dr-cook:data-visualizer

Generate publication-ready figures and runnable ggplot2 or matplotlib code from input data.

7|1|Updated Mar 9, 2026

Search Tags:#bioinformatics #matplotlib #data-visualization #network-visualization #publication-quality #ggplot2 #clinical-figures

Ready to run

npx skills add https://github.com/wen-chen/dr-cook --skill dr-cook-data-visualizer

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: dr-cook:data-visualizer
Source: https://github.com/wen-chen/dr-cook/tree/main/modules/analysis/data-visualizer
Command: npx skills add https://github.com/wen-chen/dr-cook --skill dr-cook-data-visualizer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Data visualization for academic research often requires translating raw results into publication-ready figures and runnable code. Data-visualizer automates this process by generating ggplot2 or matplotlib code that produces high-quality plots from omics, clinical, and network data, saving researchers time and ensuring consistency across manuscripts.

Core Features & Use Cases

Generates omics figures (volcano, heatmaps, PCA/UMAP) from bioinformatics outputs.
Creates clinical figures (boxplots, Kaplan-Meier curves, forest plots) and network visuals for pharmacology.
Produces publication-ready figures with ready-to-run code and templates, suitable for journals and preprints.

Quick Start

Provide your input data or result object, and let data-visualizer generate publication-ready figures with runnable ggplot2 or matplotlib code.

Frequently Asked Questions about dr-cook:data-visualizer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate publication-ready figures from omics and clinical data?▼

You can generate publication-ready figures by providing omics, clinical, or network data to template-driven workflows that output runnable ggplot2 or matplotlib code. The tool applies predefined plot templates and color palettes to save high-quality outputs via ggsave or plt.savefig with explicit width, height, and dpi settings.

Can I create volcano plots and Kaplan-Meier curves using matplotlib or ggplot2 code?▼

Yes, you can create volcano plots and Kaplan-Meier curves using ggplot2 or matplotlib. The tool generates code for omics figures like volcano plots, heatmaps, and PCA/UMAP, alongside clinical figures including Kaplan-Meier curves, forest plots, and boxplots.

What is the best way to automate network visualization for pharmacology research?▼

The best way to automate network visualization is to use template-driven workflows that process network data and generate runnable code. The tool automatically applies consistent saving workflows with explicit width, height, and dpi to produce publication-quality network visuals for pharmacology.

Does this visualization tool work with both R and Python plotting libraries?▼

Yes, it works with both R and Python by generating runnable code for ggplot2 and matplotlib. The template-driven workflows support both libraries to produce publication-quality figures, ensuring researchers can use their preferred environment for omics, clinical, and network data.

How do I ensure my data plots meet journal publication quality standards?▼

You ensure publication quality by using a consistent saving workflow with explicit width, height, and dpi settings. The tool enforces these standards through ggsave or plt.savefig commands embedded in the generated code, producing figures ready for journals and preprints.