Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Lupynow/math-modeling-skills --skill math-modeling-papergit clone --depth 1 https://github.com/Lupynow/math-modeling-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lupynow/math-modeling-skills/math-modeling-paper)<a href="https://agentmods.dev/skills/lupynow/math-modeling-skills/math-modeling-paper"><img src="https://agentmods.dev/badge/skills/lupynow/math-modeling-skills/math-modeling-paper/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lupynow/math-modeling-skills/math-modeling-paper"><img src="https://agentmods.dev/badge/skills/lupynow/math-modeling-skills/math-modeling-paper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00202 | $0.05221 |
| Opus 5 | $0.00101 | $0.02610 |
| Sonnet 5 | $0.00040 | $0.01044 |
| Haiku 4.5 | $0.00020 | $0.00522 |
Grade A, and why
math-modeling-paper scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
数学建模竞赛论文写作
使用流程
收到写作任务后，按以下步骤操作：
Step 0: 检查建模来源
先判断用户是否已完成建模：
- 用户已用
math-modeling-solver完成建模，有论文草稿片段 → 识别[PAPER_READY]信号或用户说"建模做完了/准备写论文"，直接加载草稿片段，从对应章节开始写作 - 用户未建模，直接要写论文 → 建议先用
math-modeling-solver完成建模，或直接进入 Step 1 确定写作阶段 - 用户已有自己的建模方案 → 直接进入 Step 1
Step 1: 识别比赛类型和写作阶段
向用户确认（如果信息不全）：
- 比赛类型：国赛(CUMCM) 还是 美赛(MCM/ICM)？这会决定结构模板、语言和评审重点。
- 当前阶段：
- 规划：还没动笔，需要确定论文结构和各部分要点
- 写作：正在写某个具体章节，需要指导
- 润色：已有初稿，需要优化表述、检查逻辑
- 检查：全文已完成，需要做最终的格式和规范检查
Step 2: 加载对应参考文件
根据比赛类型加载详细指南：
- 国赛 → 读取
references/cumcm-guide.md - 美赛 → 读取
references/mcm-icm-guide.md
必读：
- 文献查阅/综述写作 → 读取
references/literature-review.md（模型选择理由、参数溯源、引用格式必须有文献支撑）
根据当前阶段按需加载：
- 摘要相关 → 读取
references/abstract-writing.md - 模型检验相关 → 读取
references/model-validation.md - 需要句式参考 → 读取
references/common-phrases.md - 确定题型策略 → 读取
references/problem-type-strategies.md - 图表/代码规范 → 读取
references/figure-and-code-guide.md - 美赛 Memo/Letter → 读取
references/memo-writing.md
Step 3: 逐节指导或检查
按照论文结构顺序，对每个章节执行「目的 → 结构 → 写什么 → 红线」四步指导。具体规则见下文各节。
Step 4: 交付前自审（必做）
论文全文完成后，必须执行四轮系统性自审。加载以下两个文件：
references/self-review-framework.md— 四轮自审框架：论证逻辑 → 章节结构 → 表述质量 → 格式规范references/de-ai-writing.md— 去 AI 味写作指南：八类 AI 痕迹识别与去除 + 注入真实感
自审流程：
- 第一轮（论证逻辑）：检查每个主张是否有证据支撑，悬空主张/跳跃逻辑/循环论证必须修复
- 第二轮（章节结构）：检查摘要六要素、建模求解七要素是否完整
- 第三轮（表述质量）：对照
de-ai-writing.md逐条扫描 AI 痕迹，检查数据准确性 - 第四轮（格式规范）：图表编号、参考文献、页码等格式一致性
- 给出自审结论：✅ 通过 / ⚠️ 有条件通过 / ❌ 不通过
- 如为 ❌，修复后重新自审
每轮通过后才进入下一轮。如果时间紧迫，至少完成第一轮（论证逻辑）——这是区分三等奖和一等奖的关键差距。
论文结构模板
国赛 (CUMCM) 标准结构
| 章节 | 建议篇幅 | 核心要点 |
|---|---|---|
| 摘要 | 1页（500-800字） | 每问必须有量化结果 |
| 问题重述 | 0.5-1页 | 用自己的语言拆题，不是复制 |
| 问题分析 | 1-2页 | 为什么选这个模型，不是"将用什么方法"；建议放整体建模流程图 |
| 模型假设与符号说明 | 1页 | 每个假设服务于建模，拒绝废话 |
| 数据处理 | 2-4页 | 说明为什么这么处理（如内容少可嵌入第一个子问题中） |
| 问题一建模与求解 | 4-6页 | 目标→理由→公式→求解→结果→分析→检验 |
| 问题二建模与求解 | 5-7页 | 同上（每个子问题末尾嵌入灵敏度/误差分析） |
| 问题三建模与求解 | 5-7页 | 同上 |
| 模型评价与改进 | 1-2页 | 优缺点+检验结论汇总；评价本模型，不是评价算法 |
| 参考文献 | 0.5-1页 | ≥6条，含期刊论文和英文文献 |
| 附录 | 按需 | 完整代码+支撑材料列表 |
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .gitignore 102 B
- LICENSE 1.0 KB
- references/abstract-writing.md 9.0 KB
- references/common-phrases.md 19 KB
- references/cumcm-guide.md 8.3 KB
- references/de-ai-writing.md 13 KB
- references/figure-and-code-guide.md 22 KB
- references/literature-review.md 22 KB
- references/mcm-icm-guide.md 15 KB
- references/memo-writing.md 4.8 KB
- references/model-validation.md 7.2 KB
- references/problem-type-strategies.md 11 KB
- references/self-review-framework.md 9.4 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 343 lines · 202 tokens per session scan A 15bd01617fe7
math-modeling-paper is a skill published in the GitHub repository Lupynow/math-modeling-skills (335 stars, last pushed 1mo ago), licensed MIT. It adds 202 tokens to every session and 5,221 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
anti-defensive-writing-en
Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments. Treats the paper as a press conference, not a project summary, lab log, or self-audit: identify the single most publishable strength of the work and build the most favorable, complete, and persuasive…
anti-defensive-writing
A Chinese-language writing guide for presenting a research paper around its strongest supported contribution. It treats the paper as a focused academic presentation rather than a project diary or complete lab record.
mathmodel-skill
An end-to-end workflow for mathematical-modeling competitions, including CUMCM, MCM/ICM, and the Electrical Cup. It guides teams from choosing a problem through modeling, solving, checking, writing, rule compliance, and final review.
ez-math-model
Use when solving CUMCM, MCM, ICM, or other mathematical modeling tasks that need contest problem intake, model selection, Python solving, figures, paper writing, quality audit, and packaged deliverables.
brainstorming
Use when EZmathmodel model selection is unclear after the modeling decision tree, the problem spans multiple domains, or modeler needs several candidate approaches before writing modelingplan.md.
scientific-slides
Use when the user explicitly asks EZmathmodel to create defense slides, academic presentation slides, Beamer slides, or PPT after the modeling paper has been packaged.