Skill UI

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.

This skill automatically generates an interactive SQL Notebook designed to validate changes in dbt models or snapshots. It processes changes identified from a GitHub PR or local repository, generating comparison queries that compare 'before' (production) and 'after' (development) data states. It is essential for embedding data observability and quality checks into CI/CD pipelines.

The ETE Toolkit is a powerful Python library designed for analyzing, manipulating, comparing, and visualizing phylogenetic trees stored in Newick or Nexus formats. It allows users to perform topology edits, calculate phylogenetic distances (e.g., Robinson-Foulds), detect evolutionary events, and query external taxonomic databases like NCBI/GTDB. Note that this tool analyzes existing trees; it is not used for inferring trees from raw sequences.

A comprehensive guide and toolkit for optimizing Hex platform costs. This resource details strategies for reducing compute expenditure by auditing seat licenses, consolidating data connections, and optimizing notebook run schedules. It includes code examples for implementing result caching and usage monitoring to prevent unexpected billing spikes.

This skill scrapes Substack Notes analytics by extracting key engagement metrics (likes, comments, restacks) and content details. It overcomes the lack of a public API, allowing users to analyze performance data from a specified date range into a highly formatted, actionable Excel spreadsheet. The output includes detailed per-note data, total engagement calculations, and summary statistics.

Execute arbitrary PySpark or pure Python code directly on Fabric Spark compute using the Livy API. This method creates ephemeral sessions without generating persistent notebook artifacts. It provides full read/write access to lakehouse Delta tables, making it ideal for agent-driven ETL pipelines, quick data transformations, or analyses where session cleanup is critical. Users must manage the session lifecycle (create, run, and delete).

A comprehensive guide on querying data stored in Fabric's OneLake using DuckDB. This skill supports two operational modes: local command line interface (CLI) for ad-hoc analysis, and in-notebook mode for seamless integration within Fabric notebooks. It can read Delta Lake tables and various raw formats (Parquet, CSV, JSON), making it ideal for data exploration, validation, and schema discovery in a read-only fashion.

A read-only tool designed to compare prediction-market baskets or themes against the user's existing knowledge base, portfolio notes, research memos, or financial context. It performs gap analysis, flagging potential conflicts, stale assumptions, and areas of missing research. This skill provides structured insights into fit and exposure without offering any investment or trading advice.

This guide provides best practices for structuring tables and figures in academic econometrics manuscripts, especially when adhering to strict journal page limits. It advises researchers on exhibit triage—determining which core findings belong in the main text versus supplementary online appendices—and guarantees reproducibility by detailing required note components and generating scripts.

This guide provides comprehensive guidelines for preparing high-quality, publication-ready tables and figures specifically tailored for Journal of Banking & Finance (JBF) submissions. It covers everything from structuring descriptive statistics and regression results to designing event-study plots and ensuring proper notes and execution workflows.

A comprehensive guide detailing the conventions for constructing high-quality empirical tables and figures, especially for corporate finance and econometrics journals. Covers best practices for reporting summary statistics, fixed effects, clustering, event-study/CAR plots, and ensuring self-contained notes for academic publication.

This guide outlines the rigorous standards for presenting tables and figures in manuscripts submitted to The Journal of Finance (JF). It emphasizes the need for self-contained, accessible exhibits, ensuring that readers from any subfield can interpret the results solely from the caption and notes. Key standards include using economic units (bps, % of market cap), proper numbering schemes (Roman/Arabic), and separating decisive findings from exhaustive details in the Internet Appendix.