data-context-extractor

Extract analyst tribal knowledge into structured entity, metric, and table reference files.

Updated Apr 8, 2026
One-click install
npx skills add https://github.com/sun2443/designer-skills --skill data-context-extractor-sun2443
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-context-extractor
Source: https://github.com/sun2443/designer-skills/tree/main/data/skills/data-context-extractor
Command: npx skills add https://github.com/sun2443/designer-skills --skill data-context-extractor-sun2443

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It removes the gap between generic analytics guidance and your company’s real data reality by capturing analysts’ tribal knowledge into a structured, reusable data-analysis skill.

Core Features & Use Cases

  • Bootstrap Mode: Discovers your warehouse schemas and then guides targeted questioning to generate initial entities, metrics, and table/domain references.
  • Iteration Mode: Loads an existing skill and incrementally improves it by adding missing domain context, metrics definitions, or terminology reference files.
  • Warehouse-Aware Outputs: Produces a consistent skill structure with reference files (entities, metrics, domain tables) and SQL dialect guidance tailored to the user’s environment.

Quick Start

Ask the AI to create a data context skill for your Snowflake warehouse by discovering key tables, asking the core entity/metrics/filter questions, and generating the structured references files.

Frequently Asked Questions about data-context-extractor

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

FAQPage Schema
How do I capture analyst tribal knowledge into structured data context for a data warehouse?

The tool extracts tribal knowledge through schema discovery and targeted conversational questioning, packaging definitions into structured reference files with SQL dialect notes for your warehouse.

What is the best way to bootstrap data analysis skills for a new Snowflake warehouse?

Use bootstrap mode to discover warehouse schemas and guide targeted questioning, generating initial entities, metrics, and table or domain reference files for new warehouse environments.

Can I add missing metrics definitions to an existing data context skill?

Yes, iteration mode loads an existing skill and incrementally improves it by adding missing domain context, metrics definitions, or terminology reference files across domains and metrics.

Does the skill generation process require a warehouse connection for schema discovery?

Yes, schema discovery requires a warehouse connection to identify key tables, which then informs the targeted questioning for entities, identifiers, metrics, filters, and data gotchas.

What outputs does the data context extractor generate for metrics and entities?

It generates a skill folder structure containing reference files for entities, metrics, and domain tables, alongside SQL dialect guidance tailored to the user's specific warehouse environment.

Do I need to define skill metadata in YAML format before extracting data context?

Yes, you need YAML-frontmatter-defined skill metadata before extraction, as it structures the generated entity, metric, and table reference files into the proper skill folder format.