exploratory-data-analysis

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

Updated Aug 12, 2026
One-click install
npx skills add https://github.com/littlt-momo-c-yfc/skills --skill exploratory-data-analysis-littlt-momo-c-yfc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: exploratory-data-analysis
Source: https://github.com/littlt-momo-c-yfc/skills/tree/main/skills/scientific-toolkit-skill/references/scientific-skills/exploratory-data-analysis
Command: npx skills add https://github.com/littlt-momo-c-yfc/skills --skill exploratory-data-analysis-littlt-momo-c-yfc

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Scientific data arrives in hundreds of specialized formats, and understanding a file's structure, quality, and content before analysis requires format-specific expertise. This Skill automates file type detection, format-aware analysis, and report generation so researchers can quickly assess any scientific dataset. ## Core Features & Use Cases - Automatic Format Detection: Identifies 200+ scientific file extensions across chemistry, bioinformatics, microscopy, spectroscopy, proteomics, and general data categories. - Format-Specific Analysis: Loads detailed reference guides per format and runs appropriate analyses such as sequence statistics for FASTQ, structure validation for PDB, or intensity metrics for microscopy images. - Markdown Report Generation: Produces comprehensive reports covering file metadata, data characteristics, quality assessment, and downstream analysis recommendations. - Use Case: A researcher receives a FASTQ sequencing file and asks to explore it; the Skill detects the format, computes read counts, length distributions, and quality scores, then saves a structured EDA report with QC recommendations. ## Quick Start Analyze the attached data file and generate a full exploratory data analysis report with quality metrics 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 perform exploratory data analysis on a scientific data file?

Provide the file path and the Skill detects the extension, loads format-specific guidance, and runs appropriate analyses such as summary statistics, quality metrics, and structure checks. It then generates a markdown report saved as {filename}_eda_report.md.

What scientific file formats are supported for automated analysis?

Over 200 extensions are covered across six categories: chemistry and molecular formats like PDB and SDF, bioinformatics formats like FASTQ and BAM, microscopy formats like ND2 and CZI, spectroscopy formats like mzML, proteomics formats, and general formats like CSV, HDF5, and NumPy arrays.

Which Python libraries are needed to read bioinformatics files like FASTQ?

FASTQ and FASTA files are parsed with Biopython's SeqIO, while alignment files like BAM use pysam. If a library is missing, the Skill reports the import error and suggests the installation command such as pip install biopython.

Can the analyzer handle very large data files?

Yes, the script samples large inputs, for example reading only the first 10,000 rows of CSV files or first 10,000 FASTQ reads. For huge datasets it recommends chunked processing, memory-mapped access for HDF5 and NPY, and sample-based estimates.

What happens if my file extension is not recognized?

Unknown extensions are labeled as unknown format and the Skill falls back to generic analysis based on whether the file is text or binary. It may ask the user about the format and provide general recommendations instead of format-specific metrics.