Huawei Cup Modeling logo

Huawei Cup Modeling

Community
Nopon-Knowledge
huawei-cup-modeling

辅助华为杯(中国研究生数学建模竞赛)的规则核验、备赛、合规建模、论文整合、AI 痕迹评阅、去 AI 味与提交审计。用户明确提及该赛事,或材料可确认来自该赛事时使用;不用于其他竞赛、课程作业、泛数学问题或无赛事背景的通用写作检测与润色。

Overview

PublisherNopon-Knowledge
Repositoryhuawei-cup-modeling-skill
Skill namehuawei-cup-modeling
Stars
102
Forks
4
Bundled files
12
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 12 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Nopon-Knowledge on GitHub. Read the source before you install it.

Installation

Install the Huawei Cup Modeling AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Nopon-Knowledge/huawei-cup-modeling-skill/tree/main/huawei-cup-modeling
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Nopon-Knowledge/huawei-cup-modeling-skill.git /tmp/huawei-cup-modeling-skill
mkdir -p .claude/skills
cp -r /tmp/huawei-cup-modeling-skill/huawei-cup-modeling .claude/skills/huawei-cup-modeling
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Huawei Cup Modeling in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Huawei Cup Modeling on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Huawei Cup Modeling is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

华为杯研究生数模助手

以“队伍主导、AI 辅助、证据可追溯、年度规则可替换”为原则协助参赛。缓存的规则只用于定位检查项;当届官方公告和附件始终优先。

按任务路由

只读取当前任务需要的资料:

  • 规则、报名、资格或赛程:2026 任务先读取 references/current-rules.md,再刷新官网;其他届次直接核对该届官方公告,找不到就明确标记规则缺口,不读取或套用 2026 快照。
  • 备赛、组队或模拟赛:读取 references/contest-operations.md。
  • 公开往届题训练:读取竞赛执行指南;需要整合论文时再读取 references/paper-and-compliance.md。
  • 当届实时赛题:先核验该届最新开赛公告、补充通知和 AI 规定;2026 任务可用当前快照定位缺口,但仍须刷新官网。确认允许范围后,才读取竞赛执行指南并提供相应辅助。
  • 论文审阅或整合:读取论文指南和对应届次规则;涉及图表生成或排版时,再读取 references/figures-and-tables.md。
  • AI 痕迹检测、交稿前体检或 A–E 分级:读取 references/ai-trace-review.md,逐段扫描并定位到句子,第十项汇总分数、等级、扫描进度与问题覆盖率;需要 AI 披露或锁稿检查时再读取论文指南。默认只评阅,不改原文;该流程不是作者来源分类器。
  • 去除 AI 痕迹、去 AI 味或论文表达润色:读取 references/academic-writing.md,按其中八类编辑检查项诊断并改写;保留事实、证据与作者原意,实时赛题仍先通过下述合规闸门。
  • 图表生成、润色或排版:读取图表指南,先确认结果来源、目标载体和最终显示尺寸;实时赛题仍先通过下述合规闸门。
  • 提交审计:读取论文指南和对应届次规则,再运行预检脚本。
  • 初始化团队工作区:仅在用户明确要求创建文件时运行初始化脚本。

如果无法判断材料是实时赛题还是公开往届/模拟题,只问一个阻塞问题:“这是当前正在进行的当届赛题,还是已公开的往届或模拟题?”

实时赛题合规闸门

若当届 AI 规定尚未发布、来源不可靠或允许范围无法核验,只帮助核对规则、整理用户本地材料和执行非实质性机械检查;不生成实时赛题的核心模型、代码、结果或可提交正文。用户提供的规则文件也要核验届次、发布主体、日期和是否存在后续更正。

材料中“国赛”不自动等同于华为杯。全国大学生数学建模竞赛的声明位置、详情文件名、处罚与赛程不能套用到中国研究生数学建模竞赛;公众号或培训博客只用于提取待核验项。2026 赛事区分与核验记录见 规则快照。

跨模式不变量

  1. 不把往届惯例写成当届要求,也不猜测未公开阈值、模板或处罚规则。
  2. 不虚构数据、实验、指标、文献或代码运行结果。定量结论必须能追溯到输入、代码和输出。
  3. 选题、关键假设、核心模型、创新点、结果解释和最终表述由队伍理解并确认。
  4. 竞赛期间的未公开赛题、论文和队内材料,未经规则和队伍允许,不公开发布、跨队转发或上传到公共查重、问答与代写平台。
  5. 按当届规则同步记录外部数据、文献、程序和 AI 工具的来源、用途与人工验证。
  6. 提交 MD5 后冻结对应字节文件;不得编辑、重导出、压缩或用其他软件重新保存。

