Formal Modeling Paper Writer
yushui2022/MathModel-Skill
Plans, drafts, audits, formats and verifies a formal mathematical-modeling paper from an evidence chain, delivering audited Markdown and a Word file with native equations.
Three-role workflow for math modeling contests: problem analysis, code and results, then a paper, with independent subagent checks at each stage gate.
SKILL.md written in Chinese; this summary is our English description.
Install Math Modeling Competition Workflow
$ npx skills add XiaoMaColtAI/math-modeling-skill --skill math-modeling -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install XiaoMaColtAI/math-modeling-skill math-modeling --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "math-modeling" agent skill from https://github.com/XiaoMaColtAI/math-modeling-skill/tree/main into .claude/skills/math-modeling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "math-modeling", 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.
$ npx skills add XiaoMaColtAI/math-modeling-skill --skill math-modeling -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install XiaoMaColtAI/math-modeling-skill math-modeling --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "math-modeling" agent skill from https://github.com/XiaoMaColtAI/math-modeling-skill/tree/main into .agents/skills/math-modeling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "math-modeling", 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 XiaoMaColtAI/math-modeling-skill --skill math-modeling -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install XiaoMaColtAI/math-modeling-skill math-modeling --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "math-modeling" agent skill from https://github.com/XiaoMaColtAI/math-modeling-skill/tree/main into .cursor/skills/math-modeling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "math-modeling", 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.
$ npx skills add XiaoMaColtAI/math-modeling-skill --skill math-modeling -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install XiaoMaColtAI/math-modeling-skill math-modeling --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "math-modeling" agent skill from https://github.com/XiaoMaColtAI/math-modeling-skill/tree/main into .gemini/skills/math-modeling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "math-modeling", 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 XiaoMaColtAI/math-modeling-skill math-modelingInstalls 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 XiaoMaColtAI/math-modeling-skill --skill math-modeling -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "math-modeling" agent skill from https://github.com/XiaoMaColtAI/math-modeling-skill/tree/main into .github/skills/math-modeling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "math-modeling", 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 XiaoMaColtAI/math-modeling-skill --skill math-modeling -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install XiaoMaColtAI/math-modeling-skill math-modeling --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "math-modeling" agent skill from https://github.com/XiaoMaColtAI/math-modeling-skill/tree/main into .opencode/skills/math-modeling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "math-modeling", 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.
Facts
- Skill name
math-modeling- GitHub stars
- 1.9k
- Token cost
- ~1.2k tokens
- SKILL.md length
- 271 words
- Files
- 65 (incl. scripts, references, assets)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- None found
At a glance
Three-role workflow for math modeling contests: problem analysis, code and results, then a paper, with independent subagent checks at each stage gate.
- Works in 9 steps: 在首次进度更新中回显：已激活本… → 开始每个阶段前，实际读取该角色的 SKILL.md；使用… → 严格调用 Skill… → …
- Working through a math modeling contest problem such as CUMCM or MCM/ICM
- SKILL.md covers 强制执行协议, Subagent 默认策略与阶段门禁, 根目录契约 and 路由, plus 5 more sections
- Only analyzing a problem and choosing models
What it does
A Chinese-language skill that splits a math-modeling task into three roles: a modeler who analyzes the problem and picks models, a programmer who writes the code, runs results and makes figures, and a paper writer who produces the paper. You can run the whole sequence or any single role. The generated paper is for reference only and is not meant to be submitted as is, because its structure and format must follow the target contest's current official rules and template.
A mandatory protocol has the agent say which skill, roots and stage it is using, actually read each role's SKILL.md, use the provided scripts and templates instead of hand-written substitutes, treat any validation warning as unfinished work and report the commands run with their exit codes. By default only quality-check subagents are dispatched, at gates named M1, P1, P2, W1 and W2, and optional collaboration stays off unless you switch it on. The modeler delivers a problem analysis report and a glossary. The skill folder is read-only and new files go only to the project folder, and for real contests the agent checks official deadlines and keeps a submit-ready checkpoint.
