Skill UI

Guides building, fitting, and validating Bayesian models with PyMC 5+, covering hierarchical structures, MCMC (NUTS), variational inference, diagnostic checks, model comparison (LOO/WAIC), and prediction steps for principled uncertainty quantification.

A foresight agent that runs a rigorous 12-step pipeline combining Claude’s qualitative intelligence with Python’s deterministic arithmetic to analyze high-stakes future scenarios, infer reasonable horizons, and surface quantitative signals for prediction requests.