1start-mathmodel

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

数学建模工作流入口

Mathematical Modeling Workflow Entry

本 skill 负责识别比赛模式、初始化项目、记录关键选择并路由后续阶段。它不替代建模、编码、写作或验收阶段。

需要领域规范时读取

../_references/math_modeling_norms.md

；识别为 CUMCM 2026 时还必须读取

../_references/CUMCM_2026_RULES.md

。比赛专项规则优先于通用经验。

This skill is responsible for identifying the competition mode, initializing the project, recording key decisions, and routing subsequent stages. It does not replace the modeling, coding, writing, or verification stages.

Read

../_references/math_modeling_norms.md

when domain standards are needed; when identified as CUMCM 2026,

../_references/CUMCM_2026_RULES.md

must also be read. Competition-specific rules take precedence over general best practices.

启动确认

Startup Confirmation

先从用户提供的题面、现有文件和

plan.md

推断已知信息，只确认会改变流程的缺失项：

竞赛类型与年份；国赛、全国赛或 CUMCM 且年份未说明时，按当前届次确认是否为 CUMCM 2026。
排版引擎：LaTeX 或 Typst；未指定时默认 LaTeX。
论文语言；MCM/ICM/COMAP 默认英文，其他比赛默认中文。
当前是赛前训练还是正式竞赛时段。
子问题数量仅在题面无法判断且会影响初始化时确认。

不要重复询问已写入

plan.md

的选择。

First infer known information from the user-provided problem statement, existing files, and

plan.md

, and confirm only missing items that would change the workflow:

Competition type and year: if the competition is a domestic contest, national contest, or CUMCM and the year is unspecified, confirm whether it is the current CUMCM 2026 edition.
Typesetting engine: LaTeX or Typst; default to LaTeX when unspecified.
Paper language; MCM/ICM/COMAP defaults to English, while other competitions default to Chinese.
Whether the current phase is pre-contest training or the official contest period.
Confirm the number of subproblems only when it cannot be determined from the problem statement and would affect initialization.

Do not repeat questions about choices already recorded in

plan.md

CUMCM 2026 模式

CUMCM 2026 Mode

识别为 CUMCM 2026 后，在

plan.md

记录：

yaml

competition_mode: CUMCM_2026
ai_compliance: true
human_review_required: true
restricted_current_problem_search: <true when formal contest; false when training>
submission_packaging: true

该模式下必须遵守以下不变量：

AI 只辅助工作；核心建模与分析由参赛队主导，AI 参与内容逐项人工审查与核实。
H1–H4 必须由参赛队真实确认。Agent 不得代填
```
APPROVED
```
、推断沉默等于同意，或绕过等待状态。
正式竞赛时不得在任何交流平台浏览、发布或讨论当前赛题相关内容，也不得检索当前题目的答案、思路、代码或论文。允许查询解决问题所需的公开背景知识、官方数据、学术论文和软件文档。
所有实际使用的外部来源写入
```
compliance/SOURCE_LOG.md
```
；所有 AI 参与写入
```
compliance/AI_USAGE_LOG.md
```
。

After identifying CUMCM 2026, record the following in

plan.md

yaml

competition_mode: CUMCM_2026
ai_compliance: true
human_review_required: true
restricted_current_problem_search: <true during official contests; false during training>
submission_packaging: true

The following invariants must be observed in this mode:

AI only assists the work; the team must lead the core modeling and analysis, and all content involving AI participation must be individually reviewed and verified by humans.
H1–H4 must be genuinely confirmed by the team. The Agent must not enter
```
APPROVED
```
on the team's behalf, treat silence as consent, or bypass a waiting state.
During an official contest, do not browse, publish, or discuss content related to the current contest problem on any communication platform, and do not search for answers, approaches, code, or papers related to the current problem. It is permissible to consult public background knowledge needed to solve the problem, official data, academic papers, and software documentation.
Record every external source actually used in
```
compliance/SOURCE_LOG.md
```
; record all AI participation in
```
compliance/AI_USAGE_LOG.md
```
.

