by cjh-solver
面向数学建模竞赛的 AI Agent 技能集:读题建模、求解、可视化、论文写作与终稿评审。35 skills for CUMCM / MCM / ICM.
# Add to your Claude Code skills
git clone https://github.com/cjh-solver/MathModeling-Skills-ArsenalGuides for using ai agents skills like MathModeling-Skills-Arsenal.
See how MathModeling-Skills-Arsenal compares with popular alternatives.
MathModeling-Skills-Arsenal is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by cjh-solver. 面向数学建模竞赛的 AI Agent 技能集:读题建模、求解、可视化、论文写作与终稿评审。35 skills for CUMCM / MCM / ICM. It has 68 GitHub stars.
MathModeling-Skills-Arsenal's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/cjh-solver/MathModeling-Skills-Arsenal" and add it to your Claude Code skills directory (see the Installation section above).
MathModeling-Skills-Arsenal is primarily written in Python. It is open-source under cjh-solver on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh MathModeling-Skills-Arsenal against similar tools.
No comments yet. Be the first to share your thoughts!
Available after the catalog security scan passes.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
适合有题目、数据和人工判断,希望把建模任务、证据和成果组织起来的个人或团队。覆盖国赛、美赛、MathorCup 等竞赛;格式与 AI 使用要求以本届官方规则为准。
当前状态: 主控为开发快照,完整发布检查尚未通过;节点批准和最终交付仍由人负责。详见验证说明。
本机读取已有 Harness 项目,集中查看比赛阶段、小问、角色会话和成果。页面定时从项目文件同步,不需要额外调用模型。比赛数据和审批记录保持只读,角色会话需自行登记并核实。

截图来自仓库内的合成演示项目,不代表真实比赛进度或批准结果。打开演示项目 · 了解工作台
| 我想做什么 | 从哪里开始 | 先得到什么 |
|---|---|---|
| 组织一场完整比赛 | 竞赛主控 · 全流程提示词 | 题意划分、输入缺口、模型计划与节点安排 |
| 只处理一个问题 | 模型选择 · 数据分析 | 题型与模型选择、数据边界、可复现的分析方案 |
| 制作图表和示意图 | 科研绘图 · 图表决策 · 技术路线示例 | 图表方案、可编辑图源、质量检查材料 |
| 写作或复核论文 | 学术写作 · 论文排版 | 章节审阅、LaTeX 论文工程与检查清单 |
| 查看已有 Harness 项目 | 工作台使用说明 | 阶段、角色、文件、论文和已有审查记录 |
更多单项任务和可复制提示词见按任务启动。
git clone https://github.com/cjh-solver/MathModeling-Skills-Arsenal.git
cd MathModeling-Skills-Arsenal
仓库使用 skills/<分类>/<技能>/SKILL.md 结构,安装时将技能目录放到宿主实际读取的技能根目录。以 Codex 用户技能目录为例:
以下命令安装数模分类,跳过创意写作;已有同名技能会跳过,不会覆盖。
# PowerShell:只安装数模分类,跳过创意写作。
$skillRoot = Join-Path $env:USERPROFILE '.agents/skills'
New-Item -ItemType Directory -Force -Path $skillRoot | Out-Null
Get-ChildItem skills/0* -Directory | ForEach-Object {
Get-ChildItem $_.FullName -Directory | ForEach-Object {
if (-not (Test-Path -LiteralPath (Join-Path $_.FullName 'SKILL.md'))) { return }
$destination = Join-Path $skillRoot $_.Name
if (Test-Path -LiteralPath $destination) {
Write-Warning "已存在,跳过:$($_.Name)"
} else {
Copy-Item -LiteralPath $_.FullName -Destination $destination -Recurse
}
}
}
此命令跳过已有同名技能;需要更新时先比较与备份,再合并。Claude Code、WorkBuddy 等宿主使用各自配置的技能目录;支持 SKILL.md 不代表工具、模型和多角色能力完全相同。
安装后打开新会话,给出题目、附件路径与规则来源:
使用 contest-orchestrator。先读取我的题目和本届规则,列出缺失输入,
选择合适模式。先做题意与模型计划,不直接生成最终论文或编造实验结果。
MathorCup 全流程可指定 full-contest-mathorcup;只解一问、只画图或只审稿时使用对应单项技能。详见 启动示例。
Harness 与 MathorCup 的新模板采用 chapter_parallel。先写建模求解,目录顺序与实际写作顺序分别维护。每次提交完整一章,由使用者批准后再写下一章;图表提示词也在该章批准后产生,由使用者转交图表角色。
flowchart LR
A[全文论证计划] --> B[完整建模求解章节]
B --> C{人工批准本章}
C --> D[下一章写作]
C --> E[本章图表提示词]
E --> F[用户转交图表角色]
F --> G[成图与定向返修]
D --> H[正文与附录完成]
H --> I[摘要最后写]
G --> J[最终接图与全文终审]
I --> J
图件返修更新提示词版本,后续章节继续写;未变正文的批准保持有效。最终交付仍检查最新图件、选定版本、证据来源与全文一致性。历史四批写作记录继续兼容。
仓库不发布比赛论文全文、赛事私有数据、个人记忆和凭据。整体协议为 Apache-2.0;第三方技能保留各自许可证,详见技能目录与协议。