Mathmodel Skill
handsomeZR-netizen/mathmodel-skill
CUMCM 国赛、MCM/ICM 美赛与电工杯数学建模竞赛的端到端协作工作流。Use when a user explicitly works on one of these modeling contests or asks to run/review a modeling-competition paper from problem selection through modeling…
CUMCM(全国大学生数学建模竞赛)真题全流程实战手册。用于完整打一场数模竞赛(环境准备→读题自查→建模出图→LaTeX论文→交叉审阅→填表→AI自查表终审→清理打包),内含题意理解红线、数值严谨性守则、去AIGC特征清单、写作规范、LaTeX编号与图表规范、2026…
$ npx skills add haoxilin/cumcm-live-workflow-skill --skill cumcm-live-workflow -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install haoxilin/cumcm-live-workflow-skill cumcm-live-workflow --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/haoxilin/cumcm-live-workflow-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cumcm-live-workflow .claude/skills/cumcm-live-workflow && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "cumcm-live-workflow" agent skill from https://github.com/haoxilin/cumcm-live-workflow-skill/tree/main/cumcm-live-workflow into .claude/skills/cumcm-live-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cumcm-live-workflow", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/haoxilin/cumcm-live-workflow-skill/tree/main/cumcm-live-workflowType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add haoxilin/cumcm-live-workflow-skill --skill cumcm-live-workflow -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install haoxilin/cumcm-live-workflow-skill cumcm-live-workflow --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/haoxilin/cumcm-live-workflow-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/cumcm-live-workflow .agents/skills/cumcm-live-workflow && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cumcm-live-workflow" agent skill from https://github.com/haoxilin/cumcm-live-workflow-skill/tree/main/cumcm-live-workflow into .agents/skills/cumcm-live-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cumcm-live-workflow", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add haoxilin/cumcm-live-workflow-skill --skill cumcm-live-workflow -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install haoxilin/cumcm-live-workflow-skill cumcm-live-workflow --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/haoxilin/cumcm-live-workflow-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/cumcm-live-workflow .cursor/skills/cumcm-live-workflow && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cumcm-live-workflow" agent skill from https://github.com/haoxilin/cumcm-live-workflow-skill/tree/main/cumcm-live-workflow into .cursor/skills/cumcm-live-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cumcm-live-workflow", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/haoxilin/cumcm-live-workflow-skill.git --path cumcm-live-workflow--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add haoxilin/cumcm-live-workflow-skill --skill cumcm-live-workflow -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install haoxilin/cumcm-live-workflow-skill cumcm-live-workflow --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/haoxilin/cumcm-live-workflow-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/cumcm-live-workflow .gemini/skills/cumcm-live-workflow && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cumcm-live-workflow" agent skill from https://github.com/haoxilin/cumcm-live-workflow-skill/tree/main/cumcm-live-workflow into .gemini/skills/cumcm-live-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cumcm-live-workflow", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install haoxilin/cumcm-live-workflow-skill cumcm-live-workflowInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add haoxilin/cumcm-live-workflow-skill --skill cumcm-live-workflow -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/haoxilin/cumcm-live-workflow-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/cumcm-live-workflow .github/skills/cumcm-live-workflow && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cumcm-live-workflow" agent skill from https://github.com/haoxilin/cumcm-live-workflow-skill/tree/main/cumcm-live-workflow into .github/skills/cumcm-live-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cumcm-live-workflow", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add haoxilin/cumcm-live-workflow-skill --skill cumcm-live-workflow -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install haoxilin/cumcm-live-workflow-skill cumcm-live-workflow --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/haoxilin/cumcm-live-workflow-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/cumcm-live-workflow .opencode/skills/cumcm-live-workflow && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cumcm-live-workflow" agent skill from https://github.com/haoxilin/cumcm-live-workflow-skill/tree/main/cumcm-live-workflow into .opencode/skills/cumcm-live-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cumcm-live-workflow", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
cumcm-live-workflowCUMCM(全国大学生数学建模竞赛)真题全流程实战手册。用于完整打一场数模竞赛(环境准备→读题自查→建模出图→LaTeX论文→交叉审阅→填表→AI自查表终审→清理打包),内含题意理解红线、数值严谨性守则、去AIGC特征清单、写作规范、LaTeX编号与图表规范、2026…
Cumcm Live Workflow is an agent skill from haoxilin/cumcm-live-workflow-skill. CUMCM(全国大学生数学建模竞赛)真题全流程实战手册。用于完整打一场数模竞赛(环境准备→读题自查→建模出图→LaTeX论文→交叉审阅→填表→AI自查表终审→清理打包),内含题意理解红线、数值严谨性守则、去AIGC特征清单、写作规范、LaTeX编号与图表规范、2026 AI合规与终审核查框架。触发于用户开始完整做真题、备赛训练、即将正式参赛,或要求按AI自查表对成品论文终审整改。启动关键词:国赛、数学建模竞赛、真题全流程、按竞赛标准走完流程、备赛、环境检查/检查环境/准备环境、按自查表审查——命中任一即启动,启用后第一步自动执行环境检查。
Its SKILL.md is about 3.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/sensitivity_framework.py`, `references/verify_pdf_metrics.py` and `references/verify_xlsx_rows.py`).
