scientific-eda

Guide stepwise exploratory analysis of CSV, FASTA, and other scientific datasets with Python scripts via uv and PEP723 metadata, saving WebP plots and session journals under analysis/.

38|5|Updated Dec 20, 2025

Search Tags:#journal #eda #uv-run #scientific-data #exploratory-analysis #webp-plots #script-metadata

Ready to run

npx skills add https://github.com/ericmjl/skills --skill scientific-eda

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: scientific-eda
Source: https://github.com/ericmjl/skills/tree/main/skills/scientific-eda
Command: npx skills add https://github.com/ericmjl/skills --skill scientific-eda

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Defensive, human-led exploratory data analysis for scientific data. The agent does not open files and dump code; it captures problem context first, helps narrow to a single first step, takes instruction from the user, and asks "why?" before executing when the user requests a specific plot or table.

Core Features & Use Cases

Context-first problem capture before touching data.
Single first step guidance to narrow to one plot or summary.
Human-guided execution with prompts for clarification before actions.
Session-based analysis with a dedicated analysis/ folder, journal.md, plots/, and scripts/.
WebP plots for compact visualizations; uv-run with PEP723 scripts.

Quick Start

Describe your scientific question and data to start a guided analysis session.

Frequently Asked Questions about scientific-eda

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 without dumping code immediately?▼

Defensive exploratory data analysis captures problem context first, narrows to a single initial plot or summary, and prompts for clarification before executing any scripts on your scientific data files. This guided approach prevents premature code generation and ensures step-by-step validation.

Can I analyze CSV and FASTA files using a guided session structure?▼

Yes, you can analyze CSV, FASTA, and other scientific formats within a dedicated session structure. The process generates a per-session journal, saves WebP plots in a plots directory, and stores runnable Python scripts under an analysis folder.

Do I need uv to run Python scripts for exploratory analysis?▼

Yes, uv is required to run Python scripts for this exploratory analysis workflow. Scripts are executed via uv-run using PEP 723 inline metadata, ensuring the environment and dependencies are managed directly within each script.

What is the best way to maintain an analysis journal while exploring scientific data?▼

The best way to maintain an analysis journal is using a session-based structure that automatically records steps under an analysis directory. It captures problem context, tracks each plot or summary, and saves WebP visualizations alongside runnable scripts.

How does defensive EDA differ from standard automated data exploration?▼

Defensive EDA differs by requiring human guidance before executing plots or summaries, asking 'why?' before generating output, and avoiding automatic file dumping. Standard approaches often open files and generate code immediately without capturing initial problem context.