Hwb Cpgmcm Award Standing logo

Hwb Cpgmcm Award Standing

Community
xieyouxixi
hwb-cpgmcm-award-standing

Query a graduate training unit's Huawei Cup (CPGMCM) award profile, estimate the award band from the contest's total team count and a team's rank or paper score, and assess a student's preparation distance from first/second/third prizes using the unit's self-filled history and the student's own modeling and simulation experience. Use when a user asks about a training unit's Huawei Cup record, next-year award probability, Huawei Special Award hit rate, problem selection, preparation advice, or the rank needed for a given award level.

Overview

Publisherxieyouxixi
Repositoryhwb-math-modeling-skills
Skill namehwb-cpgmcm-award-standing
Stars
193
Forks
5
Bundled files
8
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.

  • 8 bundled files

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

  • Open source

    Published by xieyouxixi on GitHub. Read the source before you install it.

Installation

Install the Hwb Cpgmcm Award Standing 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/xieyouxixi/hwb-math-modeling-skills/tree/main/skills/综合评审与自我定位类/hwb-cpgmcm-award-standing
  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.

Use it in TypingMind

Enable Hwb Cpgmcm Award Standing 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 Hwb Cpgmcm Award Standing 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 Hwb Cpgmcm Award Standing 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.

HWB 华为杯获奖定位与竞争格局分析

使用自带 CSV 作为唯一来源。研究生赛为全国统一评奖,不设赛区、不设组别、没有省奖与国奖双层模型。三种模式:培养单位画像、获奖区间估算、备赛进度评估。

只有本科层次的“高教社杯全国大学生数学建模竞赛”才存在赛区与省奖;本赛事没有这两级概念,不得把赛区/省奖/组别套用到研究生赛上。

数据边界(必须首先声明)

  • 本仓库不提供任何未经核实的培养单位获奖数据。assets/unit_awards_template.csv 是空白模板(仅表头与 # 注释),须由使用者从官方获奖名单自行填写。
  • assets/cpgmcm_annual_statistics.csv 只含已公开可核实的总量:2024(第二十一届)521 个培养单位、20247 支队伍;2025(第二十二届)631 个培养单位、24371 支队伍、一等奖 244 队(1.00%)、二等奖 3085 队(12.66%)、三等奖 4830 队(19.82%)、总获奖率 33.48%。其余年份字段留 NA。
  • assets/优秀论文培养单位代码分布.csv 与 assets/培养单位代码对照_参考.csv 是参考统计与代码对照,只反映本地优秀论文样本的分布,不等于获奖统计;未出现的单位不代表无获奖或不能获奖。
  • 当模板未被填写时,只能给出方法性建议,不得虚构单位历史记录。 任何概率/区间预测必须标注为“经验估计”,非官方、不构成获奖承诺。

查询(培养单位画像)

运行 python scripts/query_unit.py --unit "培养单位名称"。

  • ok:输出该单位年度记录、各等奖合计、华为专项奖命中次数、下一届获奖概率区间(标注经验估计)、选题建议与备赛建议。
  • ambiguous:列出相近候选单位,请用户确认。
  • not_found:输出“按当前榜单口径未找到该单位记录。这不代表该单位本年度不能获奖,也可能仅是模板尚未填写。请以官方获奖名单为准。”并说明 1.00%/12.66%/19.82% 为全国性基线先验。
  • data_not_filled:模板为空时优雅提示“数据未填写”,仅给方法性建议,不崩溃、不虚构。

获奖区间估算(按总队数与名次)

当用户问“多少名次能拿几等奖”“我们这个名次大概什么水平”时,运行:

bash
python scripts/query_award.py --teams 24371 --rank 500     # 给定当届规模与名次
python scripts/query_award.py --teams 24371 --score 78     # 或给定论文质量分
python scripts/query_award.py                              # 无参 → 示例输出

输出内容:各奖项的临界名次(2025 实际锚点 1.00% / 12.66% / 19.82% 与章程上限 1.5% / 13% / 20% 两套)、本队所处区间、名次百分位,以及选做华为赛题时的专项奖提示。

转述时必须说明的三点:

  1. 锚点取自 2025 年(第二十二届)实际获奖比例,各届规模与比例会变,输出是经验估计,不是官方分数线;
  2. 名次进入一等奖区间不等于获奖,评审还受论文质量、形式审查与查重结果影响;
  3. 华为专项奖按“华为赛题参赛队内部排名”评定(一等 4 队、二等 12 队,奖金与常规奖项累加),全国名次不能直接换算成专项奖名次。

