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-solvergit 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-solver)<a href="https://agentmods.dev/skills/lupynow/math-modeling-skills/math-modeling-solver"><img src="https://agentmods.dev/badge/skills/lupynow/math-modeling-skills/math-modeling-solver.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00186 | $0.04814 |
| Opus 5 | $0.00093 | $0.02407 |
| Sonnet 5 | $0.00037 | $0.00963 |
| Haiku 4.5 | $0.00019 | $0.00481 |
Grade A, and why
math-modeling-solver 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 7d 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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
数学建模竞赛解题指导
本 skill 提供的矩阵、cookbook、playbook、代码模板,全部是知识参考而非决策指令。 对于同一道赛题,不同队伍理应有不同的建模路径。矩阵里的推荐只是技术起点—— 你的任务是结合题目具体约束、数据特征和团队判断,做出有理由的选择,而非照搬推荐。
使用流程
收到解题任务后,按以下五阶段工作流操作。
Step 0: 判断用户入口
先判断用户在哪个阶段切入:
- 有新题目文本,从零开始 → 阶段1
- 已有问题分析结果,需要模型推荐 → 阶段2
- 需要先查文献再看选什么模型 → 阶段1.5
- 已确定模型,需要算法展开和代码 → 阶段3
- 建模已完成,需要衔接论文 → 阶段4
- 用户直接指定了模型名(如"用 GA 求解")→ 阶段3,跳过阶段1-2
- 用户输入匹配已知题型 → 加载对应 Playbook 获取完整解题示范(12 本 Playbook 覆盖国赛 A/B/C + 美赛 D/E/F 全部题型)
阶段识别规则
| 用户说 | 切入阶段 |
|---|---|
| "这道题怎么做" + 粘贴题目 | 阶段1 |
| "帮我分析这道题" | 阶段1 |
| "帮我搜一下类似问题的文献" | 阶段1.5 |
| "有没有类似题目的论文可以参考" | 阶段1.5 |
| "选什么模型好" | 阶段2 |
| "XGBoost 和随机森林怎么选" | 阶段2 |
| "帮我写 GA 代码" | 阶段3 |
| "这个公式怎么推导" | 阶段3 |
| "建模做完了,准备写论文" | 阶段4 |
| "帮我写摘要" | 阶段4 → 引导切换 paper skill |
阶段1:拆题分析
目标:判定每个子问题的数学本质,输出结构化的分析结果。
自动加载:references/problem-decomposition.md
步骤:
- 阅读用户提供的题目文本,提取关键信息
- 按
problem-decomposition.md的方法论,对每个子问题判定数学本质类型(共 12 种):- 预测/回归、分类/判别、评价/排序、优化/决策、机理/物理、聚类/分组、关联/因果、博弈/策略
- 几何/运动学、统计推断/实验设计、网络科学/图论、生态系统/环境
- 明确每个子问题的:输入变量、输出目标、约束条件
- 分析子问题之间的数据流和递进关系
- 输出结构化分析结果(见下方输出格式)
输出格式:
## 题目拆解
### 题目概况
- 比赛类型:[国赛/美赛]
- 题型:[A/B/C/D/E/F]
- 核心场景:[一句话概括]
### 子问题分析
#### 子问题一:[标题]
- 数学本质:[预测/评价/优化/机理/分类/...]
- 输入:[哪些变量/数据]
- 输出:[需要得到什么]
- 约束:[有哪些限制条件]
- 难点:[关键挑战]
#### 子问题二:[标题]
...
### 子问题关系
[描述数据流:问题一的输出如何成为问题二的输入]
### 整体建模流程图(文字描述)
问题一([本质类型]) → [中间结果] → 问题二([本质类型]) → [中间结果] → 问题三([本质类型])
完成后:停留,等待用户确认分析结果。确认后进入阶段1.5。
阶段1.5:文献检索
目标:用文献证据支撑模型选择——知道「别人怎么解这类题」再决定「我们怎么解」。
触发条件:阶段1完成后执行。如用户明确表示不需要文献检索(例如已自行检索、有明确模型偏好、或时间紧迫),可直接进入阶段2。
自动加载:../math-modeling-paper/references/literature-review.md(跨 skill 读取,仅加载第一部分「文献检索」,不展开全文)
🚨 硬性上限(防止无限搜索,必须遵守):
- 最多执行 5 次 WebSearch 调用(不是每个检索式都搜,是总共 5 次)
- 找到 5-8 篇高度相关论文后立即停止,不需要穷尽所有检索式
- T2/T3 回退仅在用户明确要求时执行,不要自动级联回退
- 如果前 3 次搜索已经找到满意结果,直接跳到步骤 4 整理证据,不再继续搜
步骤:
- 从阶段1第4步已生成的检索关键词中,只挑最核心的 2-3 组(不是全部),中英文各至少 1 组——英文覆盖国际期刊,中文覆盖知网/万方/维普的核心期刊
- 告知用户:简要列出建议的 2-3 组检索式(中英文混合即可,不需要各 3-5 组),说明信源分级。详见
literature-review.md1.3 节 - 询问用户:「是否需要我代为搜索?预计 3-5 次搜索即可覆盖核心文献(中英文各半)。如你已自行检索过,可以直接告诉我找到的文献,我们跳过这步。」
- 用户同意 → 执行步骤 4,英文用 Google Scholar / Semantic Scholar,中文直接用中文关键词 WebSearch(覆盖知网/万方/维普的公开页面),不要走 T1→T2→T3 三级级联
- 用户拒绝或已有文献 → 跳过搜索,直接请用户提供找到的文献,进入步骤 5
- 执行搜索(遵守硬性上限):
- 中英文分配:5 次搜索中,英文 2-3 次 + 中文 2-3 次(中文搜索直接在 WebSearch 中用中文关键词,如
"玻璃文物" "成分分类" 机器学习) - 中文期刊识别:搜索结果中来自
cnki.net、wanfangdata.com.cn、cqvip.com的链接通常对应知网/万方/维普收录论文。优先采信标注为「核心期刊」「EI 收录」「SCI 收录」「CSSCI」「CSCD」的中文论文 - 每次搜索后检查:是否已找到 5+ 篇相关论文(中英文合计)?是→停止搜索
- 是否已用满 5 次 WebSearch?是→停止搜索
- 从检索结果中提取:类似问题用了哪些方法?各方法效果对比?是否有公认基准方法?
