exploratory-data-analysis

Detect scientific data file types and generate Markdown exploratory analysis reports.

6|Updated Dec 30, 2025
One-click install
npx skills add https://github.com/pur3v4d3r/pur3-pkb-codebase --skill exploratory-data-analysis-pur3v4d3r
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: exploratory-data-analysis
Source: https://github.com/pur3v4d3r/pur3-pkb-codebase/tree/main/.claude/skills/__scientific-skills/exploratory-data-analysis
Command: npx skills add https://github.com/pur3v4d3r/pur3-pkb-codebase --skill exploratory-data-analysis-pur3v4d3r

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires numpy, pandas, biopython, h5py, pillow, nd2reader, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Automates exploratory data analysis of scientific data files across 200+ formats, generating comprehensive Markdown reports with format-specific metadata, data quality metrics, and actionable recommendations.

Core Features & Use Cases

  • Automatic file-type detection and format-specific analysis across chemistry, biology, imaging, and omics domains
  • Markdown report generation with detailed metadata, quality assessments, and downstream recommendations
  • Use Case: Analyze a raw data file to produce a complete EDA report for documentation and decision-making

Quick Start

Provide an EDA report for a given data file path and save as {filename}_eda_report.md

Frequently Asked Questions about exploratory-data-analysis

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

FAQPage Schema
How do I run exploratory data analysis on scientific data files without knowing the exact format?

Exploratory data analysis on scientific files can be automated by detecting the file type from its extension and content. The analysis retrieves reference information, runs format-specific assessments, and outputs a structured Markdown report.

Can I generate an EDA report for biology and imaging data formats like HDF5 and ND2?

Yes, EDA reports can be generated for biology and imaging formats using dependencies like h5py and nd2reader. The analysis produces format-specific metadata, quality assessments, and downstream recommendations for these scientific files.

What is the best way to assess scientific data quality and metadata across multiple formats?

Assessing scientific data quality across multiple formats is best handled by auto-detecting the file type and applying format-specific analyses. This generates a comprehensive Markdown report detailing metadata, quality metrics, and actionable recommendations.

Does this EDA tool support image files for quality assessment and metadata extraction?

Yes, image files are supported for quality assessment and metadata extraction through the Pillow dependency. The tool detects imaging formats, extracts relevant metadata, and includes the results in the final Markdown report.

How do I get downstream recommendations after analyzing my raw omics data?

Downstream recommendations for omics data are generated by running format-specific analyses on the detected file. The resulting Markdown report includes actionable insights and next steps based on the extracted metadata and quality metrics.