paper-figure

Generate publication-quality vector PDF figures and LaTeX tables from experiment data.

Updated May 29, 2026
One-click install
npx skills add https://github.com/Mang30/myskills --skill paper-figure-mang30
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: paper-figure
Source: https://github.com/Mang30/myskills/tree/main/skills/paper-figure
Command: npx skills add https://github.com/Mang30/myskills --skill paper-figure-mang30

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It eliminates the manual, error-prone work of converting experiment outputs into consistent, publication-ready figures and tables for a paper.

Core Features & Use Cases

  • Data-driven figure generation: Creates line plots, bar charts, scatter plots, heatmaps, and box/violin plots from experiment data for typical ML paper workflows.
  • Paper comparison artifacts: Produces comparison tables (LaTeX) for prior work and ablation/baseline results, plus multi-panel figures for multi-dataset and multi-metric layouts.
  • Style consistency for publication: Applies a configurable publication style (DPI, fonts, palette, vector PDF) and generates LaTeX include snippets to speed up manuscript assembly.
  • Preserves manual hero figures: Detects existing manually created figures and keeps them, generating only what is data-driven.

Quick Start

Generate paper figures from your figure plan by running the paper-figure skill with your figure plan file or data path as the single argument.

Frequently Asked Questions about paper-figure

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

FAQPage Schema
How do I generate publication-quality figures from CSV experiment logs?▼

To generate publication-quality figures from CSV experiment logs, this Skill processes your data to create vector PDFs, line plots, and heatmaps. It outputs one generation script per figure into a figures directory, ensuring reproducible plots for your research paper.

What is the best way to convert ML experiment results into LaTeX tables?▼

The best way to convert ML experiment results into LaTeX tables is using a generation skill that parses your JSON or screen logs. It produces LaTeX comparison tables for ablations and baselines, plus a consolidated latex_includes.tex file with includegraphics snippets.

Can I keep my manually created hero figures while auto-generating other plots?▼

Yes, you can keep manually created hero figures while auto-generating other plots. This Skill detects existing manually created figures and preserves them, generating only the data-driven plots specified in your figure plan.

How do I ensure consistent styling across multi-panel figures for a research paper?▼

To ensure consistent styling across multi-panel figures, this Skill applies a configurable publication style with standardized DPI, fonts, and color palettes. It generates vector PDFs and multi-panel layouts for multi-dataset and multi-metric comparisons.

Do I need a figure plan file to automate paper figure generation?▼

Yes, you need a PAPER_PLAN.md figure plan file to automate paper figure generation. This plan guides the Skill to produce the correct data-driven plots, comparison tables, and LaTeX include snippets based on your available experiment data.