This skill enables querying the ChEMBL database, a manually curated collection of over 2 million bioactive molecules maintained by the European Bioinformatics Institute. It supports compound searches, target information retrieval, bioactivity data queries (IC50, Ki, EC50), similarity/substructure searches, and drug discovery workflows for medicinal chemistry research.

This skill provides access to the BRENDA enzyme database, the world's most comprehensive enzyme information system. It enables researchers to retrieve kinetic parameters (Km, kcat, Vmax), reaction equations, substrate specificities, and optimal conditions for over 45,000 enzymes. The skill also supports metabolic pathway construction and retrosynthetic analysis for enzyme engineering applications.

This skill enables access to the AlphaFold Protein Structure Database, providing code examples and documentation for retrieving AI-predicted 3D protein structures. It supports querying by UniProt ID, downloading coordinate files (PDB/mmCIF), analyzing confidence metrics (pLDDT, PAE), and bulk data access via Google Cloud for structural biology and drug discovery workflows.

A documentation skill that teaches how to use Zarr, a Python library for storing large N-dimensional arrays with chunking and compression. It covers array creation, storage backends (local, cloud, memory), compression codecs, parallel computing with Dask, and integration with NumPy and Xarray for scientific computing workflows.

A comprehensive reference skill for Vaex, a high-performance Python library for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Covers DataFrame operations, data loading, filtering, aggregations, machine learning pipelines, visualization, and performance optimization strategies.

This skill provides comprehensive documentation and guidance for using UMAP (Uniform Manifold Approximation and Projection), a fast dimensionality reduction technique for visualization and machine learning. It covers installation, parameter tuning, supervised/unsupervised learning, clustering preprocessing with HDBSCAN, and advanced features like Parametric UMAP and inverse transforms.

TorchDrug is a documentation skill that provides comprehensive guidance for using the TorchDrug PyTorch library in drug discovery and molecular science. It covers graph neural networks for molecules and proteins, including molecular property prediction, protein modeling, knowledge graph reasoning, molecular generation, and retrosynthesis planning with 40+ curated datasets and 20+ model architectures.

This skill provides comprehensive guidance for PyTorch Geometric (PyG), a library for developing Graph Neural Networks. It covers graph creation, GNN architectures (GCN, GAT, GraphSAGE, GIN), node/graph classification, molecular property prediction, and large-scale graph learning with extensive reference documentation and utility scripts.

A comprehensive reference skill for the statsmodels Python library, covering statistical modeling techniques including linear regression, generalized linear models, discrete choice models, time series analysis, and statistical diagnostics. Provides code examples, best practices, and detailed explanations for econometrics and rigorous statistical inference.

A comprehensive reference skill for reinforcement learning with Stable Baselines3. It provides algorithm selection guides, training templates, custom environment creation tutorials, callback documentation, and vectorized environment usage patterns for efficient RL agent development.

This skill provides comprehensive documentation and examples for using the seaborn Python library for statistical data visualization. It covers core plotting functions (scatter, line, distribution, categorical, regression, and matrix plots), the modern objects interface API, multi-plot grids, theming, and best practices for creating publication-quality figures.

A comprehensive documentation skill for scvi-tools, a Python framework for probabilistic deep generative models in single-cell genomics. It provides guidance on models for RNA-seq, ATAC-seq, multimodal data integration, spatial transcriptomics, and specialized modalities like methylation and cytometry analysis.

A comprehensive reference skill for scikit-bio, a Python bioinformatics library. Provides documentation and code examples for biological sequence manipulation, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination analysis (PCoA, CCA), statistical tests (PERMANOVA, ANOSIM), and microbiome data processing with FASTA/BIOM file format support.

This skill provides a comprehensive toolkit for analyzing single-cell RNA-seq data using the scanpy library. It enables quality control, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, marker gene identification, cell type annotation, and publication-quality visualizations.

RDKit is a comprehensive cheminformatics skill that guides users through molecular analysis tasks including reading/writing chemical structures (SMILES, SDF), calculating molecular descriptors (LogP, TPSA, molecular weight), generating fingerprints for similarity searching, and performing substructure matching. It includes ready-to-use Python scripts for drug-likeness screening, similarity searches, and functional group filtering.