It sits in Documents & Office, covering LaTeX. It works with LaTeX and Python. The repository describes itself as: CUMCM 数学建模竞赛全流程实战技能手册:读题自查→建模出图→LaTeX论文→交叉审阅→填 result 模板→AI 自查表终审→清理打包。含题意理解红线、数值严谨性守则、去 AIGC 特征清单、2026 AI 合规与 26 条自查终审框架。 The licence is MIT.
9 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit f024d8b. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships script files (Python), which the agent can run.
Shell commands in SKILL.md call:
pythonpipwingetpdftotextFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
pypi.tuna.tsinghua.edu.cnFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Cumcm Live Workflow loads about 3.6k tokens when it runs, and up to ~5.2k if it reads all its reference files. Until then it costs about 74 tokens; SKILL.md has 743 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from haoxilin/cumcm-live-workflow-skill at commit f024d8b, republished under its MIT licence (© haoxilin). 743 words, ~3,611 tokens.
.claude/skills/cumcm-live-workflow/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.沉淀自多轮真实竞赛实战、交叉审阅与 AI 自查表终审整改,聚焦可执行的流程、坑位与质量门禁,通用适配任意 CUMCM 题目。
启动关键词(任一命中即启动本技能):
具体场景:
PROJECT_ROOT/<题号>/:原题 PDF、格式规范 doc、附件/题号/paper/;结果 xlsx 放题号目录0. 环境检查 → 1. 读题+格式规范 → 2. 逐问建模+出图(至少8图)
→ 3. LaTeX 论文 → 4. 交叉审阅(≥2轮)→ 5. 填 result 模板
→ 6. AI 自查表驱动终审 → 7. 清理+打包技能一经启用,立即后台探测本地环境,输出前置条件完成度清单:
| 组件 | 检测命令 | 通过标准 |
|---|---|---|
| Python | python --version | ≥ 3.12 |
| numpy / scipy / pandas / matplotlib / openpyxl | python -c "import numpy,scipy,pandas,matplotlib,openpyxl" | 全部可导入 |
| scikit-learn、black(可选) | 同上 | 可导入 |
| LaTeX(xelatex) | xelatex --version | MiKTeX 或 TeX Live 可用 |
| ctex 宏包 / 中文字体 | kpsewhich ctex.sty + SimSun/SimHei 存在 | 通过 |
| pdftotext / pdftoppm(可选) | --version | 通过 |
报告格式示例:
[环境检查] Python 3.12.10 ✓ | numpy ✓ | scipy ✓ | pandas ✓ | matplotlib ✓ | openpyxl ✓
LaTeX (xelatex) ✗ 未安装 | ctex 宏包 ✗ | pdftotext ✗(可选)
完成度:6/9 ✓ 必装组件缺失:LaTeX、ctex把清单交给用户确认("缺失组件是否自动安装?"),得到明确确认后执行:
pip install X -i https://pypi.tuna.tsinghua.edu.cn/simple(国内镜像)winget install MiKTeX.MiKTeX(或提示用户用官方安装器 / TeX Live);装后需刷新 PATH 或重开终端winget install poppler(可选组件,缺失可跳过,不阻塞)HTTPS_PROXY 环境变量并询问用户附录
