Math Modeling

Execute and audit complete mathematical modeling competition workflows with the evidence-first mmflow runtime as the single source of truth, plus adaptive data analysis, model selection, validation, publication, presentation, privacy, reproducibility, and compliance templates. Use for 数学建模、数模、赛题、CUMCM、MCM/ICM、GMCM、MathorCup、APMCM、深圳杯 or any contest task involving problem selection, data analysis, model construction, validation, paper writing, review, packaging, defense preparation, auditing, or workflow recovery.

19 starsAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add Y-love-han/math-modeling-skill --skill math-modeling

Manual install

git clone --depth 1 https://github.com/Y-love-han/math-modeling-skill.git /tmp/math-modeling-skill
mkdir -p ~/.claude/skills
cp -r /tmp/math-modeling-skill/. ~/.claude/skills/math-modeling

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 数学建模自主全流程整合版

## 1. 任务定位

使用本 Skill 完成从赛题读取到本地交付的完整数学建模竞赛流程。以证据链、可复现性、题型适配、论文一致性、合规性和可审查性为首要目标；以高水平竞赛作品为质量方向，但不承诺原创性、评委接受度、奖项或任何外部检测结果。

将 `scripts/mmflow.py` 作为唯一事实入口。状态、事件账本、Registry、Lineage、stage_epoch、门禁、回退、受控执行、复现、审查关闭、隐私扫描、打包和发布标签都必须由它计算或登记。Markdown、文件名、关键词、文件大小、截图和模型自报均不能单独证明阶段完成。

把本 Skill 安装目录与具体比赛项目根目录严格分开。所有题目文件、数据、代码、实验、稿件和交付包写入用户授权的项目根目录；不要把比赛产物写入本 Skill 目录，不要把 `.mmflow` 事件或状态当作普通文本手工修改。

## 2. 不可逾越的规则

1. 读取题目原文、全部可用附件、补充说明和适用的当届官方规则；当届一手规则优先于往届经验和本 Skill 的通用建议。
2. 区分题目事实、数据事实、外部文献、数学推导、模型输出、实验观察、专业判断、假设和建议；为关键内容登记来源与适用范围。
3. 禁止编造数据、引用、运行、数值、图表、统计显著性、定理条件、最优性、复现事实、许可或外部工具结果。
4. 禁止把调试、demo、fixture、旧尝试、归档、未核验来源或陈旧证据用于论文生产主张。
5. 禁止直接写入 `PASSED`、`COMPLETE`、发布标签、门禁结果或审查关闭状态；只能调用受控命令，请程序判定。
6. 禁止用未来阶段证据、回退前旧 epoch 证据、来源阶段未通过的证据或与当前项目无血缘的产物过门禁。
7. 禁止删除失败尝试、矛盾结果、审查 finding 或日志来美化过程；修复必须产生新 attempt、execution、证据或关闭记录。
8. 禁止为了固定页数、图表数量、三维图数量、算法数量、检验名称、引用数量或创新数量注水；适用的官方格式和真实信息需求优先。
9. 禁止将复杂度、术语数量或模型数量当作质量；先排除泄漏、单位错误、不可识别、不匹配、不可复现和约束违规。
10. 门禁失败时修复最上游根因或回退，不得改阈值、扩大容差、替换规则或将 `ERROR`、`BLOCKED`、未知状态解释成通过。
11. 记录简洁的决策摘要、备选方案、证据、风险和撤销条件；不要求暴露隐藏推理过程。
12. 未获明确授权时，不执行外部提交、上传、付费、受限登录、发送消息、披露参赛者身份或改变任务范围外系统。

## 3. 启动、恢复与主循环

在每次进入任务或切换会话时执行以下循环：

1. 确定并验证项目根目录；确认本 Skill 根目录和比赛项目根目录不是同一目录。
2. 运行 `python <skill-root>/scripts/mmflow.py doctor --project <project-root> --json`，读取能力、依赖、路径和隔离等级。目录级受控执行不是操作系统沙箱；不得把它描述为阻止网络、项目外文件访问或子进程逃逸的强隔离。
3. 若项目尚未初始化，先清点材料，再运行 `init`；若存在旧契约，先运行 `migrate --dry-run`，确认迁移计划后才迁移；已初始化项目运行 `resume`。

Read the full skill on GitHub

Details

Skill name: math-modeling
Repository: Y-love-han/math-modeling-skill
License: MIT
Repo updated: 31 August 2026

FAQ

What does the Math Modeling skill do?

