Data Science & ML Agent Skills for Claude Desktop

Quantum ESPRESSO calculation skill for DFT simulations with pseudopotential management

Redistricting analysis in R using the redistverse ecosystem.

Robust statistical methods resistant to outliers

Describe and summarize the current dataset in memory.

Stata-to-Python translation for data analysis.

Bayesian probabilistic reasoning for prior specification, posterior computation, and belief updating

Scientific data analysis including data cleaning, exploratory data analysis (EDA), statistical testing, regression, and reporting.

Standard workflow order, tool selection matrix, and composition patterns for qsv CSV data wrangling

Decision tree analysis skill with expected value, risk analysis, and utility theory.

Automated decision tree construction skill for structuring complex decisions with probabilities, payoffs, and expected value calculations

Optimization without gradient information

Automates statistical distribution analysis and outlier detection for Excel datasets with high-resolution visualizations.

Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus

Classical end-to-end empirical analysis workflow in the traditional Python econometric stack — pandas + numpy + scipy + statsmodels +…

Compare your genome to George Church (PGP-1) and estimate ancestry composition via IBS and EM admixture

DAG and potential outcomes frameworks for causal mediation identification

Framework-independent LLM serving benchmark skill for comparing SGLang, vLLM, TensorRT-LLM, TokenSpeed, or another serving framework.

Parse SGLang/vLLM startup logs to explain GPU memory use and request capacity.

Open-source computer algebra system for symbolic computation

Build an operator-level compute template for an LLM and estimate FLOPs/MFU for a serving shape.

Use when an SGLang, vLLM, TensorRT-LLM, or TokenSpeed serving/model optimization task needs prior model-family PR evidence.