Verified:GitHub

exploratory-data-analysis

Detect scientific file types, extract metadata, assess quality, and generate markdown reports.

Updated Feb 13, 2026

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

Ready to run

npx skills add https://github.com/mwathiben/PropManager --skill exploratory-data-analysis-mwathiben

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires numpy, pandas, biopython, Pillow, h5py, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This skill automates the exploration and documentation of scientific data files by detecting formats, extracting metadata, evaluating data quality, and producing a structured markdown report that supports downstream analysis planning.

Core Features & Use Cases

Automatic file-type detection and format-specific analysis across 200+ scientific formats
Metadata extraction, quality assessment, and structured report generation for documentation and reproducibility
Use cases include pre-analysis scoping for chemistry, genomics, microscopy, spectroscopy, and general scientific datasets; ideal for data pipelines, labs, and research projects.

Quick Start

Run the EDA analyzer on a scientific data file to generate a Markdown report detailing format detection, metadata extraction, quality assessment, 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 across multiple formats?▼

Automated exploratory data analysis detects file types, extracts metadata, and assesses data quality across 200+ scientific formats to generate structured markdown reports. This streamlines pre-analysis scoping for chemistry, genomics, microscopy, and spectroscopy datasets.

Can I extract metadata and assess quality from microscopy and proteomics datasets?▼

Yes, metadata extraction and quality assessment support microscopy and proteomics datasets alongside chemistry, biology, and spectroscopy files. The analyzer auto-detects formats and generates structured documentation for research pipelines and lab projects.

Does the EDA analyzer work with HDF5 and image files for scientific data processing?▼

Yes, scientific data processing supports HDF5 files through h5py and image files through Pillow dependencies. These enable format-specific analysis, metadata extraction, and quality assessment for microscopy and general scientific datasets.

What's the best way to generate markdown reports for scientific data exploration?▼

Automated EDA generates markdown reports by detecting file types, extracting metadata, and evaluating data quality across scientific formats. Running the analyzer on a data file produces a structured artifact detailing format detection and recommendations.

Do I need pandas and biopython to run exploratory analysis on genomics data?▼

Yes, exploratory analysis on genomics data uses biopython for biological formats and pandas for data manipulation. These dependencies enable metadata extraction, quality assessment, and structured report generation for genomics datasets.

When should I use automated EDA instead of manual data profiling for research datasets?▼

Automated EDA is ideal for pre-analysis scoping across chemistry, biology, and spectroscopy datasets in labs or pipelines. It handles 200+ scientific formats, making it more efficient than manual profiling for format detection and reproducible documentation.