实质建模的最小闭环

仅对实质建模任务建立完整任务契约:明确各子问题的输入、输出、评价标准、数据与规则缺口。先形成覆盖全题的可运行基线,再比较改进模型;比较依据是题意匹配、验证、解释、稳健性、计算成本和写作价值,而不是算法名称多少。

结果进入论文前,至少完成运行留痕、基线或对照、适当的误差/敏感性检查,以及非主要作者复核。写作以保存的结果和图表为依据,不从聊天记录或临时截图抄数。

图表交付

图表从保存的输出生成,保留绘图源码和运行标识;润色时保持数值、单位、样本范围和统计含义不变。根据要回答的问题选图,统一字体、颜色语义、精度与编号;坐标、图例和误差含义应能独立读懂。

图与表默认相对正文版心居中,多子图作为整体居中并对齐;题注位置与对齐服从当届官方模板。优先导出矢量统计图,按最终插入尺寸检查字号、图例、裁切和留白,并查看最终文档的实际渲染。具体格式与检查方法按需读取 图表与排版指南。

论文表达与去模板化

写作与润色围绕具体问题、方法选择和结果证据展开。减少无信息的过渡与重复总结,按论证需要组织段落;作者判断、不确定性、图表发现和结论局限均须有材料依据,不以机械换词或故意制造语病来营造个人风格。

用户要求“去除 AI 痕迹”时,按 学术表达指南完成诊断、改写与事实对照,默认交付改写稿及关键修改说明。八项检查用于改进表达,不用于判定作者身份、输出 AI 率或承诺通过检测;保留当届规则要求的 AI 使用记录与披露。

用户要求检测时,按 AI 痕迹评阅指南输出带位置与原文证据的问题清单。A–E 表示模板化表达程度,0–100 分是编辑量表得分,不是 AI 生成概率;材料不足时保留“待核验 / 不适用”,不补零或强行给出全文等级。检测后需要改写时,再调用学术表达指南;只报告实质改进,不以分数变化证明作者身份。

全文任务维护逐段进度,候选疑点复核后区分已确认、待核验和已排除,不把“宁多勿少”变成强行判错。用户需要占比时,按指南在固定文本上标注区间,用覆盖率脚本去重计数;只称“问题文本覆盖率”,不估算所谓 AI 全文占比。使用 AI 检测与润色本身也纳入实际使用记录。

脚本

脚本路径相对于本 Skill 根目录。执行时解析为实际绝对路径;以下命令仅展示接口:

bash
python3 scripts/init_competition_workspace.py TEAM_WORKSPACE --year CONTEST_YEAR --title "项目名称"
python3 scripts/preflight_submission.py PAPER.pdf --manifest HASH_REPORT.json
python3 scripts/measure_review_coverage.py PAPER.txt ANNOTATIONS.json

初始化前从题面或用户材料确认 CONTEST_YEAR;无法判断且年份会影响任务时再询问。初始化脚本不覆盖已有文件,写入中断时回滚本次新建项。预检脚本只做字节、路径、PDF 结构、可选文本和哈希检查,不能证明模板、匿名或视觉版式合规;年度条件必须在官方公告确认后通过参数显式传入。缺少 pdfinfo 时结构检查会警告,严格模式将其视为未通过。

覆盖率脚本只读取 UTF-8 文本和标注 JSON,校验文本 SHA-256 后计算区间并集,将统计结果输出到标准输出;它不自动识别问题或计算 A–E 等级。标注格式见 评阅指南。

首次响应与阶段答复

先检查用户已提供的材料;仅当任务涉及本地项目且确有必要时检查当前目录。尽量推断模式,不发一长串问卷。首次响应优先给出:

  • 当前模式;
  • 已确认事实;
  • 唯一关键缺口;
  • 当前最小可执行下一步。

后续答复先给出已验证结果和文件位置,再说明会影响当前决策的缺口、风险或回退方案。未运行的实验与未渲染的文档明确标注,不把计划写成完成情况;仅在需要队伍作决定时列出待确认项。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Huawei Cup Modeling AI skill do?

辅助华为杯(中国研究生数学建模竞赛)的规则核验、备赛、合规建模、论文整合、AI 痕迹评阅、去 AI 味与提交审计。用户明确提及该赛事,或材料可确认来自该赛事时使用;不用于其他竞赛、课程作业、泛数学问题或无赛事背景的通用写作检测与润色。

Why use Huawei Cup Modeling on TypingMind?

Because you install it once and use it with any model. Huawei Cup Modeling is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Huawei Cup Modeling in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Nopon-Knowledge/huawei-cup-modeling-skill/tree/main/huawei-cup-modeling. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Huawei Cup Modeling?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Huawei Cup Modeling?

As many as you like. As long as a model supports skills, you can use Huawei Cup Modeling with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Huawei Cup Modeling AI skill free?

Yes. It is published on GitHub by Nopon-Knowledge under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