When your agent uses it
- Working through a math modeling contest problem such as CUMCM or MCM/ICM
- Only analyzing a problem and choosing models
- Writing code, running results and plotting figures for a modeling solution
- Drafting or revising a modeling paper in DOCX
Example prompts
- “Analyze this CUMCM problem and recommend models; stop after the analysis.”
- “Run the programming stage for my model and produce the result figures.”
- “Write the modeling paper from my results and charts.”
Requirements
- Python or MATLAB for the modeling code
- A project folder separate from the skill's install folder
- An agent that supports subagents, for the independent checks
Workflow steps
9 steps, taken from the first numbered list in SKILL.md.
- 在首次进度更新中回显：已激活本 Skill、SKILL_ROOT、PROJECT_ROOT、当前阶段、目标竞赛与届次、计划读取的角色和工具入口。未确认的官方规则明确标为待核验。
- 开始每个阶段前，实际读取该角色的 SKILL.md；使用 PDF、Excel、论文搜索、DOCX 或 LaTeX 时，再实际读取对应工具的 SKILL.md。知道文件路径不等于已经执行。
- 严格调用 Skill 提供的脚本和模板。已有初始化、转换、编译或校验工具时，禁止为了省时手写替代实现。
- 把任何校验预警视为未完成。只有当届官方规则或用户明确要求允许偏离时，才能记录“规则来源、偏离项、理由”后继续；不得自行降低篇幅、图表、公式、引用或编译质量目标。
- 环境缺少引擎、搜索源、渲染器或依赖时，报告阻塞并继续完成仍可验证的部分；禁止静默换工具、跳过验证或用较差产物冒充完成。
- 运行环境支持 Subagent 且任务会生成或修改固定交付物时，按 references/Subagent调度.md 在关键节点立即派发独立质检；禁止等全流程结束后才首次派发，作者自检不能替代独立验收。除固定质检外，不主动派发其他…
- 交付前运行当前角色规定的全部完成门禁。任一命令未运行、退出码非零、独立验收未通过、仍有未处理问题或产物在门禁后发生变化时，不得声称“已完成”。
- 真实竞赛或其他有明确截止时间的任务，必须读取 references/交付与截止时间协议.md，核验当届官方截止时间与提交约束，尽早走通完整导出链路并维护可立即提交的 Checkpoint V1；后续优化不得破坏该版本。
- 最终回复列出实际读取的入口、实际运行的关键命令、退出码、Subagent 门禁状态、核心质量指标和仍存在的阻塞；不得只说“已检查”。
What it can do on your machine
Read from SKILL.md and the folder at commit bf64c5f. 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
Ships 1 file in scripts/, which the agent can run.
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
Math Modeling Competition Workflow loads about 1.2k tokens when it runs, and up to ~5k if it reads all its reference files. Until then it costs about 34 tokens; SKILL.md has 271 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.
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); the scripts in this folder are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 271 words (~1,238 tokens).
- name
- math-modeling
Files
SKILL.md and 64 other files (scripts, references, assets) in the repository root of XiaoMaColtAI/math-modeling-skill.
- SKILL.md
- .github/workflows/update-star-history.yml
- .gitignore
- CHANGELOG.md
- README.md
- VERSION
- assets/01-优化算法说明.md
- assets/02-预测类算法说明.md
- assets/03-评价类算法说明.md
- assets/04-图论与网络分析算法说明.md
- assets/05-统计分析与数据处理算法说明.md
- assets/06-综合类算法说明.md
- assets/07-机器学习算法说明.md
- assets/README.md
- dsh-plugin/README.md
- dsh-plugin/math-modeling-agent/agent.cordis.yml
- … and 49 more
Open the folder on GitHubat commit bf64c5f
Compare with similar skills
Math Modeling Competition 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 |
|---|---|---|---|---|---|---|
| Math Modeling Competition Workflow this skillXiaoMaColtAI/math-modeling-skill | 1.9k | — | ~1.2k | Automated safety check: Pass | None | |
| Formal Modeling Paper Writeryushui2022/MathModel-Skill | 452 | — | ~1.6k | Automated safety check: Pass | MIT | |
| AutoMCM-Pro Math Modeling AgentRealSeaberry/AutoMCM-Pro | 257 | — | ~8.5k | Automated safety check: Pass | MIT | |
| Math Model Formulation StageWuXinbo-bo/Math-model-skills | 111 | — | ~2.9k | Automated safety check: Pass | MIT | |
| MCM/ICM Autonomous Modeling AgentRealSeaberry/AutoMCM-Pro | 257 | — | ~2.8k | Automated safety check: Pass | MIT | |
| Word Document Reader and WriterHKUDS/DeepTutor | 41k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 |
Similar skills
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.
