Pymc

This gives Claude the ability to build and validate Bayesian models using PyMC's modern API. It covers the full workflow: prior and posterior predictive checks, MCMC sampling with NUTS, model diagnostics (R-hat, ESS, divergences), and model comparison via LOO and WAIC. The included templates handle common patterns like hierarchical models with non-centered parameterization, which is critical for avoiding sampling issues. Use this when you need proper uncertainty quantification, want to work with hierarchical data structures, or need to handle missing data in a principled way. The diagnostic scripts are helpful since convergence checking is non-negotiable in Bayesian workflows. It assumes you understand why you're reaching for Bayesian methods rather than maximum likelihood approaches.