├── 支撑材料文件列表(三线表:文件 | 用途 | 运行方式) ← 与压缩包逐项一致
├── 附录A:问题一求解主程序(p1_xxx.py) ← \lstinputlisting 全文
├── 附录B:问题二……(每个脚本独立一个附录小节)
├── …(一个源文件 = 一个附录小节,全部完整列出,禁止省略/截断/伪代码)
└── 附录N:图表生成脚本 / 检验脚本\lstinputlisting 列出全文,不得只贴核心片段、不得用"见代码文件"代替、不得伪代码冒充;脚本依赖的中间数据(npz/xlsx)一并列入支撑材料python xxx.py 运行,结果必须与论文数值一致(能复现);每个问题固定两步:先明确思路 → 再建模出图,逐问重复,最后才写论文。
savefig(..., bbox_inches='tight')plt.rcParams['font.sans-serif']=['SimHei','Microsoft YaHei'] + axes.unicode_minus=False#4472C4/#ED7D31/#70AD47,或 Nature 冷色 #0072B2/#009E73/#56B4E9,或美赛 O 奖 #2E5C8A/#E8743B);禁彩虹/荧光/高饱和;对比色区分度≥4.5:1#E0E0E0、坐标轴含单位、图例不遮数据;图内文字≥10pttabularx{\textwidth} 撑满版心;实在放不下就拆成多个分表,禁用 \resizebox 压缩(字号不一致,见 §3 表格宽度规范)\documentclass[zihao=-4,UTF8]{ctexart}(小四正文)\setCJKmainfont{SimSun};标题靠字号+加粗区分(SimSun 无粗体,会伪粗,正常)\fancyfoot[C]{\thepage}(ctexart 默认可能不显示页码,实测踩坑)\mathbf{A}、范数 \lVert;推导分步 align 展示,代数变换要"一目了然"\ref/\eqref 自动编号,严禁硬编码"图N/表N/式N"(插入新图表后硬编码编号会整体错位)成品必须是一份章节完整、编号统一的论文。骨架如下(内容随题目调整,层级不得删减):
摘要(五段式,独立一页)+ 关键词
1 问题重述与问题分析
1.1 问题背景与任务
1.2 问题分析(每问独立成段,交代"为什么选该模型")
2 模型假设与符号说明
2.1 模型假设((1)(2)...)
2.2 符号说明(三线表)
3 问题一:模型的建立与求解
3.1 模型建立(必要时 3.1.1/3.1.2 子步骤)
3.2 模型求解
3.3 结果与分析
4~7 问题二~五(同上,每问独立章节)
8 模型检验
8.1 误差分析 8.2 灵敏度分析 8.3 稳健性分析
9 模型评价与改进
9.1 模型优点 9.2 局限与改进
AI 工具使用声明
参考文献
附录(支撑材料文件列表 + 完整源码)1 / 1.1 / 1.1.1,禁止手写数字编号;若团队偏好"问题一/问题二"作章名,用手写汉字节名并与自动编号二选一全篇统一,禁止混用__main__ 块;打印与解析/已知答案的对比备注\ref/\eqref 自动编号:统一 \label{fig:xx}/\label{tab:xx} + 正文"图\ref{fig:xx}";若已硬编码,编译后用 pdftotext 对比实际编号逐一修正\\ 换行);图内子图标题也要有 (a)(b) 标记;caption 必须加 justification=centering(否则多行图题第二行左对齐)\section*{附录}(不编号)+ \subsection*{附录A:...}(手写字母),引言部分不占字母编号(避免"两个附录A")enumerate + label=(\arabic*) 阿拉伯小括号 (1)(2)(3)——2026-08 实战修订:经咨询相关人员确认列表与公式同为阿拉伯小括号不会混淆(公式单独右对齐带编号、列表条目在文内靠左),正式改用阿拉伯,勿再用罗马\begin{equation} 自动 (1)(2)(3);多行 align 必须 \notag 只留一个编号(三行约束不加 \notag 会各占一个公式号且无人引用,公式号整体跳跃)\[...\] 裸公式占位——评阅会逐条核对"公式漏编号";编译后用程序提取 (n) 检查 1..N 连续无缺号# 必须转义 \#;\boxed{} 除非风格要求否则别用\captionsetup{...,labelsep=space},渲染为"图1 标题""表2 标题"(不要"图1:");题注正文里也避免用冒号,用"(xx,单位)"括号式tabularx{\textwidth} 撑满版心(数据列 >{\centering\arraybackslash}X),左右边缘与正文对齐、无横向大留白;禁止个别表用 \resizebox 压缩(字号会和其他表不一致、评阅一眼看出);太宽放不下的表按时刻/列组拆成多个分表(如 6 列时刻拆 3+3、5 列拆 3+2),分表标题"表X(一)/(二)(列范围,单位)",字号统一 footnotesize\ttfamily(lmtt) 缺 θκπ∈≈₁₂ 等字形会渲染成空白(XeLaTeX 下 listings 的 literate 对 UTF-8 多字节字符无效,勿依赖);改用 \newfontfamily\listingmono{Consolas} + basicstyle=\listingmono(Consolas 覆盖除 ∈ 外全部常用符号,代码注释里的 ∈ 改写为 ASCII "in")\subsection*{附录X:...(script.py)} 超宽时在括号前加 \\ 换行用户会把论文交给其他 AI 审阅,反馈逐条处理。处理模板:
