math-modeling-skill
XiaoMaColtAI/math-modeling-skill
A comprehensive math modeling skill that supports the entire workflow from problem analysis, algorithm design, and code implementation to scientific visualization, paper writing, and reproducibility. It includes three distinct roles (modeler, programmer, and paper writer), automated quality checks, and optional subagent collaboration for tasks like literature review, algorithm prototyping, and terminology verification. The skill is compatible with both Python and MATLAB, and supports LaTeX and Word paper generation with strict formatting and reproducibility requirements.
881 52No licenseUpdated 2026-08-25
Overview
This skill provides a complete end-to-end solution for mathematical modeling competitions and research projects. It includes three main roles: 1) the modeler who analyzes the problem, designs the mathematical model, and defines the algorithm; 2) the programmer who implements the model in Python or MATLAB, generates results, and creates visualizations; and 3) the paper writer who constructs the argument based on real results and generates a Word or LaTeX paper. The skill includes automated quality checks at each stage, supports scientific visualization with publication-quality figures, and ensures reproducibility through detailed logging of dependencies, random seeds, and input files. Optional subagents can be enabled for tasks like literature review, algorithm prototyping, and terminology verification. The skill is compatible with both Python and MATLAB, and supports LaTeX and Word paper generation with strict formatting and reproducibility requirements.
Best for
Mathematical modeling competitions (e.g., CUMCM, MCM/ICM, APMCM), Research projects requiring rigorous mathematical modeling and simulation, Academic papers requiring reproducible results and publication-quality figures, Data analysis and visualization tasks with strict formatting and reproducibility requirements
Security considerations
The skill ensures reproducibility through detailed logging of dependencies, random seeds, and input files. It includes automated quality checks at each stage to ensure the integrity of the results. The skill does not handle sensitive data and is designed for use in academic and research environments. When generating papers, it ensures that all figures, tables, and references are properly cited and formatted according to academic standards.
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.