Skill UI

Transforms raw datasets into charts, plots, and graphs by analyzing structure, picking suitable visualization types, and rendering them clearly so users can request visualizations or explore patterns and relationships.

This comprehensive guide details strategies for migrating enterprise data platforms to Databricks. It provides PySpark examples for discovery, schema mapping (converting types from Hadoop, Snowflake, etc.), and executing robust data transfer methods like SYNC, DEEP CLONE, and CTAS. Use this when moving data from legacy sources like Hadoop, Snowflake, or Redshift to a modern Delta Lake environment.

This comprehensive checklist guides the deployment of Databricks data pipelines and jobs to a production environment. It covers critical stages including pre-deployment security hardening (Service Principals, Unity Catalog), validating infrastructure (cluster types, autoscaling), ensuring code quality (unit/integration tests, Delta Lake best practices), executing controlled deployment, and performing post-deployment health checks and monitoring setup. Ideal for CI/CD pipelines and go-live procedures.

Master the implementation of Firecrawl webhooks for robust, real-time handling of asynchronous crawling and batch scraping jobs. Instead of inefficiently polling the crawl status, configure webhook endpoints to receive instant POST events (e.g., `crawl.page`, `crawl.completed`). This guide covers event types, signature verification using HMAC-SHA256, and processing streamed data for building advanced data pipelines.

This guide provides advanced patterns and best practices for optimizing Apache Spark jobs. It covers critical areas like effective partitioning, memory tuning, minimizing data skew, and optimizing different types of joins (broadcast, bucket). Use this when troubleshooting slow, large-scale data processing workflows or needing to scale Spark pipelines efficiently and reliably.

Access NCBI Gene data via E-utilities or Datasets API to look up genes by symbol or ID, retrieve RefSeqs, GO terms, chromosomal locations, phenotypes, and run batch workflows for annotation pipelines.

A comprehensive skill for managing the entire lifecycle of datasets on the Hugging Face Hub. It allows users to initialize, configure, and stream updates for datasets of various types (Chat, Text Classification, Tabular). Crucially, it extends data handling capabilities by enabling powerful SQL-based querying and transformation directly on Hub datasets using the DuckDB engine, facilitating advanced data exploration and pipeline creation.

Analyzes TCM constitution data to identify primary and mixed constitution types, assess traits and risks, and generate personalized wellness advice with links to nutrition, exercise, sleep, and trend tracking.

Query the PrimeKG precision medicine knowledge graph to explore genes, drugs, diseases, phenotypes, and their relationships, supporting drug discovery, repurposing, and phenotype analysis through programmatic scripts.

This tool analyzes ML experiment results from various paths (JSON/CSV). It computes comprehensive statistics, builds detailed comparison tables based on model types and hyperparameters, and generates actionable insights. Use it when you need to interpret raw experimental data, compare different model runs, or determine the next steps for research.

This skill provides methods for detecting covert data exfiltration channels using DNS tunneling. It analyzes DNS query patterns, including subdomain entropy, query volume anomalies, oversized TXT/CNAME records, and unusual query types, to identify potential data leakage attempts from compromised networks. Ideal for threat hunting and building advanced passive DNS monitoring capabilities.

Generate publication-quality figures and comparison tables from experiment results for academic papers. Automatically selects plot types from data and produces vector PDFs at 300 DPI.