What it does
三竞赛 (CUMCM/MCM/电工杯) 数学建模 skill — harness-agnostic, 同时支持 Claude Code 与 Codex CLI, 全程问答式 (Friendly Mode), 10 阶段 + 4 反馈层 + per-Qi 加权聚合 + 题型 dim 加权 + empirical 实测分位锚定
- Connects Instruction files the AI reads
- Account or key Not confirmed yet (README not read yet)
- Category Coding
For makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/handsomezr-netizen-mathmodel-skill)Use together with
MCP servers that connect the AI to services for the same work
Fallow
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
Desktop Commander
MCP server for terminal commands, file operations, and process management
Similar Skills
Same kind of work, ordered like the Skills list
| This one mathmodel-skill | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| Maker | handsomeZR-netizen | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skills | 1 | 1 | 1 | 1 | 1 |
| GitHub stars | 306 | 463,670 | 233,682 | 148,887 | 143,987 |
| Last code change | Sep 26, 2026 | Nov 17, 2026 | Apr 20, 2026 | Nov 17, 2026 | Nov 16, 2026 |
| License | MIT | MIT | – | Apache-2.0 | MIT |
1 skills (instruction sets) by handsomeZR-netizen that an AI reads and follows · not an MCP server
How a Skill differs from MCP
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Works with
Claude CodeCodex
From the maker’s README and the folders in the repo
Install
Is it safe?
- Who made it
GitHub account handsomeZR-netizen (person), 2 years old
- Use and upkeep
★ 306 stars, few users so far · code last changed Sep 26, 2026
- Any scripts?
20 scripts that can run on a computer: scripts/render_ai_usage.py, tests/test_ai_usage.py, scripts/doctor.py, scripts/download_cumcm_papers.py and 16 more
- Uses the internet?
Scripts that go online: scripts/download_cumcm_papers.py
- Changes machine-wide settings?
No hooks or writes to machine settings found
Checked automatically from the repo files at commit e0e65c8 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
First: which AI do you use?
Pick your app and this page shows only how to install it there
Option 1Upload to claude.ai (web and app)
Uploading to claude.ai would fail: the description is over 200 characters (536). Use "Let the AI install it" instead
Option 1Let Claude Code install it
Copy this sentence and paste it into a Claude Code chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Restart Claude Code, then type /mathmodel-skill or ask for a matching task and Claude picks it up
Checked against official docs Nov 12, 2026 · Source: code.claude.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.claude/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Restart Claude Code, then type /mathmodel-skill or ask for a matching task and Claude picks it up
ChatGPT desktop app
The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills
Option 1Let ChatGPT install it
Open Codex in the ChatGPT desktop app and paste this sentence into the chat
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Option 2Put the folder there yourself
Put the mathmodel-skill folder at ~/.agents/skills/mathmodel-skill
~ is your home folder ($HOME)
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
After installing
- ChatGPT desktop app: open Skills in the sidebar to see that the skill is there
- To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
- Codex picks up newly installed skills by itself; if one does not show up, restart Codex
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
ChatGPT on the web and mobile
Skills you install yourself do not work here; only skills that come with a plugin from the directory
To use this skill with ChatGPT, use the ChatGPT desktop app as above
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Option 1Let Codex install it
Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Restart Codex, then ask for a matching task; Codex lists the skill
Option 1Let Cursor install it
Copy this sentence and paste it into a Cursor chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
In Cursor’s Agent chat, type / and pick mathmodel-skill
Checked against official docs Nov 12, 2026 · Source: cursor.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.cursor/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
In Cursor’s Agent chat, type / and pick mathmodel-skill
Option 1Let the AI install it
For other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your app · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com
For Terminal users
Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.
Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026
View the original SKILL.md
The text below comes from the maker’s repo, not from PopNx MCP
Showing the first 8,000 characters · Open the full file on GitHub
---
name: mathmodel-skill
description: CUMCM 国赛、MCM/ICM 美赛与电工杯数学建模竞赛的端到端协作工作流。Use when a user explicitly works on one of these modeling contests or asks to run/review a modeling-competition paper from problem selection through modeling, solving, robustness, writing, compliance, and final submission review. Provides 10 stages, persistent decision state, competition-specific rules/templates, deterministic scoring helpers, numbered decisions, and Codex/Claude Code handoff. Do not trigger for generic model selection, ordinary data analysis, or non-competition paper review.
