The Data Science & Analytics Stack

Claude skills for data scientists and ML engineers cover the full analytical workflow — from raw SQL queries through exploration, validation, analysis, visualization, and dashboard delivery. This stack also includes senior-level ML and data engineering perspective for the work that goes beyond analysis into model building and pipeline design.

What these skills do

Senior Data Scientist

Get senior data science thinking on problem framing, methodology selection, statistical approach, and the judgment calls that determine whether an analysis will actually answer the question it’s supposed to answer. Useful when you’re designing a study, choosing between methods, or interpreting ambiguous results.

Senior Data Engineer

Design data pipelines and data infrastructure — schema design, ETL architecture, data modeling, and the engineering decisions that make downstream analysis easier and more reliable. Covers both batch and streaming approaches and the tradeoffs that matter for different data volumes and latency requirements.

Senior ML Engineer

Get senior ML engineering perspective on model selection, training pipeline design, feature engineering, evaluation methodology, and the production concerns that determine whether a model is actually deployable and maintainable.

Data Statistical Analysis

Run statistical analyses correctly — hypothesis testing, confidence intervals, regression analysis, experimental design, and the statistical rigor that separates conclusions you can trust from results that happen to look interesting.

Data SQL Queries

Write, review, and optimize SQL queries — complex joins, window functions, aggregation logic, query performance, and the SQL patterns that extract the right data efficiently from large tables.

Data Analyze

Structure and conduct data analyses — defining the question, choosing the approach, interpreting results, and the analytical workflow that produces conclusions rather than just numbers.

Data Explore Data

Run exploratory data analysis on a new dataset — distribution checks, correlation exploration, outlier identification, missing data assessment, and the EDA process that builds understanding before committing to a specific analysis approach.

Data Validate Data

Validate data quality — schema conformance checks, referential integrity, value range validation, consistency checks, and the data validation process that catches problems before they propagate into downstream analysis or models.

Data Build Dashboard

Design and build analytical dashboards — metric selection, layout design, filter logic, and the dashboard structure that gives stakeholders the data they need to make decisions without requiring them to pull their own analysis.

Data Create Viz

Create data visualizations — chart type selection, visual encoding, annotation, and the design decisions that make the data’s story clear rather than requiring the reader to interpret raw numbers.

Who this is for

• Data scientists and ML engineers designing analyses and building models
• Data analysts working with SQL, dashboards, and reporting for stakeholders
• Data engineers designing pipelines and data infrastructure for analytical workloads

For data work specifically in the context of AI systems, see the AI Engineer Stack. For financial data analysis specifically, see the Equity Research Stack.