Data Science & ML Agent Skills for Codex CLI

Statistical process control chart creation and analysis skill with control limit calculation and special cause detection.

CosmoSIS cosmological parameter estimation skill for MCMC sampling and likelihood analysis

Automated search for counterexamples to mathematical conjectures

Create publication-quality visualizations with Python.

Advanced skill for crystallographic structure analysis and determination including space group identification, atomic position refinement…

Expert skill for CUDA Graph capture and optimization for reduced launch overhead.

Official NVIDIA-authored guidance for cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O and…

End-to-end R data analysis for the sewage project.

End-to-end R data analysis workflow from exploration through regression to publication-ready tables and figures

Track dataset lineage, transformation steps, merge logic, and reproducibility risks in Stata workflows.

Data science methodology for Python research: EDA, validation, causal inference (IV, DiD, RD, synthetic control), clustering/PCA/UMAP…

Skill for managing data versions and provenance

Guide for debugging distributed training issues in AReaL.

AI-powered demand prediction skill using historical data, market signals, and external factors for improved forecast accuracy

Discrete event simulation skill for modeling and analyzing complex systems with stochastic processes.

Statistical distribution fitting skill for input modeling in simulation and analysis.

Convert narrative technical documents into grounded Mathematical Problem Specifications with variables, constraints, objectives, and…

Build and run LLM-powered data processing pipelines with DocETL.

Captures tool versions, packages, and kernel info as a reproducibility record in notes/.

emcee MCMC skill for Bayesian parameter estimation and posterior sampling in physics applications

Run a structural estimation pipeline — routes to /workflows:work with estimation context from empirical-playbook