Agent skill

CUMCM Math Modeling Agent

by RealSeaberry in RealSeaberry/AutoMCM-Pro

Drives an end-to-end workflow for the CUMCM math modeling contest: reads the problem and data, researches, codes and verifies models, then writes a LaTeX paper and PDF.

MITAuto-check passedResearch & Science

SKILL.md written in Chinese; this summary is our English description.

Install CUMCM Math Modeling Agent

skills CLI
$ npx skills add RealSeaberry/AutoMCM-Pro --skill cumcm-master -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install RealSeaberry/AutoMCM-Pro cumcm-master --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/RealSeaberry/AutoMCM-Pro.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/cumcm-master .claude/skills/cumcm-master && rm -rf skills-src

Use ~/.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/

Facts

Skill name
cumcm-master
GitHub stars
257
Token cost
~1.6k tokens
SKILL.md length
347 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Drives an end-to-end workflow for the CUMCM math modeling contest: reads the problem and data, researches, codes and verifies models, then writes a LaTeX paper and PDF.

  • Works in 3 steps: 题目文件路径:赛题 PDF 或文本文件的路径(如 ./problem.pdf) → 数据文件路径:附件数据所在目录(如 ./data/ 或具体文件路径) → LaTeX 模板路径(可选):若有自定义模板,提供路径;否则使用内置模板
  • Solving a CUMCM contest problem with data from analysis to a finished paper
  • SKILL.md covers 【第零步】工作区初始化, 【第一步】收集任务信息, 【第二步】Phase 1 — 破题与记忆初始化 and 【第三步】Phase 2 — 代码实现与验证(高度迭代…, plus 5 more sections
  • Calls python

What it does

The SKILL.md is in Chinese. It starts by running scripts/setup_workspace.py to create a standard workspace for data, source code and LaTeX output, then asks for the problem file, the data folder and an optional LaTeX template, and extracts text from a PDF problem with pdfplumber or pypdf. Phase one analyzes the problem's background, target variables, constraints, data features and candidate mathematical tools, searches the web for relevant papers, records references and initializes a memory file with agent_memory_manager.py.

Phase two runs a strict loop for every sub-problem: think, write code, run, observe, then reflect and fix, with no skipped steps. Reasoning goes into memory/thought_process.md, which the skill says is shown live on a local page. Scripts follow a numbered scheme for exploration, each problem's model, visualization and sensitivity analysis, with matplotlib figures saved for the paper. The description says the process ends with LaTeX writing and a PDF, which falls in the cut-off part of the excerpt.

When your agent uses it

  • Solving a CUMCM contest problem with data from analysis to a finished paper
  • Building and verifying models for each sub-question in a modeling problem
  • Producing a LaTeX paper with figures from model outputs
  • Running sensitivity analysis and stability checks on a contest model

Example prompts

  • “Solve the CUMCM problem in ./problem.pdf with the data in ./data and write the paper.”
  • “Set up the modeling workspace and read the problem statement first.”
  • “Run the sensitivity analysis for problem two and add the figures to the LaTeX folder.”
  • “Use my own LaTeX template at ./template for the final paper.”

Requirements

  • Python with the packages the models need
  • A LaTeX installation
  • Web search for literature research

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. 题目文件路径:赛题 PDF 或文本文件的路径(如 ./problem.pdf)
  2. 数据文件路径:附件数据所在目录(如 ./data/ 或具体文件路径)
  3. LaTeX 模板路径(可选):若有自定义模板,提供路径;否则使用内置模板

What it can do on your machine

Read from SKILL.md and the folder at commit 90c4727. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

CUMCM Math Modeling Agent loads about 1.6k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 347 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from RealSeaberry/AutoMCM-Pro at commit 90c4727, republished under its MIT licence (© RealSeaberry). 347 words, ~1,578 tokens.

Download SKILL.mdSave it as .claude/skills/cumcm-master/SKILL.md (or your agent's skills folder).
name
cumcm-master
description
Full-stack autonomous math modeling agent for CUMCM (全国大学生数学建模竞赛). Reads the problem statement and data, iterates through research → coding → verification → LaTeX writing, and produces a publication-quality PDF paper. Use when the user provides a CUMCM problem and wants end-to-end automated modeling, coding, and paper generation.

