data-context-extractor

Name: data-context-extractor
Availability: InStock
Author: Hiroshi75

Capture and codify company data knowledge into machine-readable dictionaries.

Updated Mar 13, 2026

Search Tags:#data quality #data dictionary #metric definition #entity definition #data documentation #tribal knowledge

Ready to run

npx skills add https://github.com/hiroshi75/agentlattice --skill data-context-extractor-hiroshi75

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-context-extractor
Source: https://github.com/hiroshi75/agentlattice/tree/main/templates/skills/data/data-context-extractor
Command: npx skills add https://github.com/hiroshi75/agentlattice --skill data-context-extractor-hiroshi75

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the challenge of scattered and undocumented institutional data knowledge, making it difficult for teams to understand and effectively use their data assets.

Core Features & Use Cases

Entity & Metric Definition: Captures and codifies definitions for core business entities and key metrics.
Data Quality & Pitfalls: Documents known data quality issues and common analyst mistakes.
Business Context Mapping: Links business processes to data structures.
Use Case: Onboarding a new data analyst to a complex data warehouse by providing them with a comprehensive, machine-readable data dictionary and a guide to common pitfalls.

Quick Start

Use the data-context-extractor skill to bootstrap documentation for a new data environment by exploring schemas and asking critical questions.

Frequently Asked Questions about data-context-extractor

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

FAQPage Schema

How do I create a data dictionary from tribal knowledge and undocumented schemas?▼

To create a data dictionary from tribal knowledge, you can codify entity definitions, metric formulas, and table schemas into a machine-readable format. This approach captures business context and common pitfalls to facilitate environment onboarding.

What is the best way to document data quality issues and entity definitions?▼

Documenting data quality issues and entity definitions involves mapping business processes to data structures and recording known analyst mistakes. This creates a comprehensive guide that preserves institutional knowledge and prevents common errors.

How do I onboard a new data analyst to a complex data warehouse environment?▼

Onboarding a new data analyst to a complex data warehouse requires providing a comprehensive data dictionary and a guide to common pitfalls. Capturing business context mapping alongside metric formulas ensures they understand institutional data knowledge.

Can I bootstrap data documentation for a new environment by exploring schemas?▼

Yes, you can bootstrap data documentation for a new environment by exploring schemas and asking critical questions. This supports iterative documentation, allowing you to comprehensively manage data context through bootstrap and iteration modes.

How does business context mapping link processes to data structures?▼

Business context mapping links processes to data structures by codifying company-specific data knowledge into entity definitions and metric formulas. This translates scattered institutional knowledge into a structured, machine-readable data dictionary.

Does data context extraction support iterating on existing metric definitions?▼

Yes, data context extraction supports iteration modes for comprehensive data context management. You can iteratively update existing metric definitions, table schemas, and tribal knowledge as your understanding of the data environment evolves.