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.

Guides using matplotlib to craft static, animated, and interactive plots through both pyplot and object-oriented APIs, detailing styling, subplots, and export options for publication-ready scientific workflows.

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.

Guides using SHAP to explain ML predictions, compute feature importance, generate diagnostic plots, debug models, analyze bias, and compare models across tree, deep, linear, or black-box architectures.

Plotly is a powerful Python graphing library designed to create highly interactive, publication-quality visualizations. It supports over 40 chart types, including scatter plots, heatmaps, candlestick charts, and geographical maps. Ideal for building sophisticated dashboards, conducting deep exploratory data analysis, and creating rich, web-embeddable presentations with features like zooming, panning, and hover tooltips.

Matplotlib is a foundational Python library for creating static, animated, and interactive plots with full customization. It supports various plot types like line, scatter, bar, and heatmaps, suitable for scientific and statistical visualizations. Users can customize appearance, create multi-panel figures, and export to PNG, PDF, or SVG. Ideal for publication-quality graphics and integrating with Jupyter notebooks.

Seaborn is a Python visualization library built on matplotlib for creating statistical graphics. It integrates with pandas for dataset-oriented plotting, offering publication-quality defaults for distributions, relationships, and categorical comparisons. Ideal for exploratory data analysis, multivariate analysis, and complex multi-panel figures. Supports various plot types like box plots, violin plots, and heatmaps.

A comprehensive guide for formatting and presenting empirical results (tables and figures) for submission to the American Economic Journal: Applied Economics (AEJ: Applied). It ensures that main causal estimates are immediately legible to referees by adhering to rigorous academic standards, including presenting standard errors, confidence intervals, and specific exhibit structures like event-study plots and balance tables.

This guide provides detailed standards for formatting empirical results (tables and figures) for the Academy of Management Journal (AMJ). It covers best practices for reporting correlation matrices, regression/SEM/HLM results, theoretical model diagrams, and interaction plots, ensuring adherence to strict academic publishing house styles (AOM house style). It helps users create self-contained, publication-ready exhibits.

A comprehensive guide for constructing conceptual exhibits—such as process models, 2x2 typologies, and multi-level frameworks—for academic manuscripts. This resource emphasizes that figures must represent pure theoretical work (constructs and relationships) rather than empirical data plots, ensuring structural clarity for top-tier academic publishing.

A guide for creating high-impact academic exhibits for literature reviews (e.g., Annual Reviews of Economics). It teaches how to synthesize findings into structured formats, including 'Who-found-what' summary tables, conceptual framework diagrams, and meta-evidence plots. The focus is on synthesizing existing knowledge across studies, not presenting original estimates. Essential for communicating complex, cross-field research findings to non-specialists.

This guide provides detailed instructions on designing high-quality visual exhibits for academic literature reviews, such as the Annual Review of Sociology (ARSoc). It covers three primary exhibit types: 'Who-found-what' summary tables, conceptual framework figures, and meta-evidence plots. The focus is on synthesizing findings across multiple studies and structuring arguments, rather than presenting new primary estimates or raw data.