# Matlab Model Code Generator

Generate and run minimal reproducible MATLAB or Beita Tianyuan compatible code for the...

- Repository: https://github.com/zhnnky329/MathModeling-skills (1073 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-09-24
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add zhnnky329/MathModeling-skills --skill matlab-model-code-generator -g -a claude-code -y`
Codex: `npx skills add zhnnky329/MathModeling-skills --skill matlab-model-code-generator -g -a codex -y`
Cursor: `npx skills add zhnnky329/MathModeling-skills --skill matlab-model-code-generator -g -a cursor -y`
Gemini CLI: `npx skills add zhnnky329/MathModeling-skills --skill matlab-model-code-generator -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add zhnnky329/MathModeling-skills`

## Description

Generate and run minimal reproducible MATLAB or Beita Tianyuan compatible code for the human-approved main method and usable baseline, with compact experiment artifacts and a canonical run summary.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Preconditions

- G2.5 human method choice is recorded.
- `code/matlab/Qx/qx_code_plan.md` exists.
- Required cleaned data and profile exist.
- The plan targets MATLAB or 北太天元.

Legacy artifacts may be read during migration but do not override the human decision.

# Workflow

1. Read the code plan, decision ledger, method card, probe conditions, and data profile.
2. Confirm scope: approved main plus usable baseline. Implement a fallback only after activation.
3. Generate conservative `.m` files under `code/matlab/Qx/`.
4. Prefer basic matrix/table operations and avoid optional toolboxes unless the plan approves them.
5. Save tables, metrics, useful figures, and `run_summary.json` under `results/Qx/experiments/roundN/`.
6. Evaluate output-degeneracy and fallback-trigger metrics required by the plan.
7. Use `diary` or another full log only for a failure or reproducibility warning.
8. Run in the available compatible runtime. If unavailable, report the unexecuted state explicitly.
9. Hand off to `code-reviewer`.

# Script Layout

```text
code/matlab/Qx/
├── qx_code_plan.md
├── qx_baseline.m
├── qx_main.m
└── run_all.m        % only when useful
```

Do not create scripts for unapproved candidates or a duplicate README.

# Compatibility Rules

- Prefer `readtable`, `readmatrix`, `writetable`, `writematrix`, `save`, `load`, and `fullfile`.
- Use `rng(2026)` or the recorded seed.
- Use `jsonencode` when supported; otherwise write the required JSON fields deterministically.
- Avoid Live Scripts, App Designer, GUI code, Simulink, and toolbox-only functions unless explicitly approved.
- Note any 北太天元 compatibility risk in the run summary.

# Run Summary

Follow the `model-code-analyzer` contract, including approved decision ID, roles, paths, metrics, output-degeneracy evidence, fallback state, timing, seed, environment, warnings, and errors.

# Rules

The rest: https://github.com/zhnnky329/MathModeling-skills/blob/HEAD/.claude/skills/matlab-model-code-generator/SKILL.md