Skill UI

This skill guides the process of transforming complex, raw data into compelling, actionable narratives. It covers the core structure (Setup, Conflict, Resolution), narrative arcs, and the three pillars (Data, Narrative, Visuals) needed to create high-impact presentations for executives, investors, and non-technical stakeholders. It ensures insights drive clear decisions.

A comprehensive guide to setting up a minimal working example on Databricks. This skill covers creating a development cluster, uploading and executing notebooks (Python SDK), running tasks as jobs, and setting up a Serverless SQL Warehouse. It is ideal for new users or initializing a basic data engineering project.

A comprehensive runbook designed for on-call engineers to manage Databricks incidents, outages, and major job failures. It provides structured procedures for immediate triage, decision tree guidance (covering cluster failures, code errors, and data quality issues), and steps for evidence collection and postmortem documentation, ensuring rapid and systematic incident resolution.

A comprehensive guide detailing optimization techniques for Databricks environments. It covers optimal cluster sizing for various workloads (ETL, ML, Streaming), advanced Spark configurations (AQE, memory management), and deep data optimization strategies for Delta Lake, including Z-Ordering and Liquid Clustering. It also provides methods for query plan analysis and join optimization.

This guide outlines a production-ready lakehouse architecture using Unity Catalog, Delta Lake, and the Medallion pattern. It provides best practices for organizing Databricks workspaces, implementing three-level governance, defining compute strategies, and adopting CI/CD best practices with Asset Bundles for robust team collaboration.

A comprehensive guide to implementing best practices for security within Databricks. Learn how to manage secrets using scoped storage, enforce the principle of least privilege via Unity Catalog grants, audit API tokens, and apply advanced data protection techniques like column-level masking and row-level security for enhanced data governance and compliance.

This comprehensive guide provides structured steps and code examples for upgrading Databricks Runtime versions and performing critical data migrations. It covers best practices for version compatibility checking, transitioning from Hive Metastore to Unity Catalog using methods like SYNC and CTAS, and updating deprecated API endpoints, ensuring a smooth platform evolution for data pipelines.

A guide to production-ready patterns for dbt (data build tool). It covers essential practices for robust data pipeline development, including model organization (staging, intermediate, marts), implementing advanced testing strategies, ensuring data quality, and optimizing incremental processing for large datasets.

Automated guidance for configuring and applying early stopping callbacks across ML training workflows, covering best practices, code generation, and validation for PyTorch, TensorFlow, and scikit-learn experiments.

A comprehensive workflow for executing advanced, semantic web searches using Exa. This tool moves beyond simple keyword matching, enabling deep context retrieval by understanding the intent behind the query. Key features include RAG context retrieval, content extraction (summaries, highlights, full text), and robust filtering by date range, specific domains, and content categories. Ideal for building knowledge base search features and complex research pipelines.

A comprehensive tool for querying and analyzing deep blockchain data across multiple EVM-compatible networks, including Ethereum, Polygon, Arbitrum, and Optimism. It supports tracking transactions by hash, checking address balances, inspecting blocks, and resolving ERC-20 token holdings. Ideal for crypto analysts, developers, and researchers requiring programmatic, detailed insights into on-chain financial activity and protocol interactions.

Automates guidance on assessing feature importance for machine learning training, covering data prep, model training, tuning, and experiment tracking while generating production-ready code, configurations, and validation instructions for best-practice compliance.