- 标注期刊含金量:英文优先 SCI Q1/Q2,中文优先一级学报/核心期刊(见
literature-review.md1.5 节期刊分级),普刊/会议短文尽量不引用
- 中英文分配:5 次搜索中,英文 2-3 次 + 中文 2-3 次(中文搜索直接在 WebSearch 中用中文关键词,如
- 输出文献证据摘要(必须标注期刊级别):
What ships with it
55 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.
- LICENSE 1.0 KB
- README.md 2.1 KB
- references/code-templates/matlab/evaluation/ahp_template.m 770 B
- references/code-templates/matlab/evaluation/topsis_template.m 1.1 KB
- references/code-templates/matlab/ml/random_forest_template.m 1.5 KB
- references/code-templates/matlab/optimization/ga_template.m 4.6 KB
- references/code-templates/matlab/optimization/monte_carlo_template.m 6.0 KB
- references/code-templates/matlab/optimization/pso_template.m 2.6 KB
- references/code-templates/matlab/optimization/sa_template.m 3.8 KB
- references/code-templates/python/evaluation/ahp_template.py 2.4 KB runs code
- references/code-templates/python/evaluation/entropy_weight_template.py 1.8 KB runs code
- references/code-templates/python/evaluation/fuzzy_eval_template.py 3.5 KB runs code
- references/code-templates/python/evaluation/grey_relational_template.py 9.6 KB runs code
- references/code-templates/python/evaluation/topsis_template.py 3.7 KB runs code
- references/code-templates/python/mechanistic/food_web_ode_template.py 10 KB runs code
- references/code-templates/python/mechanistic/ode_solver_template.py 13 KB runs code
- references/code-templates/python/ml/anova_template.py 12 KB runs code
- references/code-templates/python/ml/gmm_em_template.py 10 KB runs code
- references/code-templates/python/ml/markov_chain_template.py 8.1 KB runs code
- references/code-templates/python/ml/random_forest_template.py 2.2 KB runs code
- references/code-templates/python/ml/time_series_forecast_template.py 14 KB runs code
- references/code-templates/python/ml/xgboost_template.py 4.6 KB runs code
- references/code-templates/python/optimization/cvar_robust_opt_template.py 12 KB runs code
- references/code-templates/python/optimization/ga_template.py 6.8 KB runs code
- references/code-templates/python/optimization/integer_programming_template.py 7.4 KB runs code
- references/code-templates/python/optimization/monte_carlo_template.py 7.9 KB runs code
- references/code-templates/python/optimization/network_flow_template.py 9.8 KB runs code
- references/code-templates/python/optimization/nsga2_template.py 11 KB runs code
- references/code-templates/python/optimization/pso_template.py 3.9 KB runs code
- references/code-templates/python/optimization/sa_template.py 2.7 KB runs code
- references/code-templates/python/optimization/system_dynamics_template.py 8.2 KB runs code
- references/cookbook-clustering.md 6.9 KB
- references/cookbook-evaluation.md 4.4 KB
- references/cookbook-game-theory.md 5.3 KB
- references/cookbook-mechanistic.md 33 KB
- references/cookbook-ml.md 7.1 KB
- references/cookbook-network.md 5.8 KB
- references/cookbook-optimization.md 5.5 KB
- references/cookbook-statistical.md 19 KB
- references/mcm-specific-guide.md 4.1 KB
- references/model-selection-matrix.md 15 KB
- references/paper-bridge.md 3.7 KB
- references/playbooks/playbook-data-insight.md 16 KB
- references/playbooks/playbook-evaluation-decision.md 12 KB
- references/playbooks/playbook-geometric-kinematics.md 6.3 KB
- references/playbooks/playbook-mcm-environmental.md 5.6 KB
- references/playbooks/playbook-mcm-network.md 10 KB
- references/playbooks/playbook-mcm-policy.md 4.9 KB
- references/playbooks/playbook-ml-classification.md 10 KB
- references/playbooks/playbook-ml-regression.md 13 KB
- references/playbooks/playbook-path-planning.md 12 KB
- references/playbooks/playbook-physics-ode.md 12 KB
- references/playbooks/playbook-scheduling-opt.md 11 KB
- references/playbooks/playbook-strategy-game.md 13 KB
- references/problem-decomposition.md 8.2 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.
- 7d ago First seen · 326 lines · 186 tokens per session scan A 1e2fbea13d4c
math-modeling-solver is a skill published in the GitHub repository Lupynow/math-modeling-skills (308 stars, last pushed 1mo ago), licensed MIT. It adds 186 tokens to every session and 4,814 once invoked, about $0.0009 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
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.
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.
math-modeling-growth
A skill that turns the results and decisions from a real mathematical modelling project into a plain-language learning or review report. Mathematical modelling uses mathematical methods to represent and study a real situation.
weight-loss-learn
A guided course on sustainable fat loss that adapts to your level and tracks your progress. It teaches the principles behind weight change and long-term weight maintenance.