skills.rest
Tgoldi
TgoldiCOMMUNITY
Explore all skills by this author →
GitHub

senior-data-scientist

Design experiments, engineer features, and evaluate predictive models with Python and SQL.

1|Updated May 10, 2026
Search Tags:#python#data science#experiment design#feature engineering#model evaluation#a/b testing#statistical analysis
One-click install
npx skills add https://github.com/Tgoldi/claude-skills --skill senior-data-scientist-tgoldi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: senior-data-scientist
Source: https://github.com/Tgoldi/claude-skills/tree/main/senior-data-scientist
Command: npx skills add https://github.com/Tgoldi/claude-skills --skill senior-data-scientist-tgoldi

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? It provides structured guidance and starter tooling for data science work such as A/B test design, feature engineering, and model evaluation, reducing the effort of setting up these workflows from scratch. ## Core Features & Use Cases - Experiment Design: Plan and structure A/B tests and causal inference studies using the experiment designer script and reference frameworks. - Feature Engineering: Build feature pipelines following documented patterns for scalable data processing. - Model Evaluation: Run evaluation workflows covering metrics, monitoring, and deployment readiness. - Use Case: A data scientist preparing a product experiment can use the experiment design references to define hypotheses, sample sizes, and success metrics, then scaffold the analysis pipeline with the provided scripts. ## Quick Start Ask the assistant to design an A/B test for a new feature rollout, including hypothesis, metrics, and analysis plan.

Frequently Asked Questions about senior-data-scientist

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

FAQPage Schema
How do I design an A/B test with this skill?▼

Use the experiment_designer.py script with input and output paths to scaffold the experiment workflow, and consult references/experiment_design_frameworks.md for guidance on hypotheses, metrics, and design patterns.

What tools does this skill cover for data science work?▼

The skill references Python, SQL, R, Scikit-learn, PyTorch, TensorFlow, XGBoost, Spark, Airflow, and dbt. It also covers deployment with Docker and Kubernetes and monitoring with MLflow and Prometheus.

Does the skill include working model training code?▼

The scripts in scripts/ are scaffolding templates with argument parsing, logging, and validation structure, but the core execution logic is a placeholder. You need to implement the actual processing logic for your use case.

Can I use this skill for causal inference analysis?▼

Yes, the skill description covers causal inference and statistical modeling, and the reference documents outline design principles. However, specific causal inference implementations must be added to the provided script templates.

What are the limitations of the provided scripts?▼

The three scripts share an identical boilerplate structure with stub _execute methods returning success placeholders. They provide CLI scaffolding and logging but require custom implementation before producing real analytical results.

Related Skills

Explore More Data & Analytics Skills→
finsilabsfinsilabs
44

ecommerce-data-warehouse

Build e-commerce data warehouses with star-schema, ETL, and dbt.

Official
Advanced
duylinhdang1998duylinhdang1998

ml-infrastructure

Build and deploy ML training pipelines with Docker, Kubernetes, and FastAPI.

Community
Advanced
mkgs-databricks-demosmkgs-databricks-demos
1

querying-mlflow-metrics

Fetch aggregated MLflow metrics with configurable server URL, experiment IDs, and aggregations.

Official
Intermediate
lxh755818-botlxh755818-bot

weights-and-biases

Track ML experiments, hyperparameters, and model versions with Weights & Biases.

Community
Advanced