data-profile

Profile tabular data files to extract structure, types, and distributions.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Profiles the given tabular data file to understand its structure, data types, and distributions, enabling informed data cleaning, analysis, and modeling.

Core Features & Use Cases

  • Indexing and format detection (CSV/TSV/Excel) with headers and row counts
  • Comprehensive statistics generation (including moarstats) for data health and quality
  • Data dictionary, dataset description, and tags generation via describegpt or a fallback profile

Quick Start

Run data-profile on a CSV or Excel file to generate a full profile with row count, headers, statistics, and a data dictionary.

Frequently Asked Questions about data-profile

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

FAQPage Schema
How do I profile a large CSV file to check data quality and statistics?

To profile a large CSV file, this Skill indexes the data, sniffs the format, counts rows, and computes comprehensive statistics to assess data health and structure.

What is a data dictionary and how does it help with tabular data analysis?

A data dictionary documents tabular data structure and types. This Skill generates a dictionary, dataset description, and tags using describegpt or a fallback profile to prepare data for analysis.

Can I generate statistics and frequency distributions for Excel files?

Yes, you can generate statistics and frequency distributions for Excel files. The Skill detects Excel formats alongside CSV and TSV, extracting headers and computing statistics for quality assessments.

What's the best way to prepare a new dataset for feature engineering?

The best way to prepare a dataset for feature engineering is to run a full profile. This extracts headers, computes statistics, and produces frequency distributions to understand data types.

Does data profiling work with TSV files and generate a data dictionary?

Yes, data profiling works with TSV files. It sniffs the format, counts rows, and generates a describegpt-based data dictionary or a fallback profile to document the dataset for analytics readiness.