Turns experimental results from JSON or CSV files into publication-ready LaTeX tables with proper booktabs formatting, bold best results, and multi-row layouts. Handles the four main table types you see in papers: comparison tables (methods vs metrics), ablation studies (component analysis), descriptive tables (dataset stats), and custom layouts. The skill enforces a strict no-hallucination rule, only using numbers from actual data sources, which is exactly the kind of guardrail you want when generating tables for submission. It integrates with standard LaTeX packages and outputs properly formatted tables with captions, labels, and significance markers. Saves you from manually formatting tables in LaTeX, which is always more tedious than it should be.
npx skills add https://github.com/lingzhi227/agent-research-skills --skill table-generation