data-scientist

Automate data science workflows for forecasting, segmentation, and optimization tasks.

467|103|Updated Jan 13, 2026

Search Tags:#analytics #statistics #modeling #experimentation #data-science #machine-learning

Ready to run

npx skills add https://github.com/borghei/Claude-Skills --skill data-scientist-borghei

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-scientist
Source: https://github.com/borghei/Claude-Skills/tree/main/data-analytics/data-scientist
Command: npx skills add https://github.com/borghei/Claude-Skills --skill data-scientist-borghei

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables teams to turn raw data into actionable insights by applying data science techniques to real-world business problems, accelerating decision making and reducing manual analysis.

Core Features & Use Cases

End-to-end data science workflows from data ingestion to model deployment-ready pipelines.
Machine learning model development, evaluation, and interpretation for business decisions.
Experiment design and analysis (A/B testing) for product optimization and forecasting.
Use cases include forecasting demand, customer segmentation, churn prediction, and anomaly detection in business data.

Quick Start

Install Python data science tooling and run sample scripts to bootstrap a small analytics pipeline.

Frequently Asked Questions about data-scientist

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

FAQPage Schema

How do I automate data science workflows for business analytics?▼

You can build a data science pipeline using Python libraries like pandas, numpy, and scikit-learn. These tools enable you to ingest data, develop machine learning models, and output deployment-ready pipelines for forecasting and segmentation.

What statistical modeling techniques work for churn prediction and customer segmentation?▼

Statistical modeling for churn prediction and customer segmentation leverages machine learning classification and clustering algorithms. Using Python's scikit-learn, you can evaluate model performance to identify at-risk customers and group behavioral profiles.

Do I need Python data science libraries to run predictive analytics pipelines?▼

Yes, you need Python data science libraries like pandas, numpy, and scikit-learn to run predictive analytics pipelines. They provide the foundational data structures and machine learning algorithms required for forecasting and anomaly detection.

How do I design A/B testing and experimentation for product optimization?▼

Designing A/B testing for product optimization involves structuring controlled experiments to compare variations and analyzing the statistical significance of results. This process validates product changes and forecasts their impact on business metrics.

What is the best way to forecast demand and detect anomalies in business data?▼

Forecasting demand and detecting anomalies is best achieved through predictive analytics and machine learning models. Applying time-series forecasting and statistical thresholds to business data highlights irregular patterns and predicts future demand trends.

Can I extend custom analytics pipelines with dashboards using scikit-learn and pandas?▼

Yes, you can extend custom analytics pipelines with dashboards after developing models with scikit-learn and pandas. The workflows are designed to be extensible, allowing you to connect deployment-ready model outputs to custom visualization interfaces.