Math Modeling Workflow

Math Modeling Workflow is an AI Engineering skill for Claude Code, published by handsomeZR-netizen in mathmodel-skill.

245 stars7 forkson handsomeZR-netizen/mathmodel-skillAdded 2026/09/02+7% in starsRepository updated 2026/07/22

agents-mdclaude-codeclaude-skillcodex-clicumcmdiangongfriendly-modeharness-agnosticicmlatexmath-competitionmath-modelingmathematical-contest-in-modelingmathematical-modelingmcmpythonworkflow

Install in seconds

Install Math Modeling Workflow

Copy Math Modeling Workflow into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/handsomeZR-netizen/mathmodel-skill ~/.claude/skills/mathmodel-skill

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/handsomeZR-netizen/mathmodel-skill.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: SKILL.md in handsomeZR-netizen/mathmodel-skill
Installs to: ~/.claude/skills/mathmodel-skill
Collection: One of 2 skills cataloged from this repository
Category: AI Engineering — 2631 skills

What Math Modeling Workflow does

Math Modeling Workflow guides CUMCM, MCM/ICM, and Diangong Cup projects through problem selection, modeling, solving, robustness checks, writing, and final submission review. Use it for explicit modeling-contest work, not for generic model selection or ordinary data analysis.

Math Modeling Workflow is cataloged under AI Engineering on DirSkills. Math Modeling Workflow comes from a repository tagged agents-md, claude-code, claude-skill, codex-cli and cumcm.

Documentation

README

Excerpt

mathmodel-skill — 数学建模三竞赛工作流 (v6.1)

10 阶段把 72–96 小时的竞赛协作变成可恢复、可检查的流程。用户回答关键问题，agent 维护状态与脚本。每阶段产出经过 rubric 自评、定向精修与跨阶段一致性回检；Stage 8–9 先遵守当届官方规则，再做多视角终审。CUMCM 包含 91 份来源文档，其中 59 份进入文本统计；MCM/电工杯经验统计明确为 n=0，不提供合成分位。

v6.1 更新: 加入竞赛规则基线与 AI 使用披露链路；三竞赛统一使用 marker 模板并对提交元数据 fail closed；修复状态路径错位、评分 verdict 持久化、题型权重合并和 YAML frontmatter 等问题；新增 preflight doctor 与自动化验证。

Codex 原生入口

Codex 优先按 skill 目录发现本文件:

用户级安装: $HOME/.agents/skills/mathmodel-skill/
项目级安装: <repo>/.agents/skills/mathmodel-skill/
UI 元数据: agents/openai.yaml
插件分发元数据: .codex-plugin/plugin.json + skills/mathmodel-skill/SKILL.md shim
项目指导: AGENTS.md 仍可作为 repo / workspace 级 instructions, 但不是唯一入口

当 skill 已安装后, 用户可直接说"开始建模"或显式说"使用 $mathmodel-skill 开始建模"。

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Math Modeling Workflow

What else does handsomeZR-netizen publish alongside Math Modeling Workflow?
Math Modeling Workflow is one of 2 skills that DirSkills catalogs from handsomeZR-netizen/mathmodel-skill, the repository it ships in. Its siblings there include Math Modeling Contest Workflow. Each one is a separate skill with its own page in this directory, installs the same way Math Modeling Workflow does, and is maintained by handsomeZR-netizen in that same repository. The rest of the collection is listed on the handsomeZR-netizen/mathmodel-skill page.
How does Math Modeling Workflow compare to other AI Engineering skills?
Math Modeling Workflow ranks #2351 by stars among the 2631 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Math Modeling Workflow against them. Open each page to compare what they document and how they install.