Skill UI

Guides you through building custom Semgrep rules with a testing-first workflow, AST analysis, and taint-mode preference to catch vulnerabilities or bug patterns while steering clear of overly broad or unverified shortcuts.

Provides Pythonic probabilistic deep models for single-cell genomics, covering RNA, ATAC, multimodal, and spatial data—all with batch correction, uncertainty-aware differential expression, and scanpy-friendly APIs.

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.

Creates custom Semgrep rules focusing on vulnerabilities and bug patterns, enforcing a strict workflow of documentation reading, test-first development, taint or pattern modes, and iterative validation before optimization; ideal when building new detections for security and coding standards.