备赛进度评估

先查询培养单位画像。再仅询问缺失信息:是否参加过其他数模竞赛、次数与名称、是否获奖及等级、完整模拟/论文次数、目标奖项。输出 单位基础、个人准备度、目标差距、下一步行动。

三等奖(全国层面)

  • 无经验:建议完成 1—2 次完整限时模拟。
  • 有过其他竞赛并获奖:鼓励参赛;条件允许时做 1 次演练。
  • 有过其他竞赛未获奖:可用 $hwb-review-paper(若可用)复盘旧作,再完成 1—2 次模拟。
  • 称“具备三等奖竞争基础”;绝不承诺获奖。

二等奖

  • 多次非华为杯竞赛且多次获奖:竞争力相对强,受团队与论文质量约束。
  • 否则:系统课程学习 + 约两次使用近年华为杯赛题的完整演练(含完整代码、结果与论文)。
  • 称“达到较有竞争力的准备水平”;不说“稳定获奖”。

一等奖 / 华为专项奖

  • 先分析单位历史(若已填写)、逐年稳定性与下一届概率区间(经验估计)。
  • 单位有获奖历史可提升机会,但绝不把奖项预先分配给学生。
  • 对准备充分、经高强度演练的队伍,给出基于历史的条件性经验估计区间,标注高度不确定,不把剩余部分转成精确的“运气概率”。
  • 对未列入模板的单位,使用 1.00%/12.66%/19.82% 基线先验,并说明个体结果可能差异很大。
  • 若选择华为赛题(历届多为 B 题),可同时参评华为专项奖;建议在选题与建模深度上匹配专项奖口径。
  • 建议全流程模拟、复盘、稳定分工、可复现代码、论文质量把控与校内遴选意识。

选题建议(A—F 六题制)

华为杯固定 A—F 六题。给出选题建议时:

  • 依据团队专长、数据可得性与历年赛题难度信号(参见 数模资料/官方文件/华为杯赛事事实基准.md 中的 2020—2025 真题清单);
  • 若队伍熟悉工程数据与华为生态,可优先考虑华为赛题以争取华为专项奖;
  • 不强行推荐某题,须结合当届官方赛题说明与数据口径。

本 skill 的数据文件

文件用途边界
assets/cpgmcm_annual_statistics.csv历年参赛规模与获奖比例的已核实总量未核实年份为 NA/「待核对官方公告」,禁止编造
assets/unit_awards_template.csv培养单位获奖记录空白模板须由使用者从官方名单自行填写;空模板走“数据未填写”分支
assets/优秀论文培养单位代码分布.csv本地优秀论文样本的培养单位代码分布样本分布 ≠ 获奖统计
assets/培养单位代码对照_参考.csv5 位培养单位代码 → 单位名称(节选 30 条)教育部标准代码,仅供参考,以官方代码表为准
references/awards-data-protocol.md数据来源、字段定义、更新流程与禁止编造红线所有单位获奖表述以该文件为准

Safeguards

保留 CSV 数值。历史获奖频次只是相关性,不是配额控制。不使用“预定、分配、保证”。数据止于已填写年份;未填写年份为方法性建议。每次评估结尾必须说明:“这是一项基于单位历史(若有)与个人经历的经验评估,不是官方概率,也不能承诺具体奖项。”不得仅因单位无历史获奖而断定学生不能获奖;数据仅作先验并给出不确定性。

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 Hwb Cpgmcm Award Standing AI skill do?

Query a graduate training unit's Huawei Cup (CPGMCM) award profile, estimate the award band from the contest's total team count and a team's rank or paper score, and assess a student's preparation distance from first/second/third prizes using the unit's self-filled history and the student's own modeling and simulation experience. Use when a user asks about a training unit's Huawei Cup record, next-year award probability, Huawei Special Award hit rate, problem selection, preparation advice, or the rank needed for a given award level.

Why use Hwb Cpgmcm Award Standing on TypingMind?

Because you install it once and use it with any model. Hwb Cpgmcm Award Standing 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 Hwb Cpgmcm Award Standing in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/xieyouxixi/hwb-math-modeling-skills/tree/main/skills/综合评审与自我定位类/hwb-cpgmcm-award-standing. 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 Hwb Cpgmcm Award Standing?

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 Hwb Cpgmcm Award Standing?

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

Is the Hwb Cpgmcm Award Standing AI skill free?

It is published on GitHub by xieyouxixi. Check the repository for licensing terms. 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 👇