data-context

Interview users to document dataset knowledge, sources, relationships, and metrics.

19|5|Updated Jan 4, 2026

Search Tags:#data quality #data dictionary #data governance #data documentation #tribal knowledge #data context

Ready to run

npx skills add https://github.com/edwinhu/workflows --skill data-context-edwinhu

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you capture and document the implicit knowledge about your datasets, making complex data understandable and reusable for everyone.

Core Features & Use Cases

Data Discovery: Systematically interviews users to understand data sources, entities, and relationships.
Metric Definition: Captures precise definitions, edge cases, and common misinterpretations for key metrics.
Data Quality Documentation: Identifies and documents known data quality issues and common pitfalls.
Use Case: A data science team is onboarding a new analyst to a critical customer database. This Skill generates a comprehensive data dictionary, including entity relationships, metric calculations, and common gotchas, enabling the new analyst to quickly become productive.

Quick Start

Start an interview to create a data context skill for the 'customer_orders' dataset.

Frequently Asked Questions about data-context

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

FAQPage Schema

How do I document tribal knowledge and data context for existing datasets?▼

To document tribal knowledge and data context, you can use a structured interview process that systematically captures data sources, entity relationships, metric definitions, and data quality issues directly from domain experts.

What is the best way to create a data dictionary that includes known data quality issues?▼

The best way to create a data dictionary with data quality issues is to conduct structured user interviews that capture precise metric definitions, edge cases, common misinterpretations, and known pitfalls for comprehensive data governance.

How can I capture metric definitions and entity relationships for data governance?▼

You can capture metric definitions and entity relationships for data governance by guiding users through an interview process designed to extract implicit dataset knowledge and document it systematically.

Can I onboard new analysts faster by documenting common query patterns and gotchas?▼

Yes, you can onboard new analysts faster by generating comprehensive data documentation that details common query patterns, edge cases, and common gotchas, enabling them to quickly understand complex datasets.

Does this approach require manual input to build reusable data documentation?▼

Yes, this approach requires manual input through an interactive interview process where users answer targeted questions to ensure accurate and comprehensive documentation of their specific dataset context.

When should I use a structured interview for data discovery instead of automated profiling?▼

You should use a structured interview for data discovery when you need to uncover implicit tribal knowledge, such as common misinterpretations and business context, that automated data profiling cannot detect.