Math Modeling Skill

数学建模竞赛(国赛/美赛/校赛/企业赛/研究生赛)从读题到论文交付的标准化全流程能力——读题拆解、方案选择(大道至简+多候选)、模型搭建(机理优先/可解释)、代码实现(防伪数据/Search-Replace 纠错/可复现)、可视化风格(三套学术配色+八大绘图类型选择指南+宋体Times 字体+TikZ 流程图+论文总体架构图+详细图片命名)、论文写作(各部分长度/降 AI 率/不堆砌/公式数量合适/图表就近/图表说明100–150字/单页图表占比≤2/3禁图挨图/正文页数21–30)、审稿与修改(九维评审+三级问题清单+修复循环+评分+版面逐页视觉审查+乱码复检)。只要用户提到数学建模/数模/建模论文/国赛/美赛/CUMCM/MCM/ICM/建模大赛/读题/建模/求解/数模论文/数学模型/数模竞赛/论文总体架构图/架构图/图表排版/图表就近/图表占比/图表说明文字/版面审查/页面布局/图片乱码等,都应使用本 skill,即使没有明说"建模"。适用于从读题、建模仿真到 LaTeX 成稿交付的完整任务,可直接在 Claude Code / Codex / WorkBuddy 等 agentic 编码工具中加载使用。

24 starsAI, LLMs & Agents

Install

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

npx skills add LEEHAHAHAHA/math-modeling-skill --skill math-modeling-skill

Manual install

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

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

From the SKILL.md

# 数学建模竞赛全流程标准化 Skill

本 skill 从多轮真实数学建模竞赛任务(含四问、56 页、20+ 轮迭代修订的完整竞赛论文)与一个桌面端数学建模智能体工作流软件(mathflow,6 智能体 S0–S6 流水线、98+ 测试)中共同提炼而来。每条规则都是真实竞赛或真实智能体工程中被评审/用户真正纠正过的教训,不是空泛建议。适用于所有数学建模竞赛,不限定任何特定赛事。文中引用的具体赛事数值只作示例,规范本身通用。

## 核心理念(贯穿所有环节)

1. **大道至简**:优先机理/结构模型(幂律、对数线性、微分方程、排队论、优化模型),参数少、每个参数有业务含义;只在简单模型确实无法解决时才逐步增加复杂度。一个讲得清的简单模型 + 严谨统计推断,永远胜过堆砌的集成黑箱。
2. **可解释性优先**:模型要能说出"为什么",给出弹性系数、显著性、残差诊断等。机器学习(随机森林/XGBoost)只作**非参数稳健性检验**与参数模型对照,不作主角;必须用黑箱时配 SHAP/LIME 等可解释性补救。
3. **诚实**:结果如实报告,改善小就写小,退化就写退化,不挑好看的指标,不编造数据。诚实本身是加分项(模型评价一节有话说)。但"如实披露"建立在**已尝试多种方法**基础上;结果很差时先改进,不要直接提交差结果。
4. **忠于题目**:题目给出的官方公式、口径、规则原样采用(如旅行负担口径、休息约束定义、归一化公式),不自己发明替代口径。只允许**等价改写**(形式变了、数学上完全等价,且注明"等价于题目定义")。
5. **完整闭环**:读题 → 建模 → 求解 → 验证 → 图表 → 论文 → 审稿 → 交付,每步都有可交付产物,代码与论文一一对应。
6. **降 AI 味**:论文读起来要像资深参赛者手写,不是 AI 腔。具体反模式见 `references/writing.md` 第 5 节,核心是:不用破折号"——"过度、不堆"xx-xx-xx"三段式、不故弄玄虚、数字与单位间不加多余空格、不写"值得注意的是""综上所述"等套话。

