data-eda

Detect scientific file formats and generate Markdown analysis reports.

Updated Mar 21, 2026
One-click install
npx skills add https://github.com/ManfronEnrico/thesis-manifold --skill data-eda
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-eda
Source: https://github.com/ManfronEnrico/thesis-manifold/tree/main/.claude/skills/data-eda
Command: npx skills add https://github.com/ManfronEnrico/thesis-manifold --skill data-eda

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?

Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats.

Core Features & Use Cases

  • Automatic file-type detection and format-specific metadata extraction
  • Comprehensive data quality assessment and markdown report generation
  • Supports 200+ scientific file formats across chemistry, biology, imaging, spectroscopy, and omics
  • Downstream analysis guidance and recommendations based on detected formats

Quick Start

Run the EDA workflow on a target scientific data file to generate a detailed Markdown report.

Frequently Asked Questions about data-eda

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

FAQPage Schema
How do I automatically extract metadata and assess quality for scientific data files?

You can automatically classify scientific data files by extension and content to extract format-specific metadata and compute quality metrics. The skill routes analysis to specialized modules and outputs a structured result with a detailed Markdown report.

Can I run exploratory data analysis on bioinformatics formats like HDF5 and microscopy images?

Yes, exploratory data analysis supports bioinformatics and microscopy formats using dependencies like h5py, biopython, and Pillow. The skill automatically detects file types, extracts format-specific metadata, and computes quality metrics for downstream analysis.

What is the best way to generate a structured report from chemistry and omics data formats?

The best way to generate a structured report from chemistry and omics data is to use an automated file-type detection workflow. The skill extracts format-specific metadata, computes quality metrics, and returns a detailed Markdown report with downstream analysis recommendations.

Does this automated EDA workflow support numpy and pandas data processing?

Yes, the automated EDA workflow utilizes numpy and pandas as core dependencies to process scientific data. It leverages these libraries to compute quality metrics and extract metadata across 200+ scientific file formats before generating a Markdown report.

How do I get downstream analysis recommendations after profiling scientific data?

You get downstream analysis recommendations by running the EDA workflow on a target scientific file. The skill returns a structured Markdown report containing detected format information, quality metrics, and specific guidance for subsequent analytical steps.

What are the limitations when analyzing unsupported scientific file extensions?

When analyzing unsupported scientific file extensions, the skill cannot route analysis to specialized modules for format-specific metadata extraction. It is designed to cover 200+ known formats across chemistry, biology, imaging, spectroscopy, and omics domains.