Skill UI

Provides programmatic access to the CZ CELLxGENE Census (61M+ cells) for querying standardized single-cell expression, metadata, embeddings, and stats across tissues and diseases, supporting scanpy and ML workflows.

Molfeat is a Python toolkit that converts SMILES/RDKit molecules into embeddings via 100+ calculators, transformers, and pretrained models for QSAR, screening, similarity search, and deep learning pipelines.

Use UMAP for fast nonlinear manifold reduction to produce embeddings that keep local and global structure, making it ideal for visualization, clustering preprocessing, supervised/parametric workflows, or high-dimensional feature engineering.

Umap provides uniform manifold approximation for dimension reduction and visualization, helping data scientists explore high-dimensional embeddings through interpretable 2D/3D layouts.

This skill provides programmatic access to the CZ CELLxGENE Census, a comprehensive collection of versioned public single-cell and spatial transcriptomics data. It enables efficient querying of population-scale cell metadata, gene expression slices, and embeddings without downloading entire datasets. Suitable for analyzing human, mouse, and other organism data across tissues and diseases. Integrates with Scanpy, AnnData, and TileDB-SOMA for large-scale analysis and machine learning workflows.

Use UMAP-learn for fast, scalable nonlinear dimensionality reduction, 2D/3D visualization embeddings, clustering preprocessing, supervised and semi-supervised UMAP, DensMAP, AlignedUMAP, and Parametric UMAP workflows, with guidance on key parameter tuning.

This tool ingests raw market data (OHLCV) for a specified symbol. It normalizes the data into relative OHLCV vectors, converts these vectors into high-dimensional embeddings, and then stores and indexes them using HNSW. This process prepares the data for fast, similarity-based pattern detection and advanced financial time series analysis.

This memory bridge ingests Claude Code's local auto-memory markdown files and structures them into AgentDB. It generates high-fidelity ONNX embeddings, handles deduplication using cosine similarity, and indexes the memories in a scalable namespace. This enables seamless, unified semantic search across all historical sessions and projects, significantly enhancing RAG capabilities.

This skill helps discover natural groupings within a large collection of semantic embeddings using the `ruvector` tool. It employs graph-based algorithms (Spectral/Louvain) to cluster code or data, revealing underlying themes, identifying outliers, and organizing vast vector sets. Ideal for analyzing codebases or large datasets to understand relationships between entries.

This skill utilizes hyperbolic space embedding (Poincare ball model) to represent complex data structures with inherent hierarchy, such as dependency trees, ontologies, or module taxonomies. Unlike standard Euclidean embeddings, hyperbolic space preserves hierarchical distances efficiently, allowing for accurate distance calculations (geodesic distance) that grow logarithmically with tree depth. It is ideal for advanced knowledge graph analysis and code architecture mapping.