from your data warehouse environment.

Can I append new context to an existing data analysis skill?▼

Yes, Iteration Mode appends context to existing data analysis skills by identifying knowledge gaps and adding domain-specific context through targeted discovery. It generates new reference files to enhance the coverage of your current data warehouse playbooks.

How do I document data warehouse metrics and schemas for new SQL analysts?▼

You can document data warehouse schemas and metrics by systematically extracting company-specific information from current analysts. This process builds ready-to-use reference files that define metrics like ARR and capture common query patterns for new SQL analysts.

Does this work for generating analysis skills tailored to unique data warehouse environments like Snowflake or BigQuery?▼

Yes, this generates tailored data analysis skills for specific data warehouse environments like Snowflake or BigQuery. It systematically captures company-specific metrics, schemas, and terminology to create a ready-to-use skill for your unique organizational data.

What is the best way to build a comprehensive data analysis skill for a new data warehouse?▼

The best way to build a comprehensive data analysis skill is using Bootstrap Mode to discover schemas, ask targeted questions, and generate a tailored skill with reference files. This systematically captures essential company-specific metrics and common query patterns.