What problem does it solve?
Turning raw experiment results into publication-ready figures and tables is repetitive and error-prone, requiring consistent styling, correct figure-type selection, and LaTeX integration for every plot in a paper.
Core Features & Use Cases
- Automated figure generation: Creates line plots, bar charts, scatter plots, heatmaps, box/violin plots, and multi-panel subfigures from JSON/CSV experiment data using matplotlib with a shared publication style config.
- LaTeX table and snippet output: Produces comparison tables as standalone .tex files and generates
latex_includes.tex with ready-to-paste figure environments.
- Quality review workflow: Runs a reviewer-model pass over figure captions and plans, plus a publication checklist (font sizes, grayscale readability, no in-figure titles, vector PDF output).
- Use Case: After finishing experiments for a conference paper, point the skill at your PAPER_PLAN.md figure plan and results JSON files to generate all data-driven figures at 300 DPI in PDF format, while preserving manually created architecture diagrams.
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.