skills.rest
corticalstack
corticalstackCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

exploratory-data-analysis

Detect scientific file types and generate markdown EDA reports.

1|1|Updated Feb 2, 2026
Search Tags:#omics#eda#data-quality#markdown-report#scientific-data#qaqc#file-type-detection
One-click install
npx skills add https://github.com/corticalstack/claude-code-flow --skill exploratory-data-analysis-corticalstack
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: exploratory-data-analysis
Source: https://github.com/corticalstack/claude-code-flow/tree/main/.claude/skills/exploratory-data-analysis
Command: npx skills add https://github.com/corticalstack/claude-code-flow --skill exploratory-data-analysis-corticalstack

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

It removes the guesswork of understanding unfamiliar scientific data by automatically detecting the file type, extracting format-specific metadata, assessing data quality, and producing a detailed markdown EDA report you can use immediately.

Core Features & Use Cases

  • Automatic file-type detection (extension-based) across many scientific disciplines, then format-specific EDA routed to the right analyzer logic.
  • Data quality assessment including basic integrity checks and summary statistics for quick validation of structure and content.
  • Report generation for downstream planning, including recommendations for preprocessing and next analyses, suitable for scientific documentation.

Quick Start

Use the exploratory-data-analysis skill to analyze the file path datafile.ext and generate a corresponding EDA report in markdown.

Frequently Asked Questions about exploratory-data-analysis

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

FAQPage Schema
How do I perform exploratory data analysis on scientific data files when I don't know the format?▼

Exploratory data analysis on unknown scientific files is handled by detecting the file extension, routing it to a format-specific analyzer, and generating a markdown report with metadata, quality metrics, and downstream recommendations.

What is the best way to assess data quality for bioinformatics and omics datasets?▼

Assessing data quality for omics and bioinformatics datasets involves extracting format-specific metadata, running basic integrity checks, calculating summary statistics, and documenting the results in a structured markdown EDA report.

Can I generate a markdown report for microscopy and spectroscopy file characterization?▼

Generating a markdown report for microscopy and spectroscopy files is supported by routing the file extension to the appropriate category analyzer to extract metadata, quantify basic metrics, and output downstream analysis recommendations.

Does exploratory data analysis work with HDF5 and image files for proteomics and metabolomics?▼

Exploratory data analysis works with HDF5 and image files by utilizing underlying libraries like h5py and Pillow to extract format-specific metadata and perform quality assessment across proteomics, metabolomics, and general scientific datasets.

How do I get recommendations for downstream preprocessing after detecting my scientific file structure?▼

To get downstream preprocessing recommendations, the skill analyzes your detected file structure, calculates basic quality metrics, and appends actionable next-analysis steps directly into the generated markdown EDA report.

Related Skills

Explore More Data & Analytics Skills→
bigbiobigbio
11

sdrf:annotate

Generate SDRF files for proteomics datasets from PXD accessions.

Official
Advanced
Weiwei-MaoWeiwei-Mao
2

exploratory-data-analysis

Analyze scientific data files across 200+ formats and generate Markdown reports.

Community
Advanced
kevinlinkevinlin
14

statistical-analysis

Analyze data distributions and test hypotheses with pandas, numpy, and scipy.

Community
Intermediate
zangjeicyzangjeicy

bioinformatics

Access and execute bioinformatics pipelines for genomics, transcriptomics, and structural modeling.

Community
Advanced