# Code Reviewer

Detect whether approved modeling code is Python or MATLAB/Beita Tianyuan and route it...

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

## Install

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

## Description

Detect whether approved modeling code is Python or MATLAB/Beita Tianyuan and route it to the matching reviewer using the compact named-check review contract.

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

# Workflow

1. Inspect target code extensions and the implementation target in `qx_code_plan.md`.
2. Route `.py` work to `python-code-reviewer`.
3. Route `.m` work to `matlab-code-reviewer`.
4. If both languages are intentionally present, review each separately.
5. If the language or target is ambiguous, report the exact conflict.

# Review Contract

New reviews write JSON and evaluate these named checks:

- `syntax`
- `input_contract`
- `method_alignment`
- `reproducibility`
- `output_contract`

Additional checks are allowed when risk-driven. A review passes when all required applicable checks pass; no arbitrary bullet count is used.

# Rules

- Do not perform a second independent review in this router.
- Do not infer success because scripts exist.
- Do not require a Markdown review when the canonical JSON review exists.
- Read legacy Markdown reviews only for compatibility.