Skill UI

Combines ESM3 and ESM C protein language models to generate sequences, predict structures, condition functions, and extract embeddings via local or Forge API inference for protein design and engineering workflows.

Geniml builds machine learning workflows around BED and scATAC datasets to learn embeddings for regions, metadata, and cells, enabling similarity searches, clustering, consensus peaks, and downstream analysis of genomic intervals.

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.

Comprehensive guide to LLM Operations (LLMOps). Covers advanced topics like Retrieval-Augmented Generation (RAG), vector database management (Pinecone, Chroma), embeddings, fine-tuning, prompt engineering, and cost optimization. Essential for bridging the gap between AI prototypes and reliable, scalable, production-grade AI systems.

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 the esm Python SDK with ESM3 and ESMC for protein sequence generation, embeddings, function conditioning, structure prediction, inverse folding, and Forge/Biohub inference workflows.

Unified Python library with 100+ molecular featurizers and pretrained embeddings. Converts SMILES or RDKit molecules into ML-ready numerical features for QSAR modeling, virtual screening, similarity search, and deep learning.

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 guide demonstrates how to build advanced AI agents using Anthropic's Tool Use (Function Calling) feature. It allows Claude to dynamically determine when external actions are needed, such as querying databases, calling APIs, or reading files. The pattern involves sending the user query, receiving a `tool_use` request, executing the corresponding function in your code, and submitting the result back to Claude for a final, coherent response. Essential for building multi-step, agentic workflows.

A comprehensive guide to configuring robust CI/CD pipelines for Cohere API v2 applications. This skill covers setting up automated unit tests (mocked responses) and critical integration tests (real API calls) within environments like GitHub Actions. It ensures the stability and reliability of Cohere-powered features such as Chat, Embeddings, and Rerank across development cycles.