Predict molecular properties like solubility, toxicity, and binding affinity using DeepChem. Train graph neural networks or use pretrained models like ChemBERTa for drug discovery and materials science applications.

Access global statistical data from Data Commons including demographics, economics, health, and environmental indicators. Query population figures, GDP, unemployment rates, and geographic relationships using Python client methods.

Process datasets larger than available RAM using parallel computing. Transform single-machine pandas and NumPy workflows to run across multiple cores or distributed clusters without rewriting your code.

Metabolic modeling requires specialized knowledge of constraint-based reconstruction and analysis methods. COBRApy provides a comprehensive Python interface for flux balance analysis, gene knockout studies, and production envelope calculations for systems biology research.

Finding relevant clinical trials requires searching a large registry database. This skill provides a Python interface to query ClinicalTrials.gov API v2 to search trials by condition, drug, location, or sponsor and retrieve detailed study information.

Clinical documentation requires precision and regulatory compliance. This skill provides templates and validation tools for case reports, diagnostic reports, clinical trial documentation, and patient notes following HIPAA, FDA, and ICH-GCP standards.

Access the ChEMBL database to search compounds by structure and properties. Retrieve bioactivity measurements, find inhibitors, and perform structure-activity relationship studies for drug discovery research.

Access comprehensive enzyme kinetic data from the worlds largest enzyme database. Find Km values, reaction equations, organism-specific parameters, and substrate specificity data for biochemical research and metabolic engineering.

Query 40+ biological databases including UniProt, KEGG, and ChEMBL with a consistent Python API. Simplifies cross-database analysis and identifier conversion for bioinformatics research.

Automate laboratory workflows and manage biological data by integrating with the Benchling R&D platform. Access DNA sequences, protein data, inventory, and electronic lab notebooks through the Python SDK or REST API.

Gene regulatory network inference identifies transcription factor-target gene relationships from transcriptomics data. Arboreto provides scalable implementations of GRNBoost2 and GENIE3 algorithms that process both bulk and single-cell RNA-seq data on local machines or distributed clusters.

AnnData provides a standardized data structure for annotated matrices used in single-cell genomics. This skill enables creating, reading, writing, and manipulating .h5ad files with full support for metadata, embeddings, and the scverse ecosystem.

Time series data requires specialized algorithms beyond standard machine learning. Aeon provides scikit-learn compatible APIs for classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search on temporal data.

Get expert help writing complex T-SQL queries, stored procedures, and performance optimizations for Microsoft SQL Server. Covers advanced patterns like CTEs, window functions, PIVOT, and MERGE statements.

This skill enables Claude, Codex, and Claude Code users to generate professional AI videos by building storyboards, creating reference images, and submitting video generation tasks to Seedance 2.0 API. It streamlines the complex multi-step video creation process into a simple, automated workflow.

Home Assistant configuration files require precise YAML syntax and proper structure. This skill provides validation tools, example configurations, and best practices for automations, scripts, templates, blueprints, and Lovelace dashboards.

Users need quick insights into text content without manual counting. This tool automatically calculates word count, character count, sentence count, and reading time for any text input.

Slow DataFusion queries waste resources and time. This skill analyzes SQL and DataFrame operations to identify performance issues and suggest concrete optimizations for predicate pushdown, partition pruning, column projection, and join ordering.

Organizations need systematic ways to record and categorize expense receipts for accurate financial tracking. This skill provides documented workflows for manual receipt entry, OCR scanning integration, and database patterns for managing expense records in MySQL.

Receipt scanning requires accurate OCR extraction and database integration. This skill provides complete guidance for parsing receipt images, debugging extraction errors, and building reliable expense tracking workflows with Google Gemini AI.