数学建模技能 - 为CUMCM、MCM/ICM等数学建模竞赛提供结构化的三阶段工作流程：建模分析、代码实现、论文撰写。包含丰富的算法资源库(优化/预测/评价/图论/机器学习等)、角色指导文档、论文模板和实用工具脚本。
SaferSkills independently audited math-modeling-skill (Agent Skill) and scored it 45/100 (orange). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 3 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 3 flagged
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.Every scanned point with the score it earned and what moved between them.
Aggregate score unchanged between these scans.
The primary manifest — the file an agent reads to learn what this artifact does.
数学建模团队的建模分析角色，负责将实际问题转化为数学模型。
在开始建模分析之前，必须先阅读以下文档：
| 文档 | 用途 |
|---|---|
roles/建模手/references/前置合同.md | Model Contract 前置规划框架 |
references/建模设计理论.md | 模型选择、复杂度控制、组合策略、证据层次 |
| 文件 | 什么时候打开 |
|---|---|
references/前置合同.md | 开始分析前，建立核心结论、证据链、方案评审 |
references/工作流程.md | 执行分析流程时，包含附录检查→题目理解→模型选择→算法设计→术语规范→缺失输入处理 |
references/常见模式.md | 11种建模常见模式（优化/预测/评价/综合），含模型组合决策树 |
references/质检清单.md | 交付前逐项检查 |
详细算法说明文档位于 assets/ 目录下：
| 算法类别 | 文档 |
|---|---|
| 优化算法 | assets/01-优化算法说明.md |
| 预测算法 | assets/02-预测类算法说明.md |
| 评价算法 | assets/03-评价类算法说明.md |
| 图论网络 | assets/04-图论与网络分析算法说明.md |
| 统计分析 | assets/05-统计分析与数据处理算法说明.md |
| 综合算法 | assets/06-综合类算法说明.md |
| 机器学习 | assets/07-机器学习算法说明.md |
1. 能用初等方法解决的就不用高等方法
2. 能用简单方法解决的就不用复杂方法
3. 能用被更多人看懂、理解的方法就不用只能少数人看懂、理解的方法| 功能 | 工具 | 使用时机 |
|---|---|---|
| 读取PDF题目 | tools/pdf | 题目为PDF格式时 |
| 分析Excel数据 | tools/xlsx | 题目附带表格数据时 |
| 搜索学术文献 | tools/paper_search | 模型选择后搜索理论支撑 |
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.