data-scientist

Name: data-scientist
Availability: InStock
Author: takusaotome

Run automated exploratory data analysis and multi-model predictive evaluation on tabular datasets.

5|4|Updated Nov 9, 2025

Search Tags:#data visualization #feature engineering #model comparison #exploratory data analysis #time series forecasting #statistical diagnostics

Ready to run

npx skills add https://github.com/takusaotome/claude-skills-library --skill data-scientist-takusaotome

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-scientist
Source: https://github.com/takusaotome/claude-skills-library/tree/main/skills/data-scientist
Command: npx skills add https://github.com/takusaotome/claude-skills-library --skill data-scientist-takusaotome

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy, matplotlib, seaborn, scikit-learn, statsmodels, pytest, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill helps you analyze tabular datasets and time-series data end-to-end—so you can move from raw files to actionable insights, validated models, and clear reports without guessing which steps to take next.

Core Features & Use Cases

Automated EDA (exploratory data analysis): generates data quality summaries and visual diagnostics for missing values, distributions, correlations, and target relationships.
Model selection and comparison: trains multiple regression/classification algorithms, evaluates them with appropriate metrics, and surfaces the best-performing approach.
Time-series diagnostics and forecasting: performs stationarity testing, decomposition, autocorrelation analysis, and multi-model forecasting with saved outputs.

Quick Start

Run automated exploratory analysis on your dataset by providing your data file and (optionally) a target column so the Skill generates an EDA report and visual outputs.

Frequently Asked Questions about data-scientist

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

FAQPage Schema

How do I run exploratory data analysis on a CSV file with a target column?▼

Exploratory data analysis on a tabular file generates data quality summaries, visual diagnostics for missing values, distributions, and correlations. Provide a CSV with an optional target column to produce an automated EDA report and visual outputs.

What's the best way to compare multiple machine learning models for a regression dataset?▼

Model comparison for regression datasets involves training multiple algorithms, evaluating them with appropriate metrics, and surfacing the best performer. Supply a tabular dataset and target column to generate a consolidated model results CSV.

How do I perform time series forecasting and stationarity testing in Python?▼

Time series forecasting and stationarity testing require a date/value data structure to run decomposition, autocorrelation analysis, and multi-model predictions. This generates a timeseries analysis report with diagnostic outputs.

Can I use pandas and scikit-learn for automated feature engineering and model evaluation?▼

Pandas and scikit-learn support automated feature preparation guidance and multi-model predictive evaluation. The workflow processes tabular datasets to validate models and generate actionable insights and reports.

Do I need statsmodels for statistical diagnostics and time series decomposition?▼

Statsmodels is required for statistical diagnostics, time series decomposition, and autocorrelation analysis. It enables stationarity testing and multi-model forecasting on date/value data structures to produce diagnostic reports.

Why does my exploratory data analysis report show missing values and correlation warnings?▼

Exploratory data analysis reports show missing values and correlation warnings because the automated EDA process scans tabular datasets to generate data quality summaries and visual diagnostics for target relationships.