---
# mathmodel-skill — 数学建模三竞赛工作流 (v6.2)
10 阶段把 72–96 小时的竞赛协作变成可恢复、可检查的流程。用户回答关键问题,agent 维护状态与脚本。每阶段产出经过 rubric 自评、定向精修与跨阶段一致性回检;Stage 8–9 先遵守当届官方规则,再做多视角终审。CUMCM 包含 91 份来源文档,其中 59 份进入文本统计;MCM/电工杯经验统计明确为 `n=0`,不提供合成分位。
**v6.2 更新**: 新增 `scripts/init_workspace.py`(只创建、不覆盖的工作区初始化)与 `scripts/status.py`(只读进度看板:阶段 verdict、per-Qi、合规门、截止倒计时、模式建议与下一步);启动与“看进度”改由脚本确定性完成。v6.1 的规则基线、AI 披露链路、fail-closed 模板与 doctor 预检保持不变。
---
## Codex 原生入口
Codex 优先按 skill 目录发现本文件:
- 用户级安装: `$HOME/.agents/skills/mathmodel-skill/`
- 项目级安装: `<repo>/.agents/skills/mathmodel-skill/`
- UI 元数据: `agents/openai.yaml`
- 插件分发元数据: `.codex-plugin/plugin.json` + `skills/mathmodel-skill/SKILL.md` shim
- 项目指导: `AGENTS.md` 仍可作为 repo / workspace 级 instructions, 但不是唯一入口
当 skill 已安装后, 用户可直接说"开始建模"或显式说"使用 `$mathmodel-skill` 开始建模"。
---
## Harness 兼容 (Claude Code / Codex)
本 skill v6.2 以 Codex Skills 为一等入口, 同时保持 harness-agnostic 设计:
| harness | 入口文件 | 用户交互工具 | 状态文件 |
|---------|---------|-------------|---------|
| Claude Code | `SKILL.md` (本文件) | `AskUserQuestion` 工具 | `<cwd>/state/decision_log.json` |
| Codex CLI / Codex app | skill 目录中的 `SKILL.md` + 可选 `AGENTS.md` | markdown 编号列表 | 同上 (**互通**) |
跨 harness 互通: day 1 用 Codex 跑 stage 0-2, day 2 切回 Claude Code 接着 stage 3+, 状态完全保留。详见 `references/harness_compat.md`。
---
## 问答式优先 (Friendly Mode)
**核心原则**: 用户只需回答**编号问题**, 不应被要求手敲 bash / python / json。
- 离散选项 (选竞赛 / 选题 / 选模型 / verdict 决策) → **必须**用问答式
- 自由文本 (PDF 路径 / 截止时间) → 单行回复
- 状态读写 (decision_log.json) → agent 自动完成
- 每个 stage 的关键决策点都有 "让我决定 (推荐 X)" 兜底选项
优先使用当前 harness 可用的原生选择 UI;没有时回退到 markdown 编号列表。两者语义等价,见 `references/harness_compat.md` §1。
---
## 路径解析协议 (任何阶段必读)
| 类型 | 位置 | 例 |
|------|------|-----|
| skill 内通用 | skill 根目录的相对路径 | `references/stage_05_subproblem_loop.md`, `templates/shared/decision_log.json` |
| **竞赛特化** | `competitions/<comp>/...` 按 decision_log.competition dispatch | `competitions/cumcm/winning_patterns.md`, `competitions/mcm/abstract_template.md` |
| **LaTeX 模板** | `templates/latex/<comp>/main.tex` | `templates/latex/cumcm/main.tex`, `templates/latex/mcm/main.tex` |
| 用户产物 | 用户工作目录的相对路径 | `<cwd>/state/`, `<cwd>/results/`, `<cwd>/figures/`, `<cwd>/paper_workspace/` |
| state 持久化 | `<cwd>/state/decision_log.json` | 各 stage 必读必写 |
| 环境变量 | `MATHMODEL_STATE_DIR` (兼容 `CUMCM_STATE_DIR`) / `MATHMODEL_COMPETITION` 可覆盖 | scripts 用此变量 |
约定: `<skill>/` = skill 安装目录, `<cwd>/` = 用户 cwd, `<comp>/` = 当前竞赛 (cumcm | mcm | diangong)。
---
## Quick Start (用户首次说"开始建模")
```
1. 一段话介绍 (≤50 字): "启动数学建模工作流, 10 阶段 + 三竞赛, 全程问答式."
