Skip to content
Agentmart
Submit a tool

mathmodel-skill

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…

Skill by handsomeZR-netizen

IndexedMIT★ 294
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/handsomezr-netizen-mathmodel-skill

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

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.

Use cases: data, security, writing, research, data-analysis, writing-editing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/mathmodel-skill

What's inside

Skill 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.
License
MIT
Instructions
234 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (108)

  • plugin.json · .codex-plugin/
  • ci.yml · .github/workflows/
  • .gitignore
  • AGENTS.md
  • LICENSE
  • README.md
  • SKILL.md
  • THIRD_PARTY_NOTICES.md
  • openai.yaml · agents/
  • banner.svg · assets/
  • status-demo.svg · assets/
  • workflow.svg · assets/
  • README.md · competitions/cumcm/
  • abstract_template.md · competitions/cumcm/
  • anti_patterns.md · competitions/cumcm/
  • current_rules.md · competitions/cumcm/
  • distilled_formats.md · competitions/cumcm/
  • distilled_naming.md · competitions/cumcm/
  • distilled_phrases.md · competitions/cumcm/
  • distilled_structures.md · competitions/cumcm/
  • empirical.json · competitions/cumcm/
  • empirical_notes.md · competitions/cumcm/
  • paper_skeleton.md · competitions/cumcm/
  • phrase_bank.md · competitions/cumcm/
  • rubric_overlay.json · competitions/cumcm/
  • topic_specs.json · competitions/cumcm/
  • winning_patterns.md · competitions/cumcm/
  • README.md · competitions/diangong/
  • abstract_template.md · competitions/diangong/
  • anti_patterns.md · competitions/diangong/
  • current_rules.md · competitions/diangong/
  • empirical.json · competitions/diangong/
  • empirical_notes.md · competitions/diangong/
  • paper_skeleton.md · competitions/diangong/
  • phrase_bank.md · competitions/diangong/
  • rubric_overlay.json · competitions/diangong/
  • topic_specs.json · competitions/diangong/
  • winning_patterns.md · competitions/diangong/
  • README.md · competitions/mcm/
  • abstract_template.md · competitions/mcm/
  • anti_patterns.md · competitions/mcm/
  • current_rules.md · competitions/mcm/
  • empirical.json · competitions/mcm/
  • empirical_notes.md · competitions/mcm/
  • paper_skeleton.md · competitions/mcm/
  • phrase_bank.md · competitions/mcm/
  • rubric_overlay.json · competitions/mcm/
  • topic_specs.json · competitions/mcm/
  • winning_patterns.md · competitions/mcm/
  • dim_weights.json · config/
  • feedback_layer1_critic.md · references/
  • feedback_layer2_backtrack.md · references/
  • feedback_layer3_panel.md · references/
  • feedback_layer4_calibration.md · references/
  • harness_compat.md · references/
  • model_catalog.md · references/
  • README.md · references/papers/
  • _DOWNLOAD_REPORT.md · references/papers/
  • rubrics.md · references/
  • stage_00_kickoff.md · references/
  • …and 48 more

SKILL.md (first lines)

# 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)

---

From handsomeZR-netizen/mathmodel-skill, MIT.

Signals

Stars
294
Forks
10
Open issues
3
Last commit
Sep 26, 2026 (1 month ago)
Last release
May 22, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from handsomeZR-netizen

Cite this page

mathmodel-skill. Agent Mart. https://agentmart.dev/skills/handsomezr-netizen-mathmodel-skill (last updated 2026-10-24)