初始化产物

Initialization Artifacts

总是创建或更新：

```
plan.md
```
：用户选择、模式开关、阶段产物、风险和路由。
```
todo.md
```
：阶段 checklist 与当前状态。

CUMCM 2026 还需创建：

text

compliance/
├── CUMCM_2026_CHECKLIST.md
├── AI_USAGE_LOG.md
├── HUMAN_REVIEW_LOG.md
├── SOURCE_LOG.md
├── SUBMISSION_MANIFEST.md
└── private_identity_terms.txt

private_identity_terms.txt

只用于本地匿名扫描，不得放入论文、支撑材料或提交包。合规日志要保留空白条目结构，但不得预先声称已审核、未使用 AI 或已通过检查。

初始化完成后立即在

AI_USAGE_LOG.md

记录本 Agent 对工作流规划、题面文件盘点或规则配置的实际参与；不要等到编码阶段才开始留痕。

Always create or update the following:

```
plan.md
```
: user choices, mode switches, stage artifacts, risks, and routing.
```
todo.md
```
: stage checklist and current status.

CUMCM 2026 also requires the following:

text

compliance/
├── CUMCM_2026_CHECKLIST.md
├── AI_USAGE_LOG.md
├── HUMAN_REVIEW_LOG.md
├── SOURCE_LOG.md
├── SUBMISSION_MANIFEST.md
└── private_identity_terms.txt

private_identity_terms.txt

is used only for local anonymity scanning and must not be included in the paper, supporting materials, or submission package. Compliance logs must retain an empty-entry structure, but must not prematurely claim that content has been reviewed, AI has not been used, or checks have passed.

Immediately after initialization, record this Agent's actual participation in workflow planning, problem file inventorying, or rule configuration in

AI_USAGE_LOG.md

; do not wait until the coding stage to begin logging.

计划与目录

Plan and Directory Structure

在

plan.md

中写明实际采用的比赛、引擎、语言、子问题数量和模式开关，并按下列职责安排阶段：

阶段	Skill	主要产物
题面理解、候选模型与人工决策	`2analysis-modeling`	`ANALYSIS_MODELING_REPORT.md` , `MODEL_SELECTION_REPORT.md`
编程、基线、验证与数据图	`3coding-visual`	`code/` , `results/` , `RESULTS_REPORT.md`
非数据型图示	`4drawio`	`figures/.drawio` , `figures/.pdf` , `DRAWIO_REPORT.md`
论文写作	`5writing`	`paper/`
科学、结构与版式验收	`6verity`	`VERIFY_REPORT.md`
CUMCM 专项合规与打包	`7cumcm-submit`	`AI工具使用详情.pdf` , 支撑材料归档, `SUBMISSION_MANIFEST.md`

通用项目骨架按实际问题增减文件：

text

.
├── plan.md
├── todo.md
├── compliance/
├── reports/
│   ├── ANALYSIS_MODELING_REPORT.md
│   ├── MODEL_SELECTION_REPORT.md
│   ├── RESULTS_REPORT.md
│   ├── DRAWIO_REPORT.md
│   └── VERIFY_REPORT.md
├── code/
│   ├── run_all.py
│   ├── problem1.py
│   ├── ...
│   ├── utils.py
│   ├── requirements.txt
│   └── outputs/
├── results/
├── figures/
├── paper/
└── support_materials/

非 CUMCM 项目不必创建无关的合规目录或调用

7cumcm-submit

。

plan.md

, specify the actual competition, engine, language, number of subproblems, and mode switches, and assign stages according to the following responsibilities:

