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.