Openclaw Skills for math modeling competitions that turns problem statements into validated models, runnable code, and a complete XeLaTeX thesis.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install mathmodel-master-full
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install mathmodel-master-full using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Math Modeling Competition Expert - Model Master?
This skill is a full-stack math modeling competition assistant for CUMCM, MCM/ICM, and similar contests. It guides the entire pipeline: reading the prompt, extracting assumptions and variables, selecting a model, implementing Python or MATLAB solvers, visualizing results, running sensitivity checks, and validating whether the model is reasonable.
Built for Openclaw Skills, it also standardizes the thesis pipeline around cumcmthesis.cls and XeLaTeX, with GB/T 7714 references and a final deliverable that is a complete paper rather than disconnected notes or partial outputs. The result is a practical, competition-ready workflow for teams that need speed, rigor, and publication-quality presentation.
Math Modeling Competition Expert - Model Master Use Cases
- When you need to analyze a modeling prompt and turn it into a full solution plan.
- When you are entering CUMCM, MCM, or ICM and need end-to-end competition guidance.
- When you need to choose between optimization, differential equation, statistical, or simulation-based models.
- When you want Python or MATLAB code to solve, simulate, or verify a model.
- When you need data cleaning, missing-value handling, outlier detection, and visualization.
- When you must perform sensitivity analysis and model validation before submitting.
- When you need a complete LaTeX paper with thesis structure and references.
How Math Modeling Competition Expert - Model Master Works
- Load the core rules from
skills/modeling/manifest.yaml, including thealways_loadguidance. - Infer the current phase from the user request and task state: reading, preprocessing, modeling, visualization, sensitivity analysis, validation, innovation, or thesis writing.
- Pull the matching stage fragment from
skills/modeling/static/fragments/stage/to apply the right modeling workflow. - Load
references.on_demandonly when deeper standards, templates, or implementation details are needed. - Produce a complete competition artifact: problem analysis, model design, code, figures, validation, and a final XeLaTeX thesis.
Math Modeling Competition Expert - Model Master Setup
- Place the skill in the
skills/modeling/directory and ensuremanifest.yamlis available. - Install a XeLaTeX-capable TeX stack and the thesis assets used by the workflow, including
cumcmthesis.clsv2.6 and the GB/T 7714 bibliography style. - Install Python 3 with scientific packages, and add MATLAB if your workflow needs it.
- Make sure the local fonts referenced by the thesis template are installed or substituted correctly.
- Compile the final thesis and verify that the PDF output, bibliography, and figures render correctly.
sudo apt-get update
sudo apt-get install -y texlive-xetex texlive-lang-chinese texlive-bibtex-extra latexmk python3 python3-pip
python3 -m pip install --upgrade pip
python3 -m pip install numpy pandas scipy matplotlib
xelatex main.tex
bibtex main
xelatex main.tex
xelatex main.tex
If you are using Openclaw Skills in a managed workspace, confirm that the manifest routes the stage fragments correctly before starting the modeling run.
Math Modeling Competition Expert - Model Master Data Schema & Taxonomy
The skill is organized around a manifest-driven, stage-based structure that keeps the workflow modular while ensuring the final output is a single complete thesis.
| Layer | Path / Artifact | Purpose | Notes |
|---|---|---|---|
| Skill manifest | skills/modeling/manifest.yaml |
Loads core rules, always_load, and routing logic |
Primary entry point for Openclaw Skills |
| Stage fragments | skills/modeling/static/fragments/stage/ |
Reusable instructions for each phase | Covers reading, preprocessing, modeling, visualization, sensitivity analysis, validation, innovation, and thesis writing |
| Deep references | references.on_demand |
Optional advanced guidance | Loaded only when stricter or more detailed rules are needed |
| Problem inputs | Prompt text, task statement, and any provided data | Defines variables, assumptions, and constraints | Used to classify the problem type |
| Working artifacts | Python or MATLAB scripts, preprocessing outputs, plots, validation notes | Intermediate solution assets | Should support reproducibility and traceability |
| Thesis source | .tex files based on cumcmthesis.cls |
Final paper source | Compiled with XeLaTeX |
| Bibliography assets | GB/T 7714 .bst and bibliography entries |
Citation formatting | Required for competition-style academic output |
| Final deliverable | Complete paper plus supporting code and figures | Submission-ready package | Must be a finished thesis, not scattered partial artifacts |
Metadata taxonomy used by the workflow:
- Stage: reading, preprocessing, modeling, visualization, sensitivity, validation, innovation, thesis
- Problem type: optimization, statistical modeling, differential equations, simulation, fitting
- Variables and assumptions: definitions, units, bounds, and simplifying assumptions
- Constraints: hard constraints, soft constraints, boundary conditions, data limitations
- Methods: algorithm choice, solver design, estimation strategy, comparison baseline
- Validation: reasonableness checks, sensitivity results, error analysis, robustness review
- Output assets: tables, figures, formulas, code, and final thesis sections
Math Modeling Competition Expert - Model Master Advanced Features
- Stage-aware orchestration across the full competition lifecycle, from reading the prompt to delivering the final thesis.
- Manifest-driven loading that keeps core rules compact while routing the right fragments at the right time.
- On-demand reference expansion for deeper modeling standards, thesis conventions, and implementation detail.
- End-to-end output discipline: the workflow is designed to finish with one complete paper, not disconnected intermediate notes.
- Multi-language solver support for Python and MATLAB, with code structured for reproducibility.
- XeLaTeX thesis generation using
cumcmthesis.clsand GB/T 7714 formatting for competition-grade presentation. - Built-in emphasis on preprocessing, visualization, sensitivity analysis, and model validation to improve solution quality.
- Well-suited for Openclaw Skills users who need a repeatable, competition-ready modeling pipeline.
SKILL.md
Loading
Related Openclaw Skills
Work Productivity Weather Current Workflow Helper
A demand-backed workflow helper in Openclaw Skills that turns Weather-style requests into reliable, local-friendly artifacts, fixes, and decision aids.
Error Message Improver
Openclaw Skills for turning vague errors into clear, actionable messages that explain what failed, why it failed, and what to do next.
Mobile Responsive Layout Fixer
Openclaw Skills provides a structured frontend workflow for diagnosing and fixing mobile responsive layout, navbar, and cross-device UI issues.
Work Productivity Skill Vetter Workflow Helper
A workflow helper that reviews other skills for usefulness, safety, overlap, and publish readiness before you install, keep, merge, rename, or publish them.
Work Productivity Skill Vetter Workflow Helper
Openclaw Skills turns high-demand skill-vetter requests into practical, local-first workflows, checklists, and implementation support.
Work Productivity Proactive Agent Workflow Helper
An Openclaw Skills workflow that converts validated proactive-agent demand into practical, local-first workflows, fixes, checklists, and decision aids.
Featured*