Stage	Skill	Main Artifacts
Problem understanding, candidate models, and human decisions	`2analysis-modeling`	`ANALYSIS_MODELING_REPORT.md` , `MODEL_SELECTION_REPORT.md`
Programming, baselines, validation, and data visualization	`3coding-visual`	`code/` , `results/` , `RESULTS_REPORT.md`
Non-data diagrams	`4drawio`	`figures/.drawio` , `figures/.pdf` , `DRAWIO_REPORT.md`
Paper writing	`5writing`	`paper/`
Scientific, structural, and formatting verification	`6verity`	`VERIFY_REPORT.md`
CUMCM-specific compliance and packaging	`7cumcm-submit`	`AI工具使用详情.pdf` , supporting material archiving, `SUBMISSION_MANIFEST.md`

Adjust the files in the generic project skeleton as needed for the actual problem:

text

.
├── plan.md
├── todo.md
├── compliance/
├── reports/
│   ├── ANALYSIS_MODELING_REPORT.md
│   ├── MODEL_SELECTION_REPORT.md
│   ├── RESULTS_REPORT.md
│   ├── DRAWIO_REPORT.md
│   └── VERIFY_REPORT.md
├── code/
│   ├── run_all.py
│   ├── problem1.py
│   ├── ...
│   ├── utils.py
│   ├── requirements.txt
│   └── outputs/
├── results/
├── figures/
├── paper/
└── support_materials/

Non-CUMCM projects do not need to create unrelated compliance directories or invoke

7cumcm-submit

待办与人工门禁

To-Do List and Human Gates

CUMCM 2026 的

todo.md

使用：

markdown

undefined

For CUMCM 2026, use the following format in

todo.md

markdown

undefined

待办事项

To-Do Items

1. 赛题与附件解析
H1. 队员确认题意理解
2. 候选模型设计、独立审查与比较
H2. 队员确认核心建模方案
3. 编程实现、基线和结果验证
H3. 队员核验核心结果
4. 非数据型图示
5. 论文撰写
H4. 队员审阅论文和 AI 参与内容
6. 科学、数值、结构和版式验收
7. CUMCM 合规检查与提交打包


非 CUMCM 模式保留普通的 2→3→4→5→6 流程。每完成一个阶段或人工门禁，立即更新 `todo.md`；等待人工确认时记录明确的 `WAITING_FOR_HUMAN_*` 状态并停止跨越该门禁。

1. Parse the problem statement and attachments
H1. Team confirms understanding of the problem
2. Candidate model design, independent review, and comparison
H2. Team confirms the core modeling approach
3. Program implementation, baselines, and result validation
H3. Team verifies the core results
4. Non-data diagrams
5. Paper writing
H4. Team reviews the paper and AI-assisted content
6. Scientific, numerical, structural, and formatting verification
7. CUMCM compliance review and submission packaging


For non-CUMCM modes, retain the standard 2→3→4→5→6 workflow. After completing each stage or human gate, update `todo.md` immediately. When awaiting human confirmation, record an explicit `WAITING_FOR_HUMAN_*` status and do not proceed past that gate.

阶段边界

Stage Boundaries

```
3coding-visual
```
负责真实计算结果和数据图；
```
4drawio
```
仅负责有实际信息的流程、结构与概念图。
```
5writing
```
只能引用可追溯到结果文件或图表数据的数值，不得重新估算。
```
6verity
```
发现上游实质错误时按问题类型路由回对应阶段，不在验收阶段重新建模。
```
7cumcm-submit
```
只在 CUMCM 模式下负责官方格式、匿名、AI 详情、支撑材料和大小限制。

```
3coding-visual
```
is responsible for actual computation results and data visualization;
```
4drawio
```
handles only meaningful flow, structural, and conceptual diagrams.
```
5writing
```
may cite only numerical values traceable to result files or chart data and must not re-estimate them.
When
```
6verity
```
finds substantive upstream errors, route back to the corresponding stage according to the error type; do not remodel during the verification stage.
```
7cumcm-submit
```
is used only in CUMCM mode and is responsible for official formatting, anonymization, AI details, supporting materials, and size limits.