Data

Calculates financial ratios from statement data for investment analysis. Handles multiple input formats (CSV, JSON, text, Excel) and provides ratio calculations with basic interpretations. Includes profitability, liquidity, leverage, efficiency, and valuation metrics.

Provides step-by-step guidance for migrating PostgreSQL tables to TimescaleDB hypertables, covering configuration, validation, and troubleshooting. Includes SQL examples for partition selection, chunk sizing, constraint handling, and performance testing with clear success criteria.

Provides Python client access to Data Commons API for querying public statistical data like population, economic indicators, and health statistics. Includes entity resolution, time-series queries, and knowledge graph exploration with clear examples for common workflows.

Provides checklists and templates for optimizing SQL in OLTP systems across PostgreSQL, MySQL, SQL Server, Oracle, and SQLite. Covers query analysis, indexing, schema design, migrations, backups, and high availability with clear decision trees and platform-specific commands.

This skill transforms Claude into a dbt architecture consultant focused on implementing medallion architecture patterns. It provides concrete folder structures, naming conventions, configuration strategies, and decision trees for organizing dbt projects. The guidance includes specific SQL templates, layer-specific rules, and practical examples for bronze/silver/gold layers.

A gateway skill that auto-activates for data development tasks and provides access to 9 specialized data skills covering batch processing, stream processing, and advanced dataflow systems. It uses a progressive loading approach where users first get the gateway, then can explore specific skills as needed.

This skill manually refreshes event data by re-scraping specific URLs, updating existing database records while handling URL normalization and multi-event pages. It provides clear feedback on what was found, scraped, and updated.

This skill provides structured data research workflows with SQL, Python, and web search capabilities. It follows a systematic approach from data planning to visualization, integrating multiple MCP tools for comprehensive data tasks. The checklist-driven methodology ensures quality and reproducibility.

Automates portfolio visualization by finding latest Fidelity and Tastytrade CSV files, processing positions, detecting synthetic longs, and generating HTML charts with options expiry reports. Opens results in browser with configurable search directories and quiet mode for scripting.

Provides concrete implementations for PostgreSQL, MongoDB, and Redis operations including connection setup, query optimization, caching patterns, and multi-database synchronization. Includes working code examples for rate limiting, distributed locking, and real-time analytics using Redis data structures.

Analyzes PostgreSQL databases to identify tables suitable for conversion to TimescaleDB hypertables. Provides SQL queries to examine table statistics, index patterns, and query behaviors. Includes scoring system to evaluate candidacy based on time-series characteristics and data patterns.

Provides programmatic access to the European Nucleotide Archive for retrieving DNA/RNA sequences, raw reads, and genome assemblies. Includes detailed API documentation, rate limiting guidance, and practical examples for genomics workflows. Covers multiple data formats and download methods.