How do I install the Math Modeling skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Y-love-han/math-modeling-skill --skill math-modeling. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Math Modeling popular?

It lives in Y-love-han/math-modeling-skill, which has 19 GitHub stars and 0 forks.

Related skills

Math Modeling Single

Yoki-cmd/math-modeling-single

数学建模论文生成器。给一道数学建模竞赛题，按国赛标准四阶段流程（策略→求解→写作→审查）端到端生成完整论文（LaTeX），含摘要/问题重述/问题分析/模型假设/符号说明/模型建立与求解/模型检验/评价改进推广；用 mermaid-cli/Python 作矢量流程图、MATLAB MCP（不可用回退 Python）跑真实数据，自带国赛标准 LaTeX 模板。Triggers on "数学建模", "数模", "建模论文", "math modeling", "国赛", "美赛", "CUMCM", "MCM"，或用户显式调用 /math-modeling-single。

AI, LLMs & Agents

Rss Agent

shiquda/rss-agent

A powerful RSS subscription manager and reader. Use it to (1) Import/export OPML files, (2) Manage RSS feeds (add, remove, categorize), (3) Validate feed connectivity, (4) Schedule periodic updates via cron, (5) Fetch and summarize articles with a progressive disclosure approach.

AI, LLMs & Agents

Travel Planner

huanyuzhilv/skills-travel-planner

面向旅行顾问与定制游服务商的商用 Travel Planner Skill。**roadbook-v2 默认即交付级**：生成或更新 tripData 后须自动执行 deliver_roadbook_v2（**每日小红书正文** + 住宿飞猪简介 + **小红书预检与 strict https 配图** + 校验 + HTML）， **禁止**向用户确认「要不要跑交付」；仅当用户明示草稿/预览/跳过小红书时可降级。 Cursor Agent 角色与硬性规则见仓库根 **AGENTS.md**。支持目的地推荐、行程策划、预算拆分、路书 tripData + HTML/PDF。触发：旅行计划、路书、报价、行程单等。

AI, LLMs & Agents

Claude to Codex

padmilkhandelwal/convert-claude-to-codex-skill

Converts any Claude skill into a Codex-compatible skill. Searches the Claude skill marketplace by name, fetches the SKILL.md, rewrites Claude-specific tool references, generates agents/openai.yaml, and writes output to .codex/skills/. Use when asked to convert, port, or transform a Claude skill for use in Codex. Invoke with $claude-to-codex <skill-name>.

AI, LLMs & Agents

Grok Bot

adamanz/grok-bot-skill

Chat with Grok Bot teammates, message a named Grok Bot, create a new Grok Bot, list Grok Bots, read a Grok Bot transcript, or operate the xAI Grok Bot desktop app from Cursor, Claude Code, or Codex instead of the UI. Use when the user mentions Grok Bot, Grok teammates, Reed, Agent Computer, spinning up a new bot, or talking to Grok from the terminal.

AI, LLMs & Agents

Agents Md Generator

Eriemon/agents-md-generator

Use when creating, updating, compressing, reviewing, or verifying AGENTS.md and other AI coding-agent rules; when a managed root AGENTS.md is missing, malformed, stale, or version-incompatible; when the user explicitly mentions AGENTS.md, agent rules, or scoped AGENTS.md; when a managed skill README needs a functional illustration set; or when a request about the current workspace, repository, or work folder is a planning request and therefore requires a root AGENTS.md check first.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.