exploratory-data-analysis · davila7 — Claude Code skill: what it does

What exploratory-data-analysis does

Point the skill at a file path and it reads the extension, then looks it up across six reference categories: chemistry and molecular formats, bioinformatics and genomics, microscopy and imaging, spectroscopy, proteomics and metabolomics, and general scientific data. Over 200 extensions are covered, from .pdb and .fastq to .hdf5 and .ome.tiff. Each entry describes what data the format usually holds, which Python libraries read it, and what analysis fits.

You can run the bundled scripts/eda_analyzer.py, which detects the type, loads the reference entry and produces a markdown report. Or work in the conversation: check dimensions and missing values for tables, length distributions and quality scores for sequences, channel and calibration metadata for images. The report layout lives in assets/report_template.md.

Expect to install the Python library for whichever format you open — the skill names it in the reference, it does not install anything for you. A file whose extension is not in the references will not be detected automatically, so you fall back to manual inspection.