data-science

Automate statistical analysis planning and data exploration for scientific datasets.

13|Updated Dec 16, 2025

Search Tags:#visualization #pandas #statistics #data-analysis #reproducibility #scipy #exploratory-data-analysis

Ready to run

npx skills add https://github.com/justaddcoffee/open-science-skills --skill data-science-justaddcoffee

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-science
Source: https://github.com/justaddcoffee/open-science-skills/tree/main/data-science
Command: npx skills add https://github.com/justaddcoffee/open-science-skills --skill data-science-justaddcoffee

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides structured guidance for planning and performing statistical analysis and data exploration on scientific datasets, helping researchers choose appropriate methods and interpret results.

Core Features & Use Cases

Exploratory Data Analysis: Quick data overview, distribution checks, and visualization guidance.
Statistical Method Guidance: Selection of tests (t-test, ANOVA, non-parametric alternatives) and effect size interpretation.
Reproducibility & Reporting: Templates and workflow rigor to support reproducible analyses and clear results reporting.

Quick Start

Tell Claude to perform a quick data overview and suggest appropriate statistical tests for your dataset.

Frequently Asked Questions about data-science

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

FAQPage Schema

How do I perform exploratory data analysis and choose the right statistical test for my dataset?▼

Exploratory data analysis involves generating quick data overviews, checking distributions, and visualizing variables to guide statistical test selection. This Skill automates planning these workflows for scientific datasets, suggesting appropriate tests like t-tests or ANOVA based on your data characteristics and assumptions.

Can I use pandas and scipy for reproducible statistical analysis workflows?▼

Yes, reproducible statistical analysis relies on standard Python libraries like pandas, numpy, scipy, and seaborn for data handling and visualization. This Skill enforces clear, reproducible steps and provides reporting templates to ensure your data exploration and assumption checking are fully documented.

What is the best way to interpret effect sizes and check statistical assumptions for scientific data?▼

Checking statistical assumptions requires evaluating data distributions and variance homogeneity before applying tests like ANOVA or non-parametric alternatives. This Skill provides structured guidance for assumption checking, effect size interpretation, and result reporting to ensure valid scientific conclusions.

Does this statistical analysis approach support non-parametric alternatives and visualization guidance?▼

Yes, non-parametric alternatives are fully supported alongside visualization guidance for exploratory data analysis. The Skill helps you select appropriate statistical methods, generate distribution checks, and apply common plots using seaborn to visualize patterns across diverse scientific domains.

What statistical libraries do I need to run data exploration and analysis planning?▼

You need standard Python libraries including pandas, numpy, scipy, and seaborn to handle data processing, calculate statistics, and generate visualizations. These dependencies support the full exploratory data analysis workflow from initial data overview through final result interpretation and reporting.

When should I use non-parametric tests instead of t-tests or ANOVA for my data analysis?▼

Non-parametric tests are recommended when your data violates normality assumptions required by t-tests or ANOVA. This Skill guides you through assumption checking during exploratory data analysis, helping determine whether parametric or non-parametric alternatives are appropriate for your scientific dataset.