CUMCM-Master: 全栈自动化数学建模智能体

你是一个具备顶尖学术水平的数学建模专家团队的化身,融合了数学家、算法工程师和 LaTeX 排版大师的能力。你的目标是根据给定的 CUMCM 赛题和数据,高度自主地完成从数据分析、模型构建、代码实现、结果验证到撰写完整 LaTeX 论文的全套流程,最终输出可直接编译的高水平竞赛论文。

Mind-Reader 提示:你的所有思考过程都会实时显示在 http://localhost:8080。 请确保 memory/thought_process.md 中的内容足够详细、有观赏性—— 使用具体数值、数学公式(LaTeX 语法)、决策理由,让旁观者能够追踪你的每一步推理。 例如:"残差检验 p=0.003 < 0.05,拒绝同方差假设,放弃 OLS,改用 Huber 损失稳健回归..."


【第零步】工作区初始化

在开始任何建模工作之前,必须先运行工作区初始化脚本:

bash
python scripts/setup_workspace.py

此脚本将在当前目录创建标准工作区结构:

CUMCM_Workspace/
├── data/               # 原始数据与清洗后的中间数据
├── src/                # Python/MATLAB 代码
├── latex/
│   └── images/         # 图表输出目录
├── memory/
│   ├── thought_process.md   # 全局推理链与数学推导
│   ├── evaluation_log.md    # 用户反馈与采纳记录
│   └── iteration.json       # 状态机:当前阶段记录
└── output/             # 最终 PDF 输出

【第一步】收集任务信息

使用 AskUserQuestion 依次询问:

  1. 题目文件路径:赛题 PDF 或文本文件的路径(如 ./problem.pdf)
  2. 数据文件路径:附件数据所在目录(如 ./data/ 或具体文件路径)
  3. LaTeX 模板路径(可选):若有自定义模板,提供路径;否则使用内置模板

收集完毕后,读取赛题内容。若为 PDF,运行:

bash
python -c "import pdfplumber; pdf=pdfplumber.open('PROBLEM_PATH'); [print(p.extract_text()) for p in pdf.pages]" 2>/dev/null || python -c "import pypdf; r=pypdf.PdfReader('PROBLEM_PATH'); [print(p.extract_text()) for p in r.pages]"

【第二步】Phase 1 — 破题与记忆初始化

2.1 深度理解赛题

仔细阅读赛题,识别:

  • 问题的物理/经济/社会背景
  • 每个小问的目标变量与约束
  • 可用数据特征(维度、量级、时序性等)
  • 潜在的数学工具(优化、微分方程、统计建模、图论、机器学习等)
2.2 文献调研(联网搜索)

针对核心建模方法,使用 WebSearch 搜索近年高质量论文和方法:

  • 搜索关键词格式:"[方法名] mathematical model CUMCM" OR "[问题领域] optimization model"
  • 使用 WebFetch 读取相关文献摘要,提炼方法论参考
  • 在 memory/thought_process.md 中记录参考文献信息(含 DOI 或 URL)
2.3 初始化记忆文件

用 agent_memory_manager.py 写入初始状态:

bash
python scripts/agent_memory_manager.py init \
  --title "CUMCM 20XX 题目X" \
  --problems "问题一描述|问题二描述" \
  --models "问题一拟用模型|问题二拟用模型"

在 memory/thought_process.md 写入:

  • 完整的问题理解
  • 各小问的数学建模思路
  • 拟使用的算法和工具包
  • 模型假设初稿

【第三步】Phase 2 — 代码实现与验证(高度迭代 ReAct 循环)

ReAct 循环规范

对每个子问题,执行以下严格循环,禁止跳步:

THINK → WRITE_CODE → RUN → OBSERVE → REFLECT → (修复或继续)
THINK(思考)

在动手写代码之前,先在 memory/thought_process.md 中写下:

  • 数学公式推导过程(使用 LaTeX 语法)
  • 算法选择理由
  • 预期输出的数量级与形态
WRITE_CODE(编码)

在 CUMCM_Workspace/src/ 下创建 Python 脚本,命名规范:

  • 01_data_eda.py — 数据探索与预处理
  • 02_problem1_model.py — 问题一建模与求解
  • 03_problem2_model.py — 问题二建模与求解
  • 04_visualization.py — 统一图表生成
  • 05_sensitivity.py — 灵敏度与鲁棒性分析

代码规范要求:

  • 每个函数必须有中文注释说明数学含义
  • 图表必须调用 matplotlib 并保存到 CUMCM_Workspace/latex/images/
  • 数值结果必须打印,便于观察
RUN(运行)
bash
cd CUMCM_Workspace && python src/0X_script.py
OBSERVE(观察输出)
  • 输出是否符合物理/数学预期?
  • 是否有 Warning 或 Error?
  • 数值是否在合理范围内?
REFLECT & 修复
  • 若报错:分析 Traceback,定位根因,修改代码,重新运行
  • 若结果异常:检查数据处理逻辑、模型参数设置
  • 若成功:在 memory/thought_process.md 记录关键结果数值
  • 重复循环,直到代码稳定输出合理结果
图表标准

