建模手

by XiaoMaColtAI

建模手 is a Data skill for Claude Code, published by XiaoMaColtAI in math-modeling-skill.

819 stars51 forkson XiaoMaColtAI/math-modeling-skillAdded 2026/08/23+8% in starsRepository updated 2026/08/22

View source on GitHub Download repo ZIP

claude-codeclaude-skillscodexcodex-skillcumcmdeepseek-harnessmath-modelingmcm-icmskillsvibe-coding

Install in seconds

Install 建模手

Copy 建模手 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/XiaoMaColtAI/math-modeling-skill/tree/main/references/roles/%E5%BB%BA%E6%A8%A1%E6%89%8B' ~/.claude/skills/'%E5%BB%BA%E6%A8%A1%E6%89%8B'

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/XiaoMaColtAI/math-modeling-skill.git

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

In this catalog

Source file: references/roles/建模手/SKILL.md in XiaoMaColtAI/math-modeling-skill
Installs to: ~/.claude/skills/%E5%BB%BA%E6%A8%A1%E6%89%8B
Collection: One of 10 skills cataloged from this repository
Category: Data — 668 skills

What 建模手 does

建模手用于数学建模题目的题意理解、模型选择和算法设计，并输出题目分析报告与术语表格。它适合在建模开始阶段做问题拆解、约束梳理和方案论证。

建模手 is cataloged under Data on DirSkills. 建模手 comes from a repository tagged claude-code, claude-skills, codex, codex-skill and cumcm.

Documentation

README

Excerpt

建模手

路径

ROLE_ROOT：本文件所在目录。
SKILL_ROOT：ROLE_ROOT/../../..，只读。
PROJECT_ROOT：用户项目目录，所有产物只写这里。

固定产物

PROJECT_ROOT/题目分析报告.md
PROJECT_ROOT/术语表格.md

只使用上述两个文件；合同内容作为分析报告的一部分。

执行顺序

读取题目与全部附件，建立问题、目标、约束、数据字段和输出要求清单。
数据驱动地检查缺失、异常、量纲、时间与空间范围。
在理解题目后写出每个子问题应回答的结论类型，再评估候选模型。
每个子问题最多选两个独立模型体系，说明模型、算法、公式、参数、输入输出、验证方式和风险；同一物理机制的不同近似或精度展开按一个模型族计数。
使用 ../../../tools/paper_search/SKILL.md 搜索理论依据；引用必须可追溯。
写入两个固定产物并按 references/质检清单.md 完成作者自检。
立即派发未参与编写的质检 Subagent 执行 M1 建模终检；未返回 PASS 不得进入编程阶段或宣称建模交付完成。

独立验收

M1 的输入包括题目与附件、题目分析报告.md、术语表格.md、文献来源和作者自检结果。质检 Subagent 只读核对子问题覆盖、公式与符号、单位与约束、假设依据、模型数量、可实现性、验证方案和引用可追溯性，按 ../../../references/Subagent调度.md 返回证据回执。失败时由建模手修正两个既有产物，再复验 M1。

何时加载

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

Frequently asked about 建模手

What else does XiaoMaColtAI publish alongside 建模手?
建模手 is one of 10 skills that DirSkills catalogs from XiaoMaColtAI/math-modeling-skill, the repository it ships in. Its siblings there include DOCX Tools, Excel Tools and LaTeX工具. Each one is a separate skill with its own page in this directory, installs the same way 建模手 does, and is maintained by XiaoMaColtAI in that same repository. The rest of the collection is listed on the XiaoMaColtAI/math-modeling-skill page.
How does 建模手 compare to other Data skills?
建模手 ranks #504 by stars among the 668 Data skills in this catalog. The most-starred ones next to it are Benchmark Methodology, Jupyter Notebook and Solana. 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 建模手 against them. Open each page to compare what they document and how they install.