A comprehensive reference skill for QuTiP (Quantum Toolbox in Python), providing documentation for simulating open quantum systems, master equations, and quantum optics. Includes detailed guides for time evolution solvers, visualization tools, and advanced features like Floquet theory and HEOM methods.

This skill provides extensive guidance for working with IBM's Qiskit quantum computing framework. It covers building quantum circuits, running simulations, executing on real IBM Quantum hardware, and implementing quantum algorithms like VQE, QAOA, and Grover's search. The skill includes reference documentation for setup, primitives, transpilation, visualization, and various quantum applications in chemistry, optimization, and machine learning.

This skill provides comprehensive documentation and templates for PyTorch Lightning, a framework that organizes PyTorch code for scalable deep learning. It includes ready-to-use templates for LightningModules and DataModules, Trainer configurations for various scenarios (single GPU, multi-GPU, FSDP, DeepSpeed), and detailed guides for callbacks, logging, distributed training, and best practices.

PyTDC (Therapeutics Data Commons) provides AI-ready datasets and benchmarks for drug discovery and development. It offers curated datasets spanning ADME, toxicity, drug-target interactions, and molecular generation with standardized evaluation metrics and meaningful data splits for therapeutic machine learning applications.

Pysam is a documentation skill for genomic data analysis using Python. It provides comprehensive reference guides for reading and writing sequencing alignment files (SAM/BAM/CRAM), genetic variant files (VCF/BCF), and sequence files (FASTA/FASTQ), along with practical code examples for bioinformatics workflows like coverage analysis and variant filtering.

PufferLib is a high-performance reinforcement learning framework optimized for fast parallel training. It provides templates for creating custom environments, training scripts with PPO, and seamless integration with popular RL frameworks like Gymnasium and PettingZoo, achieving millions of steps per second.

PyOpenMS is a comprehensive documentation skill for computational mass spectrometry using Python. It provides guidance for proteomics workflows including feature detection, peptide identification, protein quantification, and LC-MS/MS data processing pipelines.

This skill provides comprehensive guidance for using pymoo, a Python framework for multi-objective optimization. It covers evolutionary algorithms (NSGA-II, NSGA-III, MOEA/D), benchmark problems (ZDT, DTLZ), constraint handling, custom problem definition, and multi-criteria decision making for selecting preferred solutions from Pareto fronts.

A comprehensive Bayesian modeling skill built on PyMC 5.x that enables probabilistic programming with MCMC sampling (NUTS), variational inference, and hierarchical models. Includes diagnostic utilities for convergence checking, model comparison using LOO/WAIC, and templates for common model patterns like linear regression and multilevel models.

Pymatgen is a comprehensive Python library for materials analysis that enables working with crystal structures, computing phase diagrams, analyzing electronic structure data, and accessing the Materials Project database. It supports 100+ file formats and integrates with major computational chemistry codes like VASP, Gaussian, and Quantum ESPRESSO.

PyLabRobot is a vendor-agnostic laboratory automation skill that helps you control liquid handling robots (Hamilton, Opentrons, Tecan), plate readers, pumps, heater shakers, and other lab equipment through a unified Python interface. It includes simulation capabilities for testing protocols without physical hardware.

PyDESeq2 is a bioinformatics skill for analyzing bulk RNA-seq count data to identify differentially expressed genes. It provides a complete workflow from data loading through statistical testing (Wald tests with FDR correction), including support for single-factor and multi-factor experimental designs, optional LFC shrinkage, and visualization with volcano/MA plots.

A comprehensive reference skill for the Polars DataFrame library, providing documentation on data operations, pandas migration patterns, I/O operations, and performance best practices. Designed for users working with in-memory data processing tasks.

This skill provides comprehensive guidance for using Plotly, a Python library for creating interactive, publication-quality data visualizations. It covers 40+ chart types including scatter plots, bar charts, 3D surfaces, and geographic maps, along with styling, export options, and Dash integration for web applications.

This skill enables AI-powered web searches using Perplexity models via OpenRouter, providing real-time answers with source citations. It's ideal for finding current information, scientific literature, and facts beyond Claude's training data cutoff, supporting multiple model tiers from cost-effective basic searches to advanced multi-step reasoning.