Skills for your AI
Guides process development scientists through statistical analysis, from data cleaning and test selection to interpretation and reporting. Use when preparing datasets, choosing or running statistical tests, building regression or ANOVA models, forecasting time
Runs an end-to-end statistical analysis workflow for research scientists, covering data cleaning, descriptive statistics, hypothesis testing, modeling, time series, experimental design, survival analysis, clustering, model comparison, and specialized methods.
Run hypothesis tests, analyze A/B experiment results, calculate sample sizes, and interpret statistical significance with effect sizes. Use when you need to validate whether observed differences are real, size an experiment correctly before launch, or interpre
Guides research associates through statistical modeling and prediction workflows, from data cleaning and feature engineering to model fitting, evaluation, forecasting, and domain-specific predictions. Use when the user needs data sources, variable selection, m
Collects, organizes, analyzes and interprets quality data with statistical methods such as descriptive statistics, control charts, capability indices, hypothesis tests, regression, Pareto, Six Sigma, DOE, FMEA, SPC and quality cost analysis. Use when an inspec
Trains and runs SentencePiece tokenizers on raw Unicode text for multilingual, CJK and pre-tokenization-free NLP. Use when the user wants to train a SentencePiece model, encode text to pieces or IDs, decode IDs to text, report model statistics, or decide wheth
Build features guided by data insights, A/B testing, and continuous measurement using specialized agents for analysis, implementation, and experimentation.
You are a data pipeline architecture expert specializing in scalable, reliable, and cost-effective data pipelines for batch and streaming data processing.
Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.
Expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business intelligence.
Transform raw data into compelling narratives that drive decisions and inspire action.
Give agents persistent structural memory of a codebase — navigate dependencies, track public APIs, and understand why connections exist without re-reading the whole repo.
Interactive visualization library. Use when you need hover info, zoom, pan, or web-embeddable charts. Best for dashboards, exploratory analysis, and presentations. For static publication figures use matplotlib or scientific-visualization.
Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger
