skills.rest
shushuzn
shushuznCOMMUNITY
Explore all skills by this author →
GitHub

exploratory-data-analysis

Detect scientific file formats and generate markdown EDA reports with quality metrics.

4|Updated Mar 2, 2026
Search Tags:#bioinformatics#exploratory data analysis#file type detection#markdown reporting#data quality assessment#scientific file formats
One-click install
npx skills add https://github.com/shushuzn/Rairos --skill exploratory-data-analysis-shushuzn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: exploratory-data-analysis
Source: https://github.com/shushuzn/Rairos/tree/main/skills/exploratory-data-analysis
Command: npx skills add https://github.com/shushuzn/Rairos --skill exploratory-data-analysis-shushuzn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires os, sys, pathlib, datetime, json, re, numpy, pandas, h5py, h5py, PIL, Bio, pydicom, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill removes the guesswork of understanding scientific data by automatically detecting file formats and producing a structured EDA report that highlights quality issues and next-step recommendations.

Core Features & Use Cases

  • Automatic file type detection across 200+ scientific formats and categories, then routes to format-specific analysis guidance.
  • Format-aware extraction & QC including structure/dimensions, statistical summaries, and data integrity checks (plus sampling strategies for large files).
  • Markdown report generation that includes required sections (metadata, findings, recommendations) to support downstream analysis planning.

Use case examples: exploring a .fastq run to assess read length and quality, inspecting an .hdf5/.h5ad dataset structure and metadata completeness, or characterizing an imaging .tif/.nd2 file’s dimensionality and pixel intensity ranges.

Quick Start

Analyze /path/to/your/scientific_file.fastq and generate a comprehensive EDA markdown report.

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 file formats like HDF5 and FASTQ?▼

You can perform exploratory data analysis on scientific files by automatically detecting the format, extracting structural dimensions and statistical summaries, and generating an actionable markdown report with quality metrics and recommendations for formats like HDF5 and FASTQ.

Can I assess data quality and structure for large bioinformatics files without loading everything into memory?▼

Yes, exploratory data analysis can assess data quality for large bioinformatics files by applying large-file sampling strategies and format-specific routing to extract structural dimensions, metadata completeness, and integrity checks without full memory loading.

Does this exploratory data analysis approach support microscopy and proteomics file types?▼

Yes, this exploratory data analysis approach supports microscopy and proteomics file types by routing format-specific analysis guidance to characterize imaging dimensionality, pixel intensity ranges, and proteomics dataset structures across 200+ scientific formats.

How do I generate a markdown report with data quality metrics from a raw scientific dataset?▼

To generate a markdown report with data quality metrics from a raw scientific dataset, the analyzer workflow detects the file type, applies format-aware extraction for statistical summaries and integrity checks, and outputs a structured report with metadata, findings, and recommendations.

What is the best way to inspect the metadata completeness of an h5ad dataset?▼

The best way to inspect metadata completeness of an h5ad dataset is using format-aware exploratory data analysis, which routes the HDF5 file to extract its internal structure, dimensions, and metadata, then highlights data integrity issues and next-step recommendations.

What are the limitations of automatic file type detection for scientific datasets?▼

Limitations of automatic file type detection for scientific datasets include relying on extension-to-reference mapping, meaning misnamed files or unsupported formats may fail to route correctly to the format-specific analysis guidance required for accurate quality assessment.

Related Skills

Explore More Data & Analytics Skills→
arm2armarm2arm
4

hdf5-on-s3-cached

Cache HDF5 files from S3 locally and convert subsets to Parquet.

Community
Intermediate
Weiwei-MaoWeiwei-Mao
2

exploratory-data-analysis

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

Community
Advanced
Mohamed-ElkahefMohamed-Elkahef

csv-data-visualizer

Generate interactive Plotly visualizations and statistical profiles from CSV datasets.

Community
Intermediate
Clay-HHKClay-HHK
2

exploratory-data-analysis

Detect scientific file types and generate markdown EDA reports with quality metrics.

Community
Advanced