data-context-extractor

Extract schema, terminology, metrics, and query patterns into a data-context skill.

5|2|Updated Feb 15, 2026
One-click install
npx skills add https://github.com/NOMARJ/sigil --skill data-context-extractor-nomarj
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-context-extractor
Source: https://github.com/NOMARJ/sigil/tree/main/packs/data/skills/data-engineering/data-context-extractor
Command: npx skills add https://github.com/NOMARJ/sigil --skill data-context-extractor-nomarj

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Build a project-specific data analysis skill by capturing schema, terminology, metrics, and common query patterns so AI agents can reason with domain context.

Core Features & Use Cases

  • Bootstrap mode discovers schema via database access or user-provided descriptions.
  • Tribal Knowledge Interview gathers business context, metrics definitions, and terminology.
  • Output a data-context skill at .claude/skills/ or .nomark/data/ with comprehensive sections: schema, metrics, queries, gotchas, terminology, and freshness.
  • Iteration mode updates existing skills and logs amendments.

Quick Start

Run the data-context-extractor to generate a project-specific data context skill and save it to the project’s .claude/skills or .nomark/data directory.

Frequently Asked Questions about data-context-extractor

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

FAQPage Schema
How do I document data warehouse schema and business terminology for AI assistants?

To build a project-specific data context skill, run the extractor in bootstrap mode to discover your database schema, complete the Tribal Knowledge Interview to gather metrics and terminology, and save the output to your project directory.

Can I update an existing data context skill with new query patterns and schema changes?

A data context skill is a structured knowledge base file that codifies table relationships, metrics definitions, and common query patterns so AI agents can reason with domain context during data analysis.

Does this data context extractor work with data lakes and analytics projects?

The generated data context skill includes dedicated sections for schema overview, metrics dictionary, common query patterns, gotchas, terminology, and freshness, providing comprehensive domain context for AI agents.

What is the best way to capture tribal knowledge and metrics definitions for a data lake?

The data context extractor requires either direct database access for schema discovery or user-provided schema descriptions, alongside your tribal knowledge of business terminology and metrics definitions to generate the skill.