Skill UI

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.

Seaborn is a powerful Python library for creating publication-quality statistical graphics. It is designed for dataset-oriented plotting, making it ideal for exploratory data analysis, multivariate analysis, and visualizing complex relationships, distributions, and comparisons with minimal code. It builds upon Matplotlib, offering high-level interfaces for functions like scatterplots, heatmaps, and pair plots.

A comprehensive guide for designing, reviewing, and migrating numerical workflows in MATLAB or GNU Octave. It emphasizes building reproducible projects, adhering to strict safety boundaries, and ensuring code semantics are explicit for robust data processing and analysis.

Seaborn is a high-level Python visualization library built on Matplotlib, designed specifically for creating publication-quality statistical graphics. It excels at dataset-oriented plotting, enabling users to perform complex multivariate analyses, visualize data distributions (like box plots, violin plots), and explore relationships with minimal code. It simplifies the process of generating multi-panel figures and statistical plots directly from pandas DataFrames.

A comprehensive suite designed for AI agents to perform safe, deep, and multi-format web searches. It allows agents to retrieve current web information, analyze PDFs, extract YouTube transcripts, and access GitHub code files. Instructions include guidelines for varying search depths and using specialized tools for code context retrieval.

A comprehensive guide for strengthening the methodological rigor of academic manuscripts, particularly for high-stakes journals. It covers advanced techniques for causal identification (e.g., Difference-in-Differences, Instrumental Variables, Regression Discontinuity), pre-analysis planning, linking theory to empirical tests, and defending claims against skeptical reviewers. This skill focuses on methodological architecture, not code.

A comprehensive guide detailing the selection of appropriate statistical estimators (e.g., DiD, Panel FE, ANOVA) for various research designs. It also outlines rigorous best practices for ensuring data integrity, conducting robustness checks, and adhering to journal code-sharing policies, ensuring highly reproducible empirical research.

This tool serves as an orchestrator for authors preparing submissions to Cognitive Psychology (Elsevier). It guides users through the entire research lifecycle—from initial topic selection and theoretical formalization to study design, data analysis, and open science practices. It emphasizes structuring the contribution as a model-driven, multi-experiment program, ensuring all necessary steps, including code transparency, are addressed.

Provides comprehensive guidelines for packaging and documenting complex robotics research artifacts (code, simulations, hardware designs, datasets, etc.) for scholarly review. It outlines best practices for ensuring reproducibility, adopting the "five-minute-skeptic standard," and managing the full lifecycle of artifacts from review submission to public acceptance.

A guide for designing and structuring empirical tables and figures for submissions to International Organizations (IOs). Focuses on meeting strict word limits, ensuring exhibits are self-contained, reproducible, and clearly separating core arguments (main text) from supporting details (supplementary material). Best practices include explicit unit labeling, prioritizing effect plots over dense tables, and guaranteeing that all displayed numbers match the original analysis code.

This guide details the rigorous, reproducible empirical strategies required to identify causal parameters in applied econometrics, meeting high standards (e.g., JAE). It covers various designs—including DID, IV, panel data, and time-series—and mandates that every assumption and diagnostic test must be explicitly stated, tested, and reproducible using deposited code/data.

A comprehensive preflight checklist designed for submitting manuscripts to the Journal of Business & Economic Statistics (JBES). This guide ensures authors have verified all necessary components—including the data/code supplement, conflict disclosures, and cover letter targeting—against the latest academic standards. It functions as a critical final review step before formal submission, emphasizing the need to cross-reference live journal guidelines.