data-describe

Generate a data dictionary, description, and semantic tags for CSV, TSV, and Excel files.

3.7k|104|Updated Dec 11, 2020
One-click install
npx skills add https://github.com/dathere/qsv --skill data-describe
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-describe
Source: https://github.com/dathere/qsv/tree/main/.claude/skills/skills/data-describe
Command: npx skills add https://github.com/dathere/qsv --skill data-describe

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generating a clear, maintainable data dictionary and dataset description for tabular data is often manual, time-consuming, and error-prone.

Core Features & Use Cases

  • Generate a Data Dictionary detailing column names, types, and descriptions.
  • Create a natural-language dataset Description to aid data catalogs and documentation.
  • Produce semantic Tags to improve searchability and data discovery.

Quick Start

Provide a path to a tabular data file (CSV/TSV/Excel) to generate the dictionary, description, and tags.

Frequently Asked Questions about data-describe

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

FAQPage Schema
How do I generate a data dictionary for a CSV file?

To generate a data dictionary for a CSV file, use this Skill to compute per-column metadata via describegpt, producing a Markdown report with column names, types, and descriptions.

Can I automatically create a dataset description from an Excel file?

Yes, you can create a dataset description from an Excel file by providing the file path. The Skill analyzes the tabular data and generates a natural-language description to aid data catalogs.

What is the best way to add semantic tags to tabular data for discovery?

The best way to add semantic tags is to process tabular data files through this Skill, which outputs tags designed to improve searchability and data discovery within analytics workflows.

Does this data documentation tool support TSV files?

Yes, this data documentation tool supports TSV files, alongside CSV and Excel formats, indexing the provided tabular file for fast access before computing the metadata.

What format is the generated data dictionary output in?

The generated data dictionary is output in Markdown format by default, detailing column names, types, and descriptions to create clear, maintainable data documentation.