data-context-extractor

Extract data warehouse knowledge to generate structured skill artifacts.

1|Updated Feb 19, 2026
One-click install
npx skills add https://github.com/cyyeh/duckdb-data-agent --skill data-context-extractor-cyyeh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-context-extractor
Source: https://github.com/cyyeh/duckdb-data-agent/tree/main/plugins/data/skills/data-context-extractor
Command: npx skills add https://github.com/cyyeh/duckdb-data-agent --skill data-context-extractor-cyyeh

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Extracts and captures company-specific, analyst tribal knowledge about data warehouses so AI assistants can query and reason correctly about business data. It reduces ambiguity around entities, metrics, and common query patterns that typically cause incorrect analysis or repeated clarifying questions.

Core Features & Use Cases

  • Bootstrap Mode: Connects to a warehouse, discovers schemas and key tables, asks targeted discovery questions, and generates a new data-analysis skill with SKILL.md and reference files.
  • Iteration Mode: Loads an existing skill, identifies gaps, prompts for domain-specific clarifications, and appends or updates domain reference files and metric definitions.
  • Deliverables & Packaging: Produces a structured skill folder with references and optional packaging into a distributable archive using an included script.
  • Common Scenarios: Onboarding new analysts, consolidating metric definitions, documenting entity relationships, and creating reproducible query patterns for BI.

Quick Start

Create a data context skill for our BigQuery warehouse by discovering schemas, identifying the 3–5 most-used tables, clarifying entity definitions and metric formulas, and generating SKILL.md plus references.

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 our data warehouse to document metrics and schemas?

To extract data warehouse tribal knowledge, this skill connects to your warehouse, discovers schemas, asks targeted questions, and generates structured reference files documenting metrics and entity relationships. It captures analyst knowledge to reduce ambiguity and prevent incorrect analysis.

Does this data context extractor support BigQuery, Snowflake, PostgreSQL, and Databricks?

Yes, the data context extractor supports BigQuery, Snowflake, PostgreSQL, and Databricks for schema discovery and metric documentation. It requires access to schema or query tools to read warehouse structures and generate corresponding skill artifacts.

How do I bootstrap a new data analysis skill from an existing warehouse schema?

To bootstrap a data analysis skill, use Bootstrap Mode to connect to your warehouse, discover schemas and key tables, answer discovery questions, and generate a SKILL.md file with reference documents. This produces a structured skill folder for querying business data.

Can I update existing metric definitions and entity documentation without starting over?

Yes, Iteration Mode loads an existing data analysis skill, identifies gaps in metric definitions or entity relationships, prompts for domain-specific clarifications, and appends or updates reference files. This iteratively improves warehouse documentation without rebuilding from scratch.

What's the best way to package a generated data skill for distribution to other analysts?

The best way to package a generated data skill is using the included packaging script, which bundles the SKILL.md, reference files, and schema documentation into a distributable archive. This creates a reproducible skill folder for onboarding new analysts.

When do I need to document data warehouse entities and query patterns for AI assistants?

You need to document warehouse entities and query patterns when AI assistants require accurate business context to query data correctly. This skill clarifies metric formulas, documents entity relationships, and produces reference files that reduce repeated clarifying questions.