Mass spectrometry generates complex spectral data that requires specialized processing. Matchms provides a complete Python toolkit for loading, filtering, comparing, and identifying compounds from spectral data with established similarity metrics.

Scientific computing tasks require appropriate hardware resources to run efficiently. This skill automatically detects CPU cores, GPU availability, memory, and disk space to recommend optimal computational strategies and library choices.

Analyzing geographic data requires specialized tools for handling vector geometries, coordinate systems, and spatial relationships. GeoPandas extends pandas to enable spatial operations on geometric types for efficient geospatial data manipulation.

Access comprehensive FDA regulatory data including drugs, medical devices, food recalls, and substance information. Search adverse events, labeling, approvals, and recalls using the official openFDA API.

Scientists need to understand the structure and quality of diverse scientific data files before analysis. This skill automatically detects file types, extracts metadata, performs statistical analysis, and generates comprehensive markdown reports for 200+ scientific formats.

Manual Excel analysis takes hours of repetitive work. This skill provides ready-to-use pandas patterns for reading, analyzing, and visualizing spreadsheet data in seconds.

Managing genomics data and building analysis pipelines on DNAnexus requires learning complex APIs and patterns. This skill provides comprehensive guidance for app development, data management, and workflow execution on the DNAnexus cloud platform.

Predict 3D binding poses between proteins and small molecule ligands using state-of-the-art diffusion models. Generate confidence-scored predictions for structure-based drug discovery and virtual screening campaigns.

Process next-generation sequencing data for ChIP-seq, RNA-seq, and ATAC-seq experiments. Convert BAM files to normalized coverage tracks and generate publication-quality visualizations including heatmaps, correlation plots, and profile graphs.

Working with molecular data in Python requires complex RDKit code. Datamol provides simple functions for SMILES parsing, property calculation, and compound analysis.

Accessing demographic, economic, and health data from multiple global sources requires navigating complex APIs. This skill provides complete guidance for using the Data Commons Python client to query population statistics, unemployment rates, GDP figures, and other public datasets through a unified knowledge graph.

Processing large datasets that exceed available RAM causes memory errors and slow performance. Dask provides parallel computing abstractions that scale pandas and NumPy operations to handle terabyte-scale data on laptops or clusters.

Working with biological sequences, protein structures, or genomic data requires specialized tools. This skill provides comprehensive Biopython documentation to help you parse FASTA files, query NCBI databases, run BLAST searches, analyze protein structures, and perform phylogenetic analysis using Python.

Managing large annotated data matrices for single-cell genomics analysis is complex. This skill provides comprehensive documentation for the AnnData library, enabling efficient handling of h5ad files, metadata annotations, and integration with the scverse ecosystem.

New team members need clear instructions to request Snowflake access. This skill provides step-by-step guidance for generating RSA keys, submitting access requests, and connecting to Snowflake via CLI, Python, or web interface.

Database mistakes cause slow applications and data loss. This skill provides comprehensive review checklists for schema design, queries, ORM patterns, and migrations.

Creating realistic test data for database development is time-consuming and error-prone. This skill helps you generate properly structured seed data with realistic relationships, constraints, and scenarios for any database system using Faker libraries and ORM tools.

Understanding complex database schemas takes time and can lead to mistakes. This skill helps you generate professional ERDs, Mermaid diagrams, and documentation from any database schema source instantly.

Transform raw data into polished markdown and HTML reports. Create documents with charts, tables, executive summaries, and actionable insights from any dataset.

Slow database queries impact application performance and user experience. This skill provides expert guidance on analyzing query execution plans, identifying performance bottlenecks, and implementing optimizations like proper indexing and query restructuring.