data-scientist

Recommends storage, ETL, and ML frameworks for data science projects.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/MattJColes/macols-configs --skill data-scientist-mattjcoles
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-scientist
Source: https://github.com/MattJColes/macols-configs/tree/main/shared/personas/data-scientist
Command: npx skills add https://github.com/MattJColes/macols-configs --skill data-scientist-mattjcoles

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill offers a structured approach for data science and engineering tasks, providing best practices for data storage, processing, and machine learning model choice.

Core Features & Use Cases

  • Data Storage Guidance: Offers expert advice on choosing the right storage solution like S3, Athena, and Redshift.
  • ETL Best Practices: Suggests light tools for data processing like Lambda, AWS Glue, and DuckDB/Pandas.
  • ML Model Recommendations: Assists in selecting appropriate ML frameworks like scikit-learn and PyTorch, emphasizing reproducibility.
  • Use Case: A data scientist seeking to set up a new project needs to choose between S3 + Athena and Redshift for storing and analyzing large datasets. The Skill helps them understand the benefits and drawbacks of each option, leading to an informed decision.

Quick Start

Set up your data science project by considering storage solutions for operational and analytics workloads. Apply ETL practices using the lightest tool for the job. For machine learning, consider using scikit-learn or PyTorch and ensure reproducibility.

Frequently Asked Questions about data-scientist

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

FAQPage Schema
How do I choose between S3 with Athena and Redshift for data lake storage?

Selecting the right data storage solution involves evaluating cloud-based systems like S3, Athena, and Redshift to match your specific operational and analytics workload requirements.

What is the best way to structure ETL pipelines using AWS Glue and Lambda?

Structuring ETL pipelines effectively requires applying the lightest tool for the job, using AWS Glue and Lambda for heavy transformation workflows or DuckDB and Pandas for localized data processing.

When do I need to use PyTorch instead of scikit-learn for machine learning models?

You need PyTorch instead of scikit-learn when your machine learning models require deep learning capabilities, whereas scikit-learn handles traditional reproducible model frameworks effectively.

How do I ensure reproducibility in my machine learning and data ecosystems?

Ensuring reproducibility in machine learning and data ecosystems requires following best practices during ML model selection and maintaining consistent data storage and ETL processing workflows.

Does this data science guidance apply to cloud-based storage systems?

Yes, the data science guidance applies directly to cloud-based storage systems, requiring an understanding of platforms like S3 and Athena to configure robust data lake architectures.