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…
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.
SKILL.md written in Chinese; this summary is our English description.
$ npx skills add RealSeaberry/AutoMCM-Pro --skill cumcm-master -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install RealSeaberry/AutoMCM-Pro cumcm-master --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/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-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-master" agent skill from https://github.com/RealSeaberry/AutoMCM-Pro/tree/main/.claude/skills/cumcm-master into .claude/skills/cumcm-master/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cumcm-master", 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/RealSeaberry/AutoMCM-Pro/tree/main/.claude/skills/cumcm-masterType 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 RealSeaberry/AutoMCM-Pro --skill cumcm-master -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install RealSeaberry/AutoMCM-Pro cumcm-master --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RealSeaberry/AutoMCM-Pro.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/cumcm-master .agents/skills/cumcm-master && 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-master" agent skill from https://github.com/RealSeaberry/AutoMCM-Pro/tree/main/.claude/skills/cumcm-master into .agents/skills/cumcm-master/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cumcm-master", 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 RealSeaberry/AutoMCM-Pro --skill cumcm-master -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install RealSeaberry/AutoMCM-Pro cumcm-master --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RealSeaberry/AutoMCM-Pro.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/cumcm-master .cursor/skills/cumcm-master && 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-master" agent skill from https://github.com/RealSeaberry/AutoMCM-Pro/tree/main/.claude/skills/cumcm-master into .cursor/skills/cumcm-master/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cumcm-master", 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/RealSeaberry/AutoMCM-Pro.git --path .claude/skills/cumcm-master--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 RealSeaberry/AutoMCM-Pro --skill cumcm-master -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install RealSeaberry/AutoMCM-Pro cumcm-master --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RealSeaberry/AutoMCM-Pro.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/cumcm-master .gemini/skills/cumcm-master && 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-master" agent skill from https://github.com/RealSeaberry/AutoMCM-Pro/tree/main/.claude/skills/cumcm-master into .gemini/skills/cumcm-master/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cumcm-master", 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 RealSeaberry/AutoMCM-Pro cumcm-masterInstalls 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 RealSeaberry/AutoMCM-Pro --skill cumcm-master -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/RealSeaberry/AutoMCM-Pro.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/cumcm-master .github/skills/cumcm-master && 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-master" agent skill from https://github.com/RealSeaberry/AutoMCM-Pro/tree/main/.claude/skills/cumcm-master into .github/skills/cumcm-master/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cumcm-master", 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 RealSeaberry/AutoMCM-Pro --skill cumcm-master -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install RealSeaberry/AutoMCM-Pro cumcm-master --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RealSeaberry/AutoMCM-Pro.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/cumcm-master .opencode/skills/cumcm-master && 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-master" agent skill from https://github.com/RealSeaberry/AutoMCM-Pro/tree/main/.claude/skills/cumcm-master into .opencode/skills/cumcm-master/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cumcm-master", 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-masterDrives 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.
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.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 90c4727. 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.
Shell commands in SKILL.md call:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From 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 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.
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 RealSeaberry/AutoMCM-Pro at commit 90c4727, republished under its MIT licence (© RealSeaberry). 347 words, ~1,578 tokens.
.claude/skills/cumcm-master/SKILL.md (or your agent's skills folder).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..."
在开始任何建模工作之前,必须先运行工作区初始化脚本:
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 输出使用 AskUserQuestion 依次询问:
./problem.pdf)./data/ 或具体文件路径)收集完毕后,读取赛题内容。若为 PDF,运行:
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]"仔细阅读赛题,识别:
针对核心建模方法,使用 WebSearch 搜索近年高质量论文和方法:
"[方法名] mathematical model CUMCM" OR "[问题领域] optimization model"memory/thought_process.md 中记录参考文献信息(含 DOI 或 URL)用 agent_memory_manager.py 写入初始状态:
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:
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)在动手写代码之前,先在 memory/thought_process.md 中写下:
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:
CUMCM_Workspace/latex/images/cd CUMCM_Workspace && python src/0X_script.pymemory/thought_process.md 记录关键结果数值每张图必须满足:
matplotlib.rcParams['font.family'])fig01_description.png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将 templates/latex_template.tex 复制到 CUMCM_Workspace/latex/main.tex:
cp templates/latex_template.tex CUMCM_Workspace/latex/main.tex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
2. 问题背景与需要解决的问题
3. 问题分析
/draw-image skill 生成(调用 scripts/draw_image.py)/draw-image4. 模型假设
\begin{enumerate}[label=假设\arabic*:]5. 符号说明
booktabs 宏包6. 模型的建立与求解
equation 或 align 环境,编号7. 模型的分析与检验
8. 模型的评价、改进与推广
9. 参考文献
\bibitem 或 BibTeX10. 附录
src/ 中每个关键脚本的完整代码listings 宏包,Python 语法高亮写完每个章节后,必须自问:
\ref{} 引用?&, %, _, $, {, })是否正确转义?\begin{} 是否有对应 \end{}?当用户提供新方向或批评时:
使用 agent_memory_manager.py 记录用户建议:
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"若采纳:立即返回 Phase 2,重新编码、验证、更新 LaTeX 对应章节
cd CUMCM_Workspace/latex && xelatex -interaction=nonstopmode main.tex 2>&1 | tail -20若出现编译错误:
! LaTeX Error: 或 Undefined control sequence)main.tex编译成功后:
cp CUMCM_Workspace/latex/main.pdf CUMCM_Workspace/output/final_paper.pdf
python scripts/agent_memory_manager.py completememory/iteration.json使用 TodoWrite 维护任务清单,格式:
© RealSeaberry, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .claude/skills/cumcm-master of RealSeaberry/AutoMCM-Pro.
Open the folder on GitHubat commit 90c4727
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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| CUMCM Math Modeling Agent this skillRealSeaberry/AutoMCM-Pro | 257 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Paper OrchestraAr9av/PaperOrchestra | 679 | 1 repos | ~3.5k | Automated safety check: Pass | Custom licence | |
| Backward Traceabilitylingzhi227/agent-research-skills | 390 | — | ~802 | Automated safety check: Pass | None | |
| Nature Polishingaiskillstore/marketplace | 433 | 1 repos | ~1.3k | Automated safety check: Pass | None | |
| Literature Surveyai4s-research/ai4s-skills | 237 | 2 repos | ~2k | Automated safety check: Pass | MIT | |
| LaTeX Research PostersK-Dense-AI/claude-scientific-writer | 2.4k | 12 repos | ~4.1k | Automated safety check: Notes | MIT |
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…
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.
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…
ai4s-research/ai4s-skills
A skill your agent uses when the user wants a comprehensive literature survey on a specific research topic.
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.
brycewang-stanford/Auto-Empirical-Research-Skills
Econometrics skill for creating publication-quality LaTeX regression and summary tables.
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.
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.
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.
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.
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.
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.
Works with
Categories
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.
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.
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.
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.
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.
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.
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.
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 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.
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.
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.
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.