skills.rest
davekim917
davekim917COMMUNITY
Explore all skills by this author →
GitHub

data-science

Standardize reproducible data science workflows for notebooks, experiments, and ML pipelines.

1|Updated Mar 6, 2026
Search Tags:#mlops#reproducibility#notebooks#data-science#experiments#model-evaluation
One-click install
npx skills add https://github.com/davekim917/bootstrap --skill data-science-davekim917
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-science
Source: https://github.com/davekim917/bootstrap/tree/main/plugins/domain/skills/data-science
Command: npx skills add https://github.com/davekim917/bootstrap --skill data-science-davekim917

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Data science teams often struggle with reproducibility, governance, and scalable patterns across notebooks, experiments, and ML pipelines. This Skill provides domain-specific patterns and checklists to standardize how data scientists build, validate, and deploy models, from data handling to experiment tracking and MLOps considerations. It helps teams maintain versioning, guardrails, and clear documentation throughout the lifecycle of data projects.

Core Features & Use Cases

  • Notebook storytelling and reproducible pipelines across model development and deployment
  • Experiment tracking, versioned data, and governance with MLflow, Weights & Biases, and feature stores
  • MLOps patterns for model serving, evaluation, and drift monitoring
  • Statistical testing, A/B experiments, and causal inference awareness for data-driven decisions

Quick Start

Open a new notebook project, set up a reproducible workflow following the data science practice guide, and run the first experiment with versioned data and tracked metrics.

Frequently Asked Questions about data-science

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

FAQPage Schema
How do I standardize reproducible data science workflows across notebooks and ML pipelines?▼

Reproducible data science workflows are standardized using domain-specific patterns, checks, and templates for data handling, versioning, and leakage prevention across notebooks and Python scripts.

What's the best way to track experiments and version data in model development?▼

Experiment tracking and versioned data are managed using integration patterns for MLflow, Weights & Biases, and feature stores to maintain governance and clear documentation throughout model development.

How do you prevent data leakage during feature engineering and model evaluation?▼

Data leakage prevention during feature engineering and model evaluation is handled through built-in guardrails, standardized checks, and templates applied throughout the data handling and pipeline process.

Does this approach work for both research notebooks and production MLOps contexts?▼

Yes, the standardized patterns apply to both research and production contexts, providing MLOps patterns for model serving, evaluation, drift monitoring, and A/B testing alongside notebook storytelling.

Can I use MLflow and feature stores for governance in my analytics projects?▼

Yes, MLflow and feature stores are supported for governance, experiment tracking, and versioned data management to maintain clear documentation throughout the lifecycle of analytics and data projects.

Why do I need standardized patterns for A/B testing and causal inference?▼

Standardized patterns for A/B testing and causal inference provide statistical testing awareness and governance guardrails, ensuring data-driven decisions are reproducible and validated across experiments.

Related Skills

Explore More Data & Analytics Skills→
panicPaulpanicPaul
5

jupyter-to-marimo

Convert Jupyter notebooks into marimo-ready Python scripts.

Community
Intermediate
ouakarouakar

ai-engineer

Design and deploy production AI/ML systems with MLOps pipelines and monitoring.

Community
Advanced
george11642george11642
2

ml-data-engineering

Orchestrate end-to-end ML data pipelines from ingestion to deployment.

Community
Advanced
efiadmefiadm

senior-data-scientist

Design experiments and evaluate machine learning models using Python, R, and SQL.

Community
Advanced