paper-figure

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

2|1|Updated Apr 19, 2026
One-click install
npx skills add https://github.com/raja21068/AutoResearch --skill paper-figure-raja21068
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: paper-figure
Source: https://github.com/raja21068/AutoResearch/tree/main/skills/aris/paper-figure
Command: npx skills add https://github.com/raja21068/AutoResearch --skill paper-figure-raja21068

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve?

It removes the time-consuming, error-prone manual work of turning experiment outputs into clean, paper-ready plots and comparison tables.

Core Features & Use Cases

  • Data-driven figure generation: creates common ML visuals such as line plots, bar charts, scatter plots, heatmaps, and box/violin distributions directly from JSON/CSV/screen logs.
  • Comparison tables and LaTeX-ready outputs: generates standalone LaTeX tables for prior-vs-method or bounds-style comparisons.
  • Consistent publication styling: enforces print-friendly typography, DPI, formatting, and reproducibility by generating per-figure scripts and matching style across outputs.
  • Preserves existing manual figures: keeps user-provided figures (e.g., hero figures, architecture diagrams) and prepares LaTeX include snippets accordingly.

Quick Start

Use the paper-figure skill to generate all paper figures from your figure plan file PAPER_PLAN.md and your available experiment data, producing publication-quality PDFs plus a figures/latex_includes.tex file for easy copy-paste into your manuscript.

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-ready figures from raw experiment data?

Generate publication-ready figures by providing a figure plan file and available experiment data, such as JSON, CSV, or screen logs. The skill automatically selects appropriate visualization types based on data patterns and outputs print-friendly PDFs with consistent styling.

Can I create LaTeX tables for experiment comparisons from CSV or JSON data?

Yes, you can create LaTeX tables for prior-vs-method or bounds-style comparisons directly from CSV or JSON data. The skill generates standalone LaTeX table outputs and ready-to-paste include snippets for your manuscript.

Does the figure generation process preserve my manually created architecture diagrams?

Yes, the figure generation process preserves your manually created figures like hero figures and architecture diagrams. It prepares LaTeX include snippets for these existing visuals while generating new data-driven plots for the rest of your paper.

How do I ensure reproducible scripts for my paper figures and plots?

Ensure reproducible scripts for paper figures by using a tool that generates per-figure reproducible scripts alongside the visual outputs. This approach applies consistent publication styling, typography, and DPI across all generated plots.

What visualization types can I generate for machine learning experiment results?

You can generate common ML visualization types including line plots, bar charts, scatter plots, heatmaps, and box or violin distributions from your experiment results. The skill selects the appropriate type by analyzing your data patterns.

What's the best way to integrate generated plots into a LaTeX manuscript?

The best way to integrate generated plots is to use the produced latex_includes.tex file, which contains ready-to-paste embed snippets for both newly generated figures and preserved manual figures, allowing direct copy-paste into your manuscript.