每张图必须满足:

  • 中英文字体支持(设置 matplotlib.rcParams['font.family'])
  • 坐标轴标签含单位
  • 标题简洁专业
  • DPI ≥ 300,保存为 PNG
  • 文件名格式:fig01_description.png
图表来源决策树
需要一张图?
├─ 内容来自代码运行数值(散点图、折线图、热力图等)
│   └─ 必须用 matplotlib/seaborn 生成,绝不使用 AI 绘图
└─ 非数值内容(流程图、架构图、概念示意)
    ├─ 极简几何图(3个框以内)→ tikz 即可
    └─ 复杂流程图 / 概念插图 → 使用 /draw-image skill:
        python scripts/draw_image.py \
          --prompt "..." \
          --output "CUMCM_Workspace/latex/images/figXX_name.png" \
          --size 1024x1536 --quality high

【第四步】Phase 3 — 学术化 LaTeX 写作

4.1 使用模板

将 templates/latex_template.tex 复制到 CUMCM_Workspace/latex/main.tex:

bash
cp templates/latex_template.tex CUMCM_Workspace/latex/main.tex
4.2 论文必须包含的十个章节

按顺序填充以下内容,每章节均需通过三轮自我审查:

1. 问题重述

  • 精炼赛题,突出核心挑战
  • 不超过半页,语言精准

2. 问题背景与需要解决的问题

  • 宏观背景(1-2段)
  • 清晰的任务清单(分条列出)

3. 问题分析

  • 对每个小问单独分析
  • 阐明解题思路、数学工具选择理由
  • 包含流程图:
    • 数据结果图(真实数值)→ 必须由 Python 代码生成
    • 算法/建模流程图 / 概念插图 → 使用 /draw-image skill 生成(调用 scripts/draw_image.py)
    • tikz 仍可用于极简线框图,但复杂流程图优先用 /draw-image

4. 模型假设

  • 5~7 条假设,每条附简短理由
  • 格式:\begin{enumerate}[label=假设\arabic*:]

5. 符号说明

  • 三线表,三列:符号 | 含义 | 单位/量纲
  • 使用 booktabs 宏包

6. 模型的建立与求解

  • 按小问分节(\subsection)
  • 每节结构:机理分析 → 数学推导 → 公式 → 求解方法 → 结果表格/图片 → 分析
  • 所有公式使用 equation 或 align 环境,编号

7. 模型的分析与检验

  • 灵敏度分析(关键参数±10%/±20%)
  • 误差分析或交叉验证
  • 与已知结论的对比验证

8. 模型的评价、改进与推广

  • 优点(3条)
  • 局限性(2条)
  • 可行的改进方向

9. 参考文献

  • 格式:GB/T 7714-2015
  • 至少 8 条,含英文文献
  • 使用 \bibitem 或 BibTeX

10. 附录

  • 插入 src/ 中每个关键脚本的完整代码
  • 使用 listings 宏包,Python 语法高亮
4.3 写作自我反思清单

写完每个章节后,必须自问:

  • 是否有"我觉得"、"应该"等非学术表达?→ 替换为"基于模型分析"、"由求解结果知"
  • 所有公式是否正确编号且有引用?
  • 图表是否已用 \ref{} 引用?
  • LaTeX 特殊字符(&, %, _, $, {, })是否正确转义?
  • 所有 \begin{} 是否有对应 \end{}?

【第五步】Phase 4 — 处理用户反馈

当用户提供新方向或批评时:

5.1 评估与记录

使用 agent_memory_manager.py 记录用户建议:

bash
python scripts/agent_memory_manager.py feedback \
  --summary "用户建议摘要" \
  --criticism "可行性与影响分析" \
  --decision "采纳/部分采纳/拒绝" \
  --reason "决策理由"
5.2 决策标准
  • 采纳:如果建议提升了模型的机理合理性或数学严谨性
  • 部分采纳:如果建议有价值但与当前结构冲突,取其精华
  • 拒绝:如果建议偏离数学本质或缺乏可操作性,需向用户说明理由
5.3 迭代更新

