Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Coder Role (Math Modeling Implementation)

Defines the implementation phase of a math-modeling project: Python/MATLAB code, result tables, publication-grade figures, flowcharts and a reproduction manifest, enforced by two independent QA gates.

Data & AnalyticsAdvanced★ 1,857⑂ 100AI score 7/10Last updated: Oct 11, 2026

What it does

  • Specifies the "coder" role of a math-modeling pipeline: it consumes the problem-analysis report and glossary, then builds the Python (.py) or MATLAB (.m) implementation.
  • Enforces fixed deliverables: result tables in results/, figures in figures/ split into raw-data / process / final-result classes (≥3 each, ≥9 total, every sub-question q1…qN covered), a mandatory overall model flowchart flow_overall_model.*, and a JSON reproduction manifest.
  • Checks dependencies per feature (check_env.py --features data visualization optimization) instead of demanding every package, and runs a P1 minimal-run gate before full computation plus a P2 final gate before delivery, both executed by independent QA subagents that must return PASS.
  • Figures must pass the layout gate of export_figure.py / export_publication_figure(), exporting SVG plus ≥300 DPI PNG, then be audited with figure_audit.py --strict and visually inspected in color and grayscale.

Who it's for

  • Math-modeling competition teams (MCM/ICM, CUMCM) and their advisors
  • Researchers who must combine model implementation with reproducibility and figure quality
  • Users automating a multi-role agent pipeline (modeler → coder → writer)

Example uses

  1. "Implement the q1–q3 optimization models in Python from the analysis report and produce the result tables."
  2. "Prepare the paper figures" — generate the three figure classes per sub-question, export SVG + 300 DPI PNG, and verify grayscale readability at print size.
  3. "Verify reproducibility before submission" — build the manifest with repro_manifest.py and let the P2 gate re-run the single reproduction command, checking input hashes, seeds and key numbers.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/XiaoMaColtAI/math-modeling-skill/HEAD/dsh-plugin/math-modeling-agent/skills/math-modeling/references/roles/编程手/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the dsh-plugin/math-modeling-agent/skills/math-modeling/references/roles/编程手 folder from the GitHub repo XiaoMaColtAI/math-modeling-skill into my ~/.claude/skills/xiaomacoltai-skill/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/XiaoMaColtAI/math-modeling-skill.git && mkdir -p ~/.claude/skills && cp -r math-modeling-skill/dsh-plugin/math-modeling-agent/skills/math-modeling ~/.claude/skills/math-modeling

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal in your working directory.
  2. Clone the repository: git clone https://github.com/XiaoMaColtAI/math-modeling-skill.git
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy the whole plugin skill (including its references/tools/scripts): cp -r math-modeling-skill/dsh-plugin/math-modeling-agent/skills/math-modeling ~/.claude/skills/math-modeling
    • Do not copy this SKILL.md alone; it depends on tools/figure, scripts/*.py and references/*.md from parent folders.
  5. Prepare a Python environment (Matplotlib, NumPy, optimization libs) or install MATLAB if you plan to use it.
  6. Restart Claude Code, open your project folder, and ask something like "run the math-modeling implementation phase" to trigger the skill.
  7. Note: the documentation is written in Chinese, so ask Claude to translate outputs if needed.
View source on GitHub ↗