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 yushui2022/MathModel-Skill --skill storegit clone --depth 1 https://github.com/yushui2022/MathModel-SkillWrote 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/yushui2022/mathmodel-skill/store)<a href="https://agentmods.dev/skills/yushui2022/mathmodel-skill/store"><img src="https://agentmods.dev/badge/skills/yushui2022/mathmodel-skill/store/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/yushui2022/mathmodel-skill/store"><img src="https://agentmods.dev/badge/skills/yushui2022/mathmodel-skill/store.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00086 | $0.01200 |
| Opus 5.5 | $0.00034 | $0.00480 |
| Sonnet 5.5 | $0.00017 | $0.00240 |
| Haiku 4.5 | $0.00009 | $0.00120 |
Grade A, and why
MathModel Skill Standard 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 5d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MathModel Skill Standard
这是 MathModel Skill 标准档(Standard 2.4 开发版)的商店条目。包内是十个协作技能加一个入口路由技能,按 S0-S8 阶段用文件和 SHA-256 交接:先真实计算,再正式成文,最后过 Word/PDF 渲染检查。
它不是一个"一键生成论文"的提示词。Agent 必须运行真实代码、保存结果证据,并通过证据门禁后才允许进入正式写作。
包内结构
SKILL.md 本条目说明(商店展示用)
install.py 安装器
requirements.txt 基础依赖
requirements-modeling.txt 优化求解可选依赖
VERSION
skills/
├── paper-workflow-orchestrator/ 入口:S0-S8 路由
├── problem-doc-model-selector/ S1 题意分析
├── modeling-paper-rubric-and-model-selector/ S2 模型路线与评分对齐
├── data-cleaning-and-visualization/ S3 数据清洗与图表
├── model-code-and-result-generator/ S4/S5 建模代码与真实运行
├── quality-assurance-auditor/ S6 证据门禁
├── paper-formal-writer/ S7/S8 正式写作与格式渲染检查
├── paper-micro-unit-generator/ 单章局部修复(非正式草稿)
├── context-memory-keeper/ 中断续跑记忆
└── authoritative-data-harvester/ 必要的公开外部数据
docs/ 安装、写作、契约、输出目录等说明
安装
方式一(推荐,支持托管升级):解压到独立目录,准备好另一个赛题项目目录,然后执行
python "<解压目录>/install.py" --project-root "<赛题目录>" --platform codex --check
python "<解压目录>/install.py" --project-root "<赛题目录>" --platform codex
--platform 取 codex(安装到 .agents/skills/)、claude(.claude/skills/)或 trae(.trae/skills/)。安装器只复制技能并记录哈希,不联网,不覆盖项目根配置、依赖文件、赛题或旧结果。
方式二(手动,不纳入托管升级):把 skills/ 下的十个目录整体复制到上面某一个位置,不能只复制 SKILL.md。
依赖在赛题项目的 Python 环境里单独安装:
python -m pip install -r "<解压目录>/requirements.txt"
python -m pip check
使用
- 在赛题项目根目录建立
problem_files/,放入赛题、官方附件与数据。 - 对 Agent 说:
请使用 paper-workflow-orchestrator 完成这个数学建模项目。
赛题和官方附件已放在 problem_files/。
先预检输入,再按 S0-S8 执行,必须真实运行代码并保留结果证据。
采用完整章节写作,允许分多轮完成,最后统一全文,不要只输出摘要或拼接微单元。
请核对当年赛题的篇幅和格式规则,不自行降低为短报告。
所有赛题产物写入 paper_output/;证据、写作与 Word/PDF 检查未通过,不要称为最终稿。
主要产物:paper_output/final_paper.docx、final_paper_source.md、qa/rendered/final_paper.pdf,以及 code/、results/、figures/、format_check_report.json。
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.
- 5d ago First seen · 79 lines · 86 tokens per session scan A 5ea47a1c5d18
MathModel Skill Standard is a skill published in the GitHub repository yushui2022/MathModel-Skill (456 stars, last pushed 3d ago), licensed MIT. It adds 86 tokens to every session and 1,200 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-23.
Other skills, from other repositories
pydicom
Reads, inspects, writes, transforms, and preflights local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
pptx-posters
Creates and audits editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. Used when the requested deliverable is a PowerPoint research/conference poster and exact physical, printer, accessibility, provenance, and package-security checks are required.
nature-paper2word
A document conversion workflow that turns an academic Markdown manuscript into a Word .docx file. It supports specified academic formatting, equations, tables, references, cross-references, and export checks.
nature-paper-trans
A workflow for translating selected pages or a complete English research-paper PDF into a simplified-Chinese, image-based PDF. bioRxiv is not mentioned in the provided details; the workflow applies to research-paper PDFs generally.
extracting-lab-tables
Detects and extracts tabular laboratory panels from PDFs, scans, and images into structured rows ready for OpenMed and FHIR. Use when the user has a CBC, CMP, lipid panel, or other lab report as a scanned image / PDF / spreadsheet and needs the test name, value, unit, reference range, and abnormal flag as clean rows.…
figures
Makes publication-quality plots from data with matplotlib, learning curves, scaling laws, benchmark and ablation comparisons, Pareto trade-offs, heatmaps and confusion matrices, sized for the page, vector, with uncertainty shown. Use whenever results are plotted, charted or visualized for a paper, report or answer, or…