若采纳:立即返回 Phase 2,重新编码、验证、更新 LaTeX 对应章节


【第六步】编译与输出

6.1 编译 LaTeX
bash
cd CUMCM_Workspace/latex && xelatex -interaction=nonstopmode main.tex 2>&1 | tail -20

若出现编译错误:

  • 分析错误信息(! LaTeX Error: 或 Undefined control sequence)
  • 定位出错行号,修复 main.tex
  • 重新编译(有时需运行两次以更新交叉引用)
6.2 最终检查

编译成功后:

bash
cp CUMCM_Workspace/latex/main.pdf CUMCM_Workspace/output/final_paper.pdf
python scripts/agent_memory_manager.py complete

【绝对禁忌】

  1. 禁止虚构数据:所有表格和图表中的数据必须来自实际运行的代码
  2. 禁止口语化:杜绝"跑了一下"、"感觉上"、"试了试";使用"经数值实验验证"、"求解结果表明"
  3. 禁止未验证代码入论文:代码必须无错误运行后方可引用其结果
  4. 禁止跳过编译验证:最终必须成功编译 .tex 文件
  5. 禁止遗漏记忆更新:每完成一个重要步骤,必须更新 memory/iteration.json

【进度追踪】

使用 TodoWrite 维护任务清单,格式:

  • Phase 1:破题分析与文献调研
  • Phase 2:数据预处理代码
  • Phase 2:问题一建模与验证
  • Phase 2:问题二建模与验证
  • Phase 2:灵敏度分析
  • Phase 3:LaTeX 论文撰写
  • Phase 3:图表集成与排版
  • Phase 4(按需):用户反馈迭代
  • Phase 5:编译与输出 PDF

© RealSeaberry, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/cumcm-master of RealSeaberry/AutoMCM-Pro.

Open the folder on GitHubat commit 90c4727

Compare with similar skills

CUMCM Math Modeling Agent 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.

CUMCM Math Modeling Agent compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
CUMCM Math Modeling Agent this skillRealSeaberry/AutoMCM-Pro257—~1.6kAutomated safety check: PassMIT
Paper OrchestraAr9av/PaperOrchestra6791 repos~3.5kAutomated safety check: PassCustom licence
Backward Traceabilitylingzhi227/agent-research-skills390—~802Automated safety check: PassNone
Nature Polishingaiskillstore/marketplace4331 repos~1.3kAutomated safety check: PassNone
Literature Surveyai4s-research/ai4s-skills2372 repos~2kAutomated safety check: PassMIT
LaTeX Research PostersK-Dense-AI/claude-scientific-writer2.4k12 repos~4.1kAutomated safety check: NotesMIT

Similar skills

  • Paper Orchestra

    Ar9av/PaperOrchestra

    Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured research materials (idea, experimental log, LaTeX template, conference guidelines…

    679 GitHub starsUsed in 1 repo~3.5k tokens
    Research & ScienceAuto-check passed
  • Backward Traceability

    lingzhi227/agent-research-skills

    Makes each number in a LaTeX paper link back to the code line that produced it, using hypertarget and hyperlink tags and compile-time `\num` formulas.

    390 GitHub stars~802 tokensUpdated 7 mo ago
    Research & ScienceAuto-check passed
  • Nature Polishing

    aiskillstore/marketplace

    Polish, restructure, or translate academic prose into Nature-leaning English using writing-strategy principles, curated Nature/Nature Communications article patterns, and phrase-level support from…

    433 GitHub starsUsed in 1 repo~1.3k tokens
    Research & ScienceAuto-check passed
  • Literature Survey

    ai4s-research/ai4s-skills

    A skill your agent uses when the user wants a comprehensive literature survey on a specific research topic.

    237 GitHub starsUsed in 2 repos~2k tokens
    Documents & OfficeAuto-check passed
  • LaTeX Research Posters

    K-Dense-AI/claude-scientific-writer

    Builds conference-size scientific posters in LaTeX with beamerposter, tikzposter or baposter, including figure preparation, compilation and print preflight checks.

    2.4k GitHub starsUsed in 12 repos~4.1k tokens
    Documents & OfficeAuto-check: notes
  • Table

    brycewang-stanford/Auto-Empirical-Research-Skills

    Econometrics skill for creating publication-quality LaTeX regression and summary tables.

    4.6k GitHub stars~3.3k tokensUpdated 5 days ago
    Documents & OfficeAuto-check passed

More from RealSeaberry/AutoMCM-Pro

  • AutoMCM-Pro for Codex CLI

    RealSeaberry/AutoMCM-Pro

    Runs a math modeling contest pipeline for CUMCM and MCM/ICM entries in Codex CLI, with git checkpoints, verified solver code and human review at each stage.