## 何时读哪个 reference

| 任务阶段 | 读 | 核心内容 |
|---|---|---|
| 读题/拆解 | `references/parsing.md` | 读题协议、图片多模态识别、数据文件结构探查、问题类型判定、拆题 JSON |
| 选方案/建模 | `references/modeling.md` | 大道至简偏好序、候选方案 2-3 个、小巧思技法、可解释性验证、诚实披露、优化模型完整形式 |
| 写代码/求解 | `references/coding.md` | 防伪数据红线、真实数据绝对路径、Search-Replace 纠错、可复现清单、求解汇总提炼 |
| 做图 | `references/visualization.md` | nature/science/IEEE 三套配色、八大绘图类型选择指南、宋体+Times 字体、TikZ 流程图(各问解题流程=蛇形横向布局+现代柔和6色,见 §5.1.1)、图片命名规范、CJK 豆腐块预警、图表就近/说明字数/占比规范 |

Read the full skill on GitHub

Details

Skill name: math-modeling-skill
Repository: LEEHAHAHAHA/math-modeling-skill
Repo updated: 2 September 2026

FAQ

What does the Math Modeling Skill skill do?

How do I install the Math Modeling Skill skill?

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

Is Math Modeling Skill popular?

It lives in LEEHAHAHAHA/math-modeling-skill, which has 24 GitHub stars and 0 forks.

Related skills

Dayu Harness

kinoward/dayu-harness-skill

大禹治库 Skill（Dayu Harness Skill）是帮助项目低成本接入 Harness Engineering 理念的一次性部署工具。将以 AGENTS.md 为根的渐进式披露治理体系部署到目标项目。仅通过 /dayu-harness 显式命令激活。

AI, LLMs & Agents

Tag

1756141021/tag-skill

AI 绘画 TAG/prompt 创作。用于画面描述、OC 标签化、旧提示词调整和出图偏差修正；不用于代码标签或非绘画任务。

AI, LLMs & Agents

Hush

royashbrook/hush

Use whenever an agent needs to STORE, GENERATE, or USE a secret such as an API token, signing key, or password. Hush has one hard rule: the agent never sees plaintext, so it never enters chat, transcripts, stdout, logs, the clipboard, or a temp file. A user-provided value enters once through a hidden prompt; a strong random value can be generated directly into the OS-backed store. Hush later injects it straight into a consumer through an environment variable or stdin, never prints it, and deliberately has no plaintext get command. Trigger on "store this token", "save this key", "add it to the

AI, LLMs & Agents

Opencode

pcx-wave/opencode-skill

Delegate a coding task to OpenCode CLI and supervise the result via git diff. Trigger: /opencode <instruction>. Claude orchestrates, OpenCode codes. Also handles /opencodeon, /opencodeoff, /opencodestatus, /opencode-report, /opencode-model-pick, /opencode-model-clear.

AI, LLMs & Agents

Pandaai Factor Online

quantskills/skill-pandaai-factor-online

Set up pandaai-cli, log in to PandaAI, and mine, backtest, and iterate quantitative factors on the platform. Use when an agent needs to onboard a user to the PandaAI factor competition, install or log in to pandaai-cli, look up available fields and operators, write or debug factor formulas, run and batch factor analyses, or interpret IC / group-return / turnover results on portable agent platforms such as Claude Code, Cursor, OpenClaw, or Codex-style skill systems.

AI, LLMs & Agents

LLM Council

gestordeaudiencia/llm-council-skill-ptbr

Passa qualquer pergunta, ideia ou decisão por um conselho de 5 conselheiros de IA que analisam de forma independente, fazem revisão por pares anonimamente, e sintetizam um veredito final. Baseado na metodologia LLM Council do Karpathy. GATILHOS OBRIGATÓRIOS (PT-BR): 'convoca o conselho', 'roda o conselho', 'leva pro conselho', 'submete ao conselho', 'war room isto', 'stress-test isto', 'pressure-test isto', 'debate isto'. GATILHOS OBRIGATÓRIOS (inglês): 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'. GATILHOS FORTES (use quando combi

AI, LLMs & Agents

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