Math Model Formulation Stage
WuXinbo-bo/Math-model-skills
Stage protocol for a math-modeling pipeline that turns a problem analysis into a unified mathematical mechanism, formulas, a solution route and a validation plan.
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.
Word Document Reader and Writer
HKUDS/DeepTutor
Reads, creates and edits Word .docx files with python-docx, and drops to raw OOXML for tracked changes, comments and byte-exact edits.
NSFC Budget Justification Writer
huangwb8/ChineseResearchLaTeX
Writes a submission-ready NSFC budget justification as a LaTeX project and renders budget.pdf from your grant proposal text and supporting materials.
Related
Works with
Categories
Questions about Math Modeling Competition Workflow
What does Math Modeling Competition Workflow do?
Three-role workflow for math modeling contests: problem analysis, code and results, then a paper, with independent subagent checks at each stage gate. A Chinese-language skill that splits a math-modeling task into three roles: a modeler who analyzes the problem and picks models, a programmer who writes the code, runs results and makes figures, and a paper writer who produces the paper. You can run the whole sequence or any single role.
When should I use Math Modeling Competition Workflow?
Math Modeling Competition Workflow fits situations like: working through a math modeling contest problem such as CUMCM or MCM/ICM; only analyzing a problem and choosing models; writing code, running results and plotting figures for a modeling solution; drafting or revising a modeling paper in DOCX.
How do I install Math Modeling Competition Workflow in Claude Code?
Run `npx skills add XiaoMaColtAI/math-modeling-skill --skill math-modeling -a claude-code`. Or copy the skill folder (the XiaoMaColtAI/math-modeling-skill repository) into .claude/skills/math-modeling in your project. Claude Code loads it when a task matches its description.
How do I install Math Modeling Competition Workflow in Codex?
Run `npx skills add XiaoMaColtAI/math-modeling-skill --skill math-modeling -a codex`. Or copy the skill folder (the XiaoMaColtAI/math-modeling-skill repository) into .agents/skills/math-modeling in your project. Codex loads it when a task matches its description.
Can I use Math Modeling Competition Workflow 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 XiaoMaColtAI/math-modeling-skill --skill math-modeling -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/math-modeling, .gemini/skills/math-modeling, .github/skills/math-modeling and .opencode/skills/math-modeling in your project.
What does Math Modeling Competition Workflow need to run?
SKILL.md names no scripts, command-line tools or credentials: Math Modeling Competition Workflow is instructions for the agent only. Our summary lists: Python or MATLAB for the modeling code; A project folder separate from the skill's install folder; An agent that supports subagents, for the independent checks.
Does Math Modeling Competition Workflow 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 Math Modeling Competition Workflow 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Math Modeling Competition Workflow use?
No licence was found for Math Modeling Competition Workflow or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Math Modeling Competition Workflow use?
About 1.2k tokens (SKILL.md is roughly 5k 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 3.8k tokens, read only when the agent opens those files.
What are the alternatives to Math Modeling Competition Workflow?
Skills that share tags, products or a category with Math Modeling Competition Workflow: Formal Modeling Paper Writer (yushui2022/MathModel-Skill, 452 stars), AutoMCM-Pro Math Modeling Agent (RealSeaberry/AutoMCM-Pro, 257 stars), Math Model Formulation Stage (WuXinbo-bo/Math-model-skills, 111 stars) and MCM/ICM Autonomous Modeling Agent (RealSeaberry/AutoMCM-Pro, 257 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Math Modeling Competition Workflow?
XiaoMaColtAI (a GitHub user) maintains it in XiaoMaColtAI/math-modeling-skill, which has 1,850 GitHub stars. The repository was last updated on October 7, 2026.
Source: XiaoMaColtAI/math-modeling-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.