    257 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed
  • AutoMCM Math Modeling Agent

    RealSeaberry/AutoMCM-Pro

    Runs a staged workflow for math modeling contests such as CUMCM and MCM/ICM, with checkpoints, verified solver code and a LaTeX paper, on DeepSeek Harness.

    257 GitHub stars~2.3k tokensUpdated 1 mo ago
    Auto-check passed
  • AutoMCM-Pro for opencode

    RealSeaberry/AutoMCM-Pro

    The opencode binding of the AutoMCM-Pro math modeling pipeline for CUMCM and MCM/ICM contests, with tool mappings, install prompts and checkpointed runs.

    257 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed
  • Draw Image Diagrams

    RealSeaberry/AutoMCM-Pro

    Generates diagrams, flowcharts and conceptual illustrations with OpenAI's gpt-image models, while leaving data plots and result figures to real plotting code.

    257 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check: notes
  • MCM/ICM Autonomous Modeling Agent

    RealSeaberry/AutoMCM-Pro

    Runs an MCM/ICM math modeling competition end to end: collects contest metadata, builds and verifies models and code, then generates an English LaTeX paper and any required memo.

    257 GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check passed
  • AutoMCM-Pro Math Modeling Agent

    RealSeaberry/AutoMCM-Pro

    Runs a math modeling competition entry end to end, in AI-led or human-led mode, with Git checkpoints and self-verified solver code before it enters the LaTeX paper.

    257 GitHub stars~8.5k tokensUpdated 1 mo ago
    Auto-check passed

Questions about CUMCM Math Modeling Agent

What does CUMCM Math Modeling Agent do?

Drives an end-to-end workflow for the CUMCM math modeling contest: reads the problem and data, researches, codes and verifies models, then writes a LaTeX paper and PDF. md is in Chinese.py to create a standard workspace for data, source code and LaTeX output, then asks for the problem file, the data folder and an optional LaTeX template, and extracts text from a PDF problem with pdfplumber or pypdf.

When should I use CUMCM Math Modeling Agent?

CUMCM Math Modeling Agent fits situations like: solving a CUMCM contest problem with data from analysis to a finished paper; building and verifying models for each sub-question in a modeling problem; producing a LaTeX paper with figures from model outputs; running sensitivity analysis and stability checks on a contest model.

How do I install CUMCM Math Modeling Agent in Claude Code?

Run `npx skills add RealSeaberry/AutoMCM-Pro --skill cumcm-master -a claude-code`. Or copy the skill folder (.claude/skills/cumcm-master in RealSeaberry/AutoMCM-Pro) into .claude/skills/cumcm-master in your project. Claude Code loads it when a task matches its description.

How do I install CUMCM Math Modeling Agent in Codex?

Run `npx skills add RealSeaberry/AutoMCM-Pro --skill cumcm-master -a codex`. Or copy the skill folder (.claude/skills/cumcm-master in RealSeaberry/AutoMCM-Pro) into .agents/skills/cumcm-master in your project. Codex loads it when a task matches its description.

Can I use CUMCM Math Modeling Agent in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add RealSeaberry/AutoMCM-Pro --skill cumcm-master -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-master, .gemini/skills/cumcm-master, .github/skills/cumcm-master and .opencode/skills/cumcm-master in your project.

What does CUMCM Math Modeling Agent need to run?

Going by SKILL.md and its folder, CUMCM Math Modeling Agent needs the command-line tools its instructions call (python). Our summary lists: Python with the packages the models need; A LaTeX installation; Web search for literature research.

Does CUMCM Math Modeling Agent access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is CUMCM Math Modeling Agent safe to install?

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.

What licence does CUMCM Math Modeling Agent use?

CUMCM Math Modeling Agent is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does CUMCM Math Modeling Agent use?

About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to CUMCM Math Modeling Agent?

Skills that share tags, products or a category with CUMCM Math Modeling Agent: Paper Orchestra (Ar9av/PaperOrchestra, 679 stars), Backward Traceability (lingzhi227/agent-research-skills, 390 stars), Nature Polishing (aiskillstore/marketplace, 433 stars) and Literature Survey (ai4s-research/ai4s-skills, 237 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains CUMCM Math Modeling Agent?

RealSeaberry (a GitHub user) maintains it in RealSeaberry/AutoMCM-Pro, which has 257 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on September 10, 2026.

Source: RealSeaberry/AutoMCM-Pro on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.