跳到正文
cccskills
免费在 GitHub 公开

matlab-code-reviewer

Review, run, debug, and verify approved MATLAB or Beita Tianyuan modeling code against its plan, data contract, method decision, compatibility constraints, and experiment outputs, saving one compact JSON review.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md1.9 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Preconditions

  • MATLAB code and code/matlab/Qx/qx_code_plan.md exist.
  • Approved decision, method card, data profile, and run summary are available.
  • MATLAB or 北太天元 runtime availability is known.

Workflow

  1. Resolve approved main/baseline scope and any activated fallback.
  2. Inspect and run the code when a compatible runtime is available.
  3. Evaluate:
    • syntax
    • input_contract
    • method_alignment
    • reproducibility
    • output_contract
  4. Include compatibility evidence for toolbox usage, jsonencode, file I/O, plotting/export, and 北太天元 constraints.
  5. Add only relevant numerical, feasibility, leakage, or scale checks.
  6. If runtime is unavailable, use NOT_RUN rather than claiming execution success.
  7. If asked to fix findings, patch minimally and rerun affected checks.
  8. Save code/matlab/Qx/reviews/qx_matlab_review.json.

Review Schema

Use the same schema as python-code-reviewer, with:

  • "language": "matlab"
  • runtime
  • compatibility_target
  • optional compatibility check

Required named checks use PASS, FAIL, or justified NOT_APPLICABLE. Runtime-dependent checks use NOT_RUN when execution was impossible; this blocks G3 until executed.

Rules

  • Do not pad pass items.
  • Do not fabricate MATLAB/北太天元 execution.
  • Do not approve unavailable toolbox dependencies without an explicit target exception.
  • Do not change the mathematical model silently.
  • Do not require a duplicate Markdown review.

Verification

  • Approved main and baseline scope is enforced.
  • Compatibility constraints are checked.
  • Run summary and outputs agree.
  • Verdict follows required check statuses and runtime evidence.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

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.

中文简介正在准备中。当前显示原文说明。

zhnnky329/MathModeling-skills10612026年9月24日 更新

Audit whether the semantic evidence required by the active lean or submission profile exists and is current, without requiring one verbose artifact per skill or an arbitrary number of pass bullets.

中文简介正在准备中。当前显示原文说明。

zhnnky329/MathModeling-skills10612026年9月24日 更新

Run scoped or final cross-media consistency checks for mathematical-modeling artifacts, comparing canonical numbers, symbols, parameters, decisions, files, and paper claims without performing full-workspace audits for low-risk changes.

中文简介正在准备中。当前显示原文说明。

zhnnky329/MathModeling-skills10612026年9月24日 更新

Map contest attachments to subquestions, audit and clean raw data, and emit one reusable data profile with quality, coverage, imbalance, concentration, and method-readiness evidence for downstream risk screening.

中文简介正在准备中。当前显示原文说明。

zhnnky329/MathModeling-skills10612026年9月24日 更新

Build one compact choice card at a genuine mathematical-modeling judgment point. Use before method screening, after a meaningful experiment, or before final claim/freeze approval so the human chooses the trade-off while AI handles mechanical consequences.

中文简介正在准备中。当前显示原文说明。

zhnnky329/MathModeling-skills10612026年9月24日 更新

Plan the smallest set of diagnostic, comparison, paper, and appendix figures or tables needed to support verified mathematical-modeling decisions and claims.

中文简介正在准备中。当前显示原文说明。

zhnnky329/MathModeling-skills10612026年9月24日 更新

查看 zhnnky329 的全部技能

报告此技能的问题