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.
Entry point for a math modeling competition project: asks about preferences, writes plan.md and todo.md, then calls stage skills for analysis, code, diagrams, paper and verification.
SKILL.md written in Chinese; this summary is our English description.
Install Math Modeling Workflow Starter
$ npx skills add jihe520/MathModelAgent --skill 1start-mathmodel -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jihe520/MathModelAgent 1start-mathmodel --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/jihe520/MathModelAgent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/1start-mathmodel .claude/skills/1start-mathmodel && 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 "1start-mathmodel" agent skill from https://github.com/jihe520/MathModelAgent/tree/main/skills/1start-mathmodel into .claude/skills/1start-mathmodel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "1start-mathmodel", 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/jihe520/MathModelAgent/tree/main/skills/1start-mathmodelType 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 jihe520/MathModelAgent --skill 1start-mathmodel -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jihe520/MathModelAgent 1start-mathmodel --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jihe520/MathModelAgent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/1start-mathmodel .agents/skills/1start-mathmodel && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "1start-mathmodel" agent skill from https://github.com/jihe520/MathModelAgent/tree/main/skills/1start-mathmodel into .agents/skills/1start-mathmodel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "1start-mathmodel", 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 jihe520/MathModelAgent --skill 1start-mathmodel -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jihe520/MathModelAgent 1start-mathmodel --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jihe520/MathModelAgent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/1start-mathmodel .cursor/skills/1start-mathmodel && 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 "1start-mathmodel" agent skill from https://github.com/jihe520/MathModelAgent/tree/main/skills/1start-mathmodel into .cursor/skills/1start-mathmodel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "1start-mathmodel", 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/jihe520/MathModelAgent.git --path skills/1start-mathmodel--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 jihe520/MathModelAgent --skill 1start-mathmodel -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jihe520/MathModelAgent 1start-mathmodel --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jihe520/MathModelAgent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/1start-mathmodel .gemini/skills/1start-mathmodel && 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 "1start-mathmodel" agent skill from https://github.com/jihe520/MathModelAgent/tree/main/skills/1start-mathmodel into .gemini/skills/1start-mathmodel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "1start-mathmodel", 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 jihe520/MathModelAgent 1start-mathmodelInstalls 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 jihe520/MathModelAgent --skill 1start-mathmodel -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jihe520/MathModelAgent.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/1start-mathmodel .github/skills/1start-mathmodel && 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 "1start-mathmodel" agent skill from https://github.com/jihe520/MathModelAgent/tree/main/skills/1start-mathmodel into .github/skills/1start-mathmodel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "1start-mathmodel", 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 jihe520/MathModelAgent --skill 1start-mathmodel -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jihe520/MathModelAgent 1start-mathmodel --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jihe520/MathModelAgent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/1start-mathmodel .opencode/skills/1start-mathmodel && 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 "1start-mathmodel" agent skill from https://github.com/jihe520/MathModelAgent/tree/main/skills/1start-mathmodel into .opencode/skills/1start-mathmodel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "1start-mathmodel", 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
1start-mathmodel- GitHub stars
- 6.2k
- Token cost
- ~918 tokens
- SKILL.md length
- 125 words
- Files
- 1
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- None found
At a glance
Entry point for a math modeling competition project: asks about preferences, writes plan.md and todo.md, then calls stage skills for analysis, code, diagrams, paper and verification.
- Works in 4 steps: 询问用户偏好 AskUserQuestions → 制定方案 → 生成待办 → …
- Starting a math modeling competition project from the problem statement
- SKILL.md covers 数学建模规范参考, 必须产出, 工作流 and 项目目录结构, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
This is the control skill for a contest workflow, and it does not replace the stage skills. It asks only the few questions that change the process: the typesetting engine (Typst or LaTeX, with xelatex run twice for cross-references), the competition type, the paper language (MCM, ICM and COMAP require English, other contests default to Chinese) and whether the number of sub-questions is known. Both engines cover all templates, 14 Chinese and 3 English, and the choices are recorded in plan.md.
