paper-figure

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

Updated Jul 9, 2026
One-click install
npx skills add https://github.com/Lingjie-wang/autoRL --skill paper-figure-lingjie-wang
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: paper-figure
Source: https://github.com/Lingjie-wang/autoRL/tree/main/Auto-claude-code-research-in-sleep/skills/paper-figure
Command: npx skills add https://github.com/Lingjie-wang/autoRL --skill paper-figure-lingjie-wang

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires matplotlib.

What problem does it solve? Writing an academic paper requires turning raw experiment results into polished, consistent, publication-quality figures and tables, which is tedious and error-prone when done by hand. This Skill automates the generation of data-driven plots and LaTeX tables from JSON/CSV experiment data with a unified visual style. ## Core Features & Use Cases - Automated figure generation: Creates line plots, bar charts, scatter plots, heatmaps, box/violin plots, and multi-panel subfigures from experiment data using matplotlib with a shared publication style config (300 DPI, vector PDF, serif fonts). - LaTeX table and include generation: Produces standalone comparison tables as .tex files and ready-to-paste \includegraphics snippets saved to figures/latex_includes.tex. - Quality review workflow: Runs a render-then-verify self-check plus a GPT-5.5 reviewer pass via Codex MCP against a partitioned correctness/guidance checklist. - Use Case: After finishing experiments for a conference submission, point the Skill at your PAPER_PLAN.md figure plan and results JSON files to produce all data-driven figures, tables, and LaTeX snippets in one pass. ## Quick Start Ask the assistant to generate all paper figures from the figure plan in PAPER_PLAN.md and the experiment data in the figures directory.

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 matplotlib figures for a paper?

Use a shared style configuration that sets serif fonts, 300 DPI, vector PDF output, and disabled top/right spines, then write one script per figure that reads data from JSON or CSV files. This Skill automates that workflow and saves LaTeX include snippets for each figure.

What figure types can be auto-generated from experiment data?

Data-driven plots including line plots for training curves, bar charts for method comparison, scatter plots, heatmaps, box/violin plots, and multi-panel subfigures can be auto-generated. Comparison tables are produced as standalone LaTeX .tex files.

Can this tool create architecture diagrams or pipeline figures?

No, architecture diagrams, generated image grids, and screenshots are outside its scope and must be created manually with tools like draw.io, Figma, or TikZ. The Skill preserves existing manually created figures and only generates the LaTeX include snippet for them.

Should paper figures use PDF or PNG format in LaTeX?

Vector PDF is the required default because it keeps text and lines sharp at any zoom and avoids rasterized fonts. PNG is only a fallback option when vector output is not possible.

Why should figures not have titles inside the plot?

Titles belong in the LaTeX \caption{} command, not inside the figure, so formatting stays consistent with the paper's typesetting. The Skill's checklist enforces removing plt.title and any matplotlib default titles.