| 意见 | 处理 |
|---|---|
| 每条意见 | 定位→核实(跑代码/视觉QA)→修改→说明 |触发:拿到成品论文,要求"按自查表审查/自查"或提交前终审时。
AI工具使用详情.pdf(①工具名称/版本 ②使用目的环节 ③提示方式与过程 ④采纳/人工修改/核验情况,语言润色除外)一、AI 新规合规(4) 二、AI 幻觉与数据真实性(4) 三、建模逻辑与题意适配(5) 四、求解及结果合理性(3) 五、官方写作规范(6) 六、官方排版与页数(4) (自查表 docx 用 python-docx 提取段落+表格,表格行即 26 条核查条目)
(\arabic*) 阿拉伯小括号(2026-08 经咨询确认与公式号不混淆,勿用罗马);align 多行公式 \notag 只留一个号;图表引用全部 \ref/\eqref;正文每个展示公式都编号,勿用 \[...\] 裸公式^!/undefined/Overfull \hbox 分级(正文段落 >15pt 必修,代码附录长行可忽略)→ PDF 文本层抽查关键内容(AI 声明页码、新表页码、量化数字出现次数)tabularx X 列自动换行(比 resizebox 缩字清晰),超宽内容合并行'题号/xxx':Windows/Linux 通吃。禁止反斜杠和混合写法(实测漏网 62 处)Select-String -Path *.py -Pattern "\\\\" 确认无路径反斜杠残留pip install black + python -m black *.py),格式化后重跑验证功能未破坏| 文件 | 何时用 | 用法 |
|---|---|---|
references/verify_xlsx_rows.py | 填 result 模板后 | 校验 xlsx 行映射与数值:python references/verify_xlsx_rows.py <结果.xlsx> |
references/verify_pdf_metrics.py | 论文编译后交付前 | PDF 结构/越界/匿名/关键数字体检:python references/verify_pdf_metrics.py <论文.pdf> 412.47 0.4503 ... |
references/sensitivity_framework.py | 敏感性分析 | 参数扰动跑批框架:实现 run_metric 后运行 |
| 文件 | 用途 |
|---|---|
templates/格式规范.pdf | 当届官方《论文格式规范》,§1 读题时对照 |
templates/AI工具使用规定(2026试行).pdf | 2026 AI 合规红线,§6.1 终审时对照 |
templates/2026数学建模国赛AI自查表.docx | §6 AI 自查表驱动终审的核查清单 |
templates/2026数学建模国赛标准论文Word模板.doc | Word 排版参考(三线表/页码/样式),LaTeX 论文亦可对照其结构 |
templates/2026国赛国奖级论文AI自动优化升级提示词.docx | 国奖级九大模块升级标准(数据预处理/模型创新/求解/检验/写作/图表/排版)与 🔴🟡🟢 硬性指标核查清单——作为"国奖级指标"章节的展开细节,生成与终审阶段均可对照 |
WORKED_EXAMPLE.md:通用"水箱注水"案例,演示从题面→解析验证→数值求解→交叉验证→敏感性→结构化交付的完整链路。PROJECT_ROOT/
├── 题号/paper/main.pdf # 电子版论文(第1页摘要)
├── 支撑材料.zip # 代码+图表+结果(含 AI工具使用详情.pdf)
└── 题号/
├── 原题.pdf 格式规范.doc 附件/
├── p1_*.py ... p5_*.py # 核心可运行代码(black格式化+正斜杠)
├── result1/2/4.xlsx # 填好的结果模板
├── figures/ # 全部图 PNG+PDF
└── 建模结果汇总.md© haoxilin, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files (references) in cumcm-live-workflow of haoxilin/cumcm-live-workflow-skill.