2. 收集下列 5 个启动字段;用户已经提供或 state 已记录的字段不再询问,只把尚缺字段合并成一轮问答 (Claude Code: AskUserQuestion; Codex: 编号列表):
- 竞赛 (cumcm 国赛 / mcm 美赛 / diangong 电工杯, 默认 cumcm)
- 题号 (依竞赛: cumcm A-E / mcm A-F / diangong A-B; "未公布"亦可)
- 队员数 + 各人擅长 (建模/编程/写作)
- 截止时间 (ISO 字符串或 "距现在 X 小时")
- 题目 PDF 路径 ("未公布"亦可)
3. 自动初始化 (agent 自动完成, 不要让用户编辑 json):
- 运行 `python <skill>/scripts/init_workspace.py --competition <comp> --workspace <cwd>`,按已知答案追加 `--problem <题号|未公布>`、`--team-size N`、`--deadline <ISO>` 或 `--hours-left H`、`--problem-pdf <path>`
- 脚本创建 `state/ results/ figures/ paper_workspace/ paper_output/ support_materials/`,从模板生成 state 并写入 competition 与 problem_meta
- state 已存在时脚本**不修改**任何内容,只报告 competition 与 current_stage;竞赛不一致时失败,按“切到 <comp>”处理
- 脚本输出的模式建议只是建议;与用户确认后才改 mode 并写入 events
- 无法运行 Python 时,才手动复制 `<skill>/templates/shared/decision_log.json` 并写入 competition
4. 加载 `competitions/<comp>/current_rules.md`(若存在),打开其中官方链接核对当届规则并写入 compliance;再按需加载 winning patterns
5. 进入 Stage 0 (`references/stage_00_kickoff.md`), 不重复问已知字段;若题面未公布,完成环境与协作准备后保持 `qi_count=null` 并等待题面,不进入 Stage 1
```
**已有 state 触发** (用户中途回到 skill):
```
1. 运行 `python <skill>/scripts/status.py --workspace <cwd> --json` 取得 competition、current_stage、最新 verdict 与下一步;需要细节时再读 `<cwd>/state/decision_log.json`
2. 加载对应 stage_NN.md (按需结合 competitions/<comp>/* 内容)
3. 不重复读 winning_patterns
```
---
## 三竞赛 × 三模式 矩阵
时长 / 语言 / 模板 / 数据状态 由 competition 决定; token 预算 / 反馈深度由 mode 决定。两者**正交组合**。
| Competition | 时长 | 语言 | LaTeX | 规则基线 | 经验数据状态 |
|---|---|---|---|---|---|
| cumcm | 72h | 中文 | xelatex / 原创 ctexart | CUMCM 2026 | 91 来源文档 / 59 可提取样本 |
| mcm | 96h | English | pdflatex / article | COMAP 2027 | `n=0`,无论文分位 |
| diangong | 72h | 中文 | xelatex / ctex | 官网 2026-03-21 页面 | `n=0`,无论文分位 |
| Mode | 上下文策略 | 反馈层 | 用途 |
|---|---|---|---|
| fast | 只保留当前阻断项与最小证据 | L1 单次 | 选题试跑 / sanity check |
| standard | 按阶段加载并保留决策摘要 | L1+L2 | 默认主流程 |
| championship | 在终审阶段扩展证据与独立视角 | L1+L2+L3+L4 + red-team | 提交前最后冲刺 |
模式自动推荐 (按距 deadline 剩余;`scripts/status.py` 按同一规则计算,仅作建议):
- > 60h: standard (最后 6h 升 championship)
- 24-60h: standard
- 6-24h: fast 关键阶段 + championship 终审
- < 6h: 直接进 stage 9 (championship)
---
## 10 阶段索引
| # | 阶段 | reference | 时长 | 反馈 | 竞赛差异点 |
|---|------|-----------|------|------|-----------|
| 0 | 团队启动 + 资料预扫 | `stage_00_kickoff.md` | 1h | L1 | 时长 / 语言 / 编译器 / 题号体系 |
| 1 | 选题 (多题对比 → 1) | `stage_01_problem_selection.md` | 2-4h | L1 | 题号体系 (A-E/A-F/A-B) + task_type 写入 |
| 2 | 问题深度解析与分解 | `stage_02_analysis.md` | 2-3h | L1 | 通用 |
| 3 | 模型选型 (证据驱动的候选比较) | `stage_03_model_selection.md` | 2-4h | L1 + 反事实 | 通用 |
| 4 | Foundation (假设+符号+术语) | `stage_04_foundation.md` | 1h | L1 | 通用 |
