Explore all skills by this author →

Verified:𝕏@tomlupo7 GitHub

exploratory-data-analysis

Automate exploratory data analysis of scientific files and generate Markdown reports.

Updated Jan 22, 2026

Search Tags:#analyze #metadata-extraction #markdown-report #exploratory-data-analysis #scientific-data #file-detection

Ready to run

npx skills add https://github.com/tomlupo/ai-playground --skill exploratory-data-analysis-tomlupo

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: exploratory-data-analysis
Source: https://github.com/tomlupo/ai-playground/tree/main/.claude/skills/exploratory-data-analysis
Command: npx skills add https://github.com/tomlupo/ai-playground --skill exploratory-data-analysis-tomlupo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires numpy, pandas, biopython, h5py, Pillow.

What problem does it solve?

This Skill automates exploratory data analysis for scientific data files, providing automatic file type detection, format-specific metadata extraction, data quality assessment, and actionable downstream recommendations. It eliminates manual trial-and-error exploration and delivers ready-to-share markdown reports.

Core Features & Use Cases

Automatic detection of 200+ scientific file formats and extraction of format-specific metadata.
Automated Markdown report generation with data quality metrics and actionable downstream recommendations.
Use cases include data inventories, quality control, preprocessing planning, and documentation for research workflows.

Quick Start

Provide a path to a data file (e.g., data.csv, reads.fastq, or image.tif) and the skill will generate a structured EDA report with metadata, statistics, and recommendations.

Frequently Asked Questions about exploratory-data-analysis

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

FAQPage Schema

How do I automate exploratory data analysis for scientific files?▼

Automate exploratory data analysis by providing a file path, which triggers automatic format detection, metadata extraction, and quality assessment to generate a structured markdown report.

Can I extract metadata and generate a report from microscopy or spectroscopy data?▼

Yes, you can extract format-specific metadata and generate reports across microscopy, spectroscopy, proteomics, metabolomics, chemistry, and biology data formats.

How do I check data quality and structure for research workflows?▼

Check data quality by running the skill on your scientific files to compute quality metrics and summarize structure, producing a markdown report with actionable downstream recommendations.

Does exploratory data analysis work with HDF5, FASTQ, and TIFF image files?▼

Yes, exploratory data analysis works with these formats by detecting over 200 scientific file types and leveraging dependencies like h5py, biopython, and Pillow to parse their content.

What is the best way to document data inventories and preprocessing planning?▼

The best way to document data inventories is to use automated markdown report generation, which captures metadata, statistics, and quality metrics for preprocessing planning and research documentation.

Related Skills

Explore More Data & Analytics Skills→

dralkh