Open the folder on GitHubat commit f024d8b
Cumcm Live Workflow next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Cumcm Live Workflow this skillhaoxilin/cumcm-live-workflow-skill | 181 | — | ~3.6k | Automated safety check: Pass | MIT | |
| Mathmodel SkillhandsomeZR-netizen/mathmodel-skill | 292 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Literature Surveyai4s-research/ai4s-skills | 237 | 2 repos | ~2k | Automated safety check: Pass | MIT | |
| My Mathmodel Agentchengyike20110519-create/MathModelRun | 128 | — | ~2.3k | Automated safety check: Pass | MIT | |
| MineruNebutra/MinerU-Skill | 123 | — | ~504 | Automated safety check: Pass | MIT | |
| My Mathmodel Agentchengyike20110519-create/MathModelRun | 128 | — | ~923 | Automated safety check: Pass | MIT |
handsomeZR-netizen/mathmodel-skill
CUMCM 国赛、MCM/ICM 美赛与电工杯数学建模竞赛的端到端协作工作流。Use when a user explicitly works on one of these modeling contests or asks to run/review a modeling-competition paper from problem selection through modeling…
ai4s-research/ai4s-skills
A skill your agent uses when the user wants a comprehensive literature survey on a specific research topic.
chengyike20110519-create/MathModelRun
Evidence-driven mathematical modeling contest workflow for CUMCM, MCM/ICM, HiMCM, Huawei Cup, and similar events.
Nebutra/MinerU-Skill
An AI-Native skill for parsing PDF / Office / image files into Markdown with MinerU — a fast, zero-config document parser for AI agents.
chengyike20110519-create/MathModelRun
Evidence-driven mathematical modeling contest workflow for Claude Code: decompose a problem, select baseline/primary/fallback model routes, validate PoCs, run reproducible Python/AMPL experiments…
lingzhi227/agent-research-skills
Sets up conference-specific LaTeX paper templates, checks a draft for formatting and submission issues, and auto-fixes common problems for venues like ICML, ICLR, NeurIPS, AAAI and ACL.
Categories
CUMCM(全国大学生数学建模竞赛)真题全流程实战手册。用于完整打一场数模竞赛(环境准备→读题自查→建模出图→LaTeX论文→交叉审阅→填表→AI自查表终审→清理打包),内含题意理解红线、数值严谨性守则、去AIGC特征清单、写作规范、LaTeX编号与图表规范、2026…. Cumcm Live Workflow is an agent skill from haoxilin/cumcm-live-workflow-skill.
Cumcm Live Workflow fits situations like: tasks that involve LaTeX.
Run `npx skills add haoxilin/cumcm-live-workflow-skill --skill cumcm-live-workflow -a claude-code`. Or copy the skill folder (cumcm-live-workflow in haoxilin/cumcm-live-workflow-skill) into .claude/skills/cumcm-live-workflow in your project. Claude Code loads it when a task matches its description.
Run `npx skills add haoxilin/cumcm-live-workflow-skill --skill cumcm-live-workflow -a codex`. Or copy the skill folder (cumcm-live-workflow in haoxilin/cumcm-live-workflow-skill) into .agents/skills/cumcm-live-workflow in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add haoxilin/cumcm-live-workflow-skill --skill cumcm-live-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cumcm-live-workflow, .gemini/skills/cumcm-live-workflow, .github/skills/cumcm-live-workflow and .opencode/skills/cumcm-live-workflow in your project.
Going by SKILL.md and its folder, Cumcm Live Workflow needs Python for the scripts in its folder and the command-line tools its instructions call (python, pip, winget and pdftotext). Our summary lists: Python 3.
SKILL.md names 1 domain. In commands or code: pypi.tuna.tsinghua.edu.cn; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Cumcm Live Workflow is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.6k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.6k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Cumcm Live Workflow: Mathmodel Skill (handsomeZR-netizen/mathmodel-skill, 292 stars), Literature Survey (ai4s-research/ai4s-skills, 237 stars), My Mathmodel Agent (chengyike20110519-create/MathModelRun, 128 stars) and Mineru (Nebutra/MinerU-Skill, 123 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
haoxilin (a GitHub user) maintains it in haoxilin/cumcm-live-workflow-skill, which has 181 GitHub stars. The repository was last updated on September 7, 2026.
Source: haoxilin/cumcm-live-workflow-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.