| 5 | **递归子问题循环** Q1..Qn + per-Qi 加权聚合 | `stage_05_subproblem_loop.md` | 按题目分配 | L1 + 子检查点 | 从题面提取实际子问数;per-Qi 加权 |
| 6 | 全局灵敏度 / 稳健性 | `stage_06_robustness.md` | 2-3h | L1 + L2 | 工程参数 (diangong) vs 数学参数 (cumcm/mcm) |
| 7 | 模型评价 + 推广 | `stage_07_evaluation.md` | 1-2h | L1 | 通用 |
| 8 | 论文写作 + 合规装配 | `stage_08_writing.md` | 12-30h | L1 + L2 | 当届规则、AI 披露、摘要类型与 LaTeX 模板 |
| 9 | 提交合规 + Panel | `stage_09_review.md` | 2-6h | L1 + L3 panel | 页数/匿名/披露 + anti-patterns + personas |
---
## 加载协议 (节省 token 的关键)
**只在进入阶段 N 时加载** `references/stage_NN_*.md`。**切勿**一次性全读。
各阶段额外加载 (按需 + 按 competition 切换):
- 每阶段开头: `<cwd>/state/decision_log.json` 必读
- 每阶段结尾: `<cwd>/state/decision_log.json` 必写 (核心决策 + 5 维评分)
- stage 1-9: `references/rubrics.md` 对应章节 (L1 评分用)
- **stage 1**: `competitions/<comp>/topic_specs.json` (题号 → task_type 映射)
- stage 3, 5: `references/model_catalog.md` (跨竞赛通用)
- **stage 5**: per-Qi 评分跑完后调 `scripts/score_artifact.py --mode aggregate_qi` 聚合
- **stage 0 / 8 / 9**: `competitions/<comp>/current_rules.md` 存在时读取,并核对其中官方链接
- **stage 8**: `competitions/<comp>/{winning_patterns, phrase_bank, abstract_template, paper_skeleton}.md`
- **stage 8 经验锚点**: `competitions/<comp>/empirical.json` 只作评分前参考;CUMCM 为 59 份可提取样本的观察分位,MCM/电工杯为 `n=0` 占位且不得推断数值门槛
- **stage 9**: 先做规则合规门,再用 `anti_patterns.md` 与 `rubric_overlay.json` 的 panel personas
- 触发反馈时: 对应 `references/feedback_layer*.md`
- harness 适配差异 (Codex 用户必读): `references/harness_compat.md`
---
## 收敛准则 (统一定义, 三处一致)
**verdict 优先级 (从高到低)**:
| verdict | 触发 | 行为 |
|---------|------|------|
| `block` | issues 含 ≥1 high-severity | 暂停 skill, 用户介入 |
| `pass_early` | raw_min ≥ 9 AND weighted_mean ≥ 9 | iter-1 早退 |
| `pass` | raw_min ≥ 7 AND weighted_mean ≥ 8 | 进下一阶段 |
| `pass_with_review` *(stage 5)* | 任 Qi mark_for_review 但加权阈值满足 | 进 stage 6, L2 必读 review_qis |
| `refine` | 其他 | section-patch 精修, iter+=1 (cap 3) |
| `refine_partial` *(stage 5)* | 任 Qi.min < 7, 其他 Qi 已 pass | 仅 refine 该 Qi, 不动其他 |
| `carryover` | iter == 3 仍 refine | 进下一阶段, 标记由 L2 处理 |
`weighted_mean` = Σ(s_i × w_i) / Σ(w_i), 权重来自 `config/dim_weights.json[<comp>][<task_type>]` (clamp [0.7, 1.5]); `task_type=default` 全 1.0 等价老逻辑。
此定义在 `feedback_layer1_critic.md` / `rubrics.md`Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
From GitHub
- GitHub stars
- 306
- Maker
- handsomeZR-netizen
- License
- MIT
- Last code change
- Sep 26, 2026
- SKILL.md files in the repo (including translated copies and templates)
- 2
- Topics
- agents-md, claude-code, claude-skill, codex-cli, cumcm, diangong, friendly-mode, harness-agnostic, icm, latex, math-competition, math-modeling