Deep generative models for single-cell omics. Use when you need probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, or multi-modal integration (TOTALVI, MultiVI). Best for advanced modeling, batch effects, multimodal data. For standard analysis pipelines use scanpy.
8.3
Rating
0
Installs
Machine Learning
Category
Excellent skill for deep generative modeling in single-cell omics. The description clearly explains when to use scvi-tools vs. scanpy, making invocation straightforward. Task knowledge is comprehensive with complete code examples, unified API patterns, and extensive references for specialized models across RNA-seq, ATAC-seq, multimodal, and spatial data. Structure is well-organized with a concise SKILL.md that provides overview and workflow while delegating detailed model documentation to reference files. Novelty is high—probabilistic batch correction, uncertainty quantification, and complex multimodal integration require specialized deep learning expertise that would be token-intensive and error-prone for a CLI agent alone. Minor improvement possible in explicitly listing all reference file contents in the overview section.
K-Dense-AI
Skill Author
Loading SKILL.md…
