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.

Manual text extraction from images and screenshots is slow and error-prone. This skill automates OCR processing through the Scanlume API, delivering structured text, Markdown, HTML, or table data from image files.

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.

Writing efficient database queries requires deep knowledge of SQL and NoSQL patterns. This skill generates optimized queries with proper parameterization and explains execution strategies for better performance.

JSON data often comes in complex nested structures that are hard to work with. This skill provides expert guidance for parsing, transforming, validating, and converting JSON for any use case.

Poor data quality leads to system failures and bad decisions. This skill validates data against JSON schemas, database schemas, and custom business rules to catch errors early. It also detects duplicates, outliers, and format issues while generating detailed quality reports.

CSV files often contain messy data that needs cleaning and transformation. This skill provides comprehensive tools and examples for parsing, cleaning, and analyzing CSV data efficiently.

Transform raw data into compelling visual stories. Create bar charts, line graphs, scatter plots, heatmaps, and interactive dashboards with professional styling.

Database queries written with for-loops are slow and create maintenance problems. This skill provides guidelines for using SQLAlchemy bulk operations and repository patterns to write fast, maintainable database code.

Large document sets exceed context limits. Process corpora into knowledge graphs for efficient multi-hop reasoning and persistent querying across thousands of documents.

Revenue teams struggle with disconnected systems, undefined handoffs, and poor data hygiene that leak pipeline. This skill provides battle-tested frameworks for lead scoring, routing, CRM automation, and metrics dashboards that align marketing, sales, and customer success.

AI model names change frequently. This skill fetches current model lists from Anthropic, OpenAI, Gemini, and Ollama, then classifies them by performance tier for optimal model selection.

Working with Excel files manually is time consuming and error prone. This skill automates spreadsheet creation, editing, and formula recalculation using standard Python libraries.

Writing R code with outdated patterns wastes time and creates technical debt. This skill provides current best practices for tidyverse, rlang metaprogramming, and package development so you can write clean, efficient R code.