It then writes plan.md and a todo.md checklist, lays out a project directory skeleton and runs the downstream skills in order: 2analysis-modeling for problem analysis and the model, 3coding-visual for reproducible code, results and data figures, 4drawio for flowcharts and architecture diagrams, 5writing for the paper and 6verity for reproducibility, consistency and submission-readiness checks. Boundaries are explicit: data charts come only from the coding stage, draw.io handles concept diagrams, and the writing stage must take every number from the results report instead of inventing it.
When your agent uses it
- Starting a math modeling competition project from the problem statement
- Planning stages and deliverables before modeling begins
- Choosing between Typst and LaTeX for a contest paper
- Keeping a todo checklist that tracks each stage
Example prompts
- “开始一个数学建模项目，国赛，论文用中文，排版用 LaTeX。”
- “Start an MCM paper project in English with Typst, and make a plan and todo list.”
- “Set up the workflow for our contest problem, we do not know the number of sub-questions yet.”
Requirements
- Typst, or a LaTeX installation with xelatex, to compile the paper
- The downstream stage skills 2analysis-modeling through 6verity
- Pre-approved tools (allowed-tools): Bash(*), Read, Write, Edit, Grep, Glob, Agent, WebSearch, WebFetch
Workflow steps
4 steps, taken from the step headings in SKILL.md.
- 询问用户偏好 AskUserQuestions
- 制定方案
- 生成待办
- 依次执行阶段
What it can do on your machine
Read from SKILL.md and the folder at commit 03f4eb3. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
Bash(*)ReadWriteEditGrepGlobAgentWebSearchWebFetch
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
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 Workflow Starter loads about 918 tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 125 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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, Agent, WebSearch, WebFetch
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
Without a licence we can't republish the file, so here is its outline and opening line. It has 125 words (~918 tokens).
- name
- 1start-mathmodel
- allowed-tools
- Bash(*), Read, Write, Edit, Grep, Glob, Agent, WebSearch, WebFetch
Files
Just SKILL.md in skills/1start-mathmodel of jihe520/MathModelAgent.
Open the folder on GitHubat commit 03f4eb3
Compare with similar skills
Math Modeling Workflow Starter 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 Workflow Starter this skilljihe520/MathModelAgent | 6.2k | — | ~918 | Automated safety check: Notes | None | |
| AutoMCM-Pro for Codex CLIRealSeaberry/AutoMCM-Pro | 258 | — | ~1.6k | Automated safety check: Pass | MIT | |
| AutoMCM-Pro Math Modeling AgentRealSeaberry/AutoMCM-Pro | 258 | — | ~8.5k | Automated safety check: Pass | MIT | |
| NSFC Budget Justification Writerhuangwb8/ChineseResearchLaTeX | 2.9k | 1 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Thesis Figure Skill0xE1337/thesis-figure-skill | 142 | — | ~9.1k | Automated safety check: Pass | MIT | |
| Market Research Reportsdavila7/claude-code-templates | 32k | 10 repos | ~7.2k | Automated safety check: Notes | MIT |
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.
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.
Thesis Figure Skill
0xE1337/thesis-figure-skill
生成学术论文配图：LaTeX/TikZ 代码（结构化图表，直接嵌入论文）或 draw.io XML （技术路线图、汇报配图）。自动按论文领域风格设计，编译验证后交付。
Market Research Reports
davila7/claude-code-templates
Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner).
Academic LaTeX Formatter
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.
More from jihe520/MathModelAgent
All 10 skills in this repoMathModel Figure Templates
jihe520/MathModelAgent
Renders ready-made scientific figure templates, such as raincloud plots, Taylor diagrams and chord diagrams, from bundled Python scripts in the MathModel sandbox.
Typst Author
jihe520/MathModelAgent
Generates, edits and debugs Typst (.typ) documents using the bundled Typst documentation as the source of truth, with formatting checks after each edit.
Math Modeling to EI Conference Paper
jihe520/MathModelAgent
Rewrites a math modeling competition paper into an English EI conference submission, using a bundled IEEE LaTeX template, with evidence tracked back to the original paper.
Math Modeling Paper Verifier
jihe520/MathModelAgent
Runs the final verification pass on a math-modeling competition paper written in Typst or LaTeX, checking structure, figures, numbers, leaks and compilation.
Math Modeling Problem Analysis
jihe520/MathModelAgent
Chinese-language stage that turns a math modeling contest problem and its data files into a modeling report with sub-problems, formulas and a task list for coding.
Math Modeling Code and Figures
jihe520/MathModelAgent
Math modeling stage that turns an analysis report into reproducible code, validates the solutions, writes RESULTS_REPORT.md and produces data-driven PDF charts for the paper.
Related
Categories
Questions about Math Modeling Workflow Starter
What does Math Modeling Workflow Starter do?
Entry point for a math modeling competition project: asks about preferences, writes plan.md and todo.md, then calls stage skills for analysis, code, diagrams, paper and verification. This is the control skill for a contest workflow, and it does not replace the stage skills. It asks only the few questions that change the process: the typesetting engine (Typst or LaTeX, with xelatex run twice for cross-references), the competition type, the paper language (MCM, ICM and COMAP require English, other contests default to Chinese) and whether the number of sub-questions is known.
When should I use Math Modeling Workflow Starter?
Math Modeling Workflow Starter fits situations like: starting a math modeling competition project from the problem statement; planning stages and deliverables before modeling begins; choosing between Typst and LaTeX for a contest paper; keeping a todo checklist that tracks each stage.
How do I install Math Modeling Workflow Starter in Claude Code?
Run `npx skills add jihe520/MathModelAgent --skill 1start-mathmodel -a claude-code`. Or copy the skill folder (skills/1start-mathmodel in jihe520/MathModelAgent) into .claude/skills/1start-mathmodel in your project. Claude Code loads it when a task matches its description.
How do I install Math Modeling Workflow Starter in Codex?
Run `npx skills add jihe520/MathModelAgent --skill 1start-mathmodel -a codex`. Or copy the skill folder (skills/1start-mathmodel in jihe520/MathModelAgent) into .agents/skills/1start-mathmodel in your project. Codex loads it when a task matches its description.
Can I use Math Modeling Workflow Starter 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 jihe520/MathModelAgent --skill 1start-mathmodel -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/1start-mathmodel, .gemini/skills/1start-mathmodel, .github/skills/1start-mathmodel and .opencode/skills/1start-mathmodel in your project.
What does Math Modeling Workflow Starter need to run?
SKILL.md names no scripts, command-line tools or credentials: Math Modeling Workflow Starter is instructions for the agent only. Our summary lists: Typst, or a LaTeX installation with xelatex, to compile the paper; The downstream stage skills 2analysis-modeling through 6verity. Its frontmatter pre-approves these tools: Bash(*), Read, Write, Edit, Grep, Glob, Agent, WebSearch, WebFetch.
Does Math Modeling Workflow Starter 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 Workflow Starter safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Math Modeling Workflow Starter use?
No licence was found for Math Modeling Workflow Starter or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Math Modeling Workflow Starter use?
About 918 tokens (SKILL.md is roughly 3.7k 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 Math Modeling Workflow Starter?
Skills that share tags, products or a category with Math Modeling Workflow Starter: AutoMCM-Pro for Codex CLI (RealSeaberry/AutoMCM-Pro, 258 stars), AutoMCM-Pro Math Modeling Agent (RealSeaberry/AutoMCM-Pro, 258 stars), NSFC Budget Justification Writer (huangwb8/ChineseResearchLaTeX, 2.9k stars) and Thesis Figure Skill (0xE1337/thesis-figure-skill, 142 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Math Modeling Workflow Starter?
jihe520 (a GitHub user) maintains it in jihe520/MathModelAgent, which has 6,177 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 3, 2026.
Source: jihe520/MathModelAgent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.