Implements mathematical models from a design report as reproducible code, runs calculations, and checks results. It records methods and validation findings in a results report and produces data-based PDF charts for papers.
数学建模编程实现与数据图表生成阶段。根据 ANALYSIS_MODELING_REPORT.md 编写可复现代码、运行求解、验证约束、输出 RESULTS_REPORT.md 并生成论文可用的数据驱动图表 PDF。
Review the instructions the agent will receive before you install.
本 skill 承接 2analysis-modeling。目标是把 reports/ANALYSIS_MODELING_REPORT.md 里的模型和算法落实为可复现程序，跑出可信结果，并生成论文中需要的数据型图表。
如需领域判断，读取 ../_references/math_modeling_norms.md 中的“题型防错速查”“代码实现与结果”“编码阶段常见错误”和“图表与可视化”小节。该文件只作为规范知识库，不新增本阶段的固定产物。
4drawio。5writing 提供可信数值和图表资产。按 plan.md 中"项目目录结构"创建 code/ 和 figures/ 骨架，再开始写代码。子问题数不一定是 3，按赛题实际数量调整。
按子问题顺序实现，不要一次性写完不跑。
每个子问题必须完成：
reports/RESULTS_REPORT.md 中写清楚方法、关键数值和校验结果。优化类问题必须先保证可行解，再优化目标值。预测类问题必须做训练/验证划分或合理误差评估。评价类问题必须说明指标方向、归一化方法和权重来源。
AI 在实现、求解和作图过程中，必须把关键中间过程保存成数据并做好记录，例如清洗后的数据摘要、模型参数、迭代历史、约束检查、灵敏度分析过程、图表所用数据和运行日志。中间数据优先保存到 figures/ 或 code/outputs/，并在 reports/RESULTS_REPORT.md 中说明文件用途。
reports/RESULTS_REPORT.md 推荐结构：
# 计算结果
## 运行环境
## 数据读取与预处理
## 问题一结果
## 问题二结果
## 问题三结果
## 灵敏度分析
## 约束与一致性校验
## 与建模报告的一致性说明
## 可复现运行方式
所有数据和图表结果都必须出现在 reports/RESULTS_REPORT.md 中引用
根据 reports/ANALYSIS_MODELING_REPORT.md 和 reports/RESULTS_REPORT.md 规划图表，生成 PDF 到 figures/。
典型图表：
图表要求：
caption: 或 LaTeX 的 \caption{}）。图表可以由主程序或独立脚本生成，不强制固定脚本名。无论采用哪种方式，都必须保存图表对应的数据来源和生成记录。
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Provides shared reference material for mathematical modeling competitions, covering writing conventions, problem-specific pitfalls, and chart guidelines. Other skills consult relevant sections during their work; this resource does not run independently.
Coordinates a mathematical modeling competition project from planning to final checks. It records formatting and language preferences, creates a plan and task checklist, and calls dedicated skills for modeling, coding, diagrams, paper writing, and verification.
Turns mathematical modeling competition problems and attachments into an implementation-ready report. It breaks down questions, examines ambiguous assumptions and data quality, and defines variables, equations, constraints, solution methods, and validation steps.
Turn mathematical modeling reports into DrawIO diagrams showing solution steps, model structures, and data processing flows. Produce editable source files, export PDFs for papers when DrawIO is available, and record diagram choices and export results.
Write mathematical modeling competition papers from existing analysis reports, results, and figure PDFs. Use competition templates in Typst or LaTeX, tools for document layout, to organize sections, place figures, and prepare references and summaries.
Check a completed mathematical modeling competition paper for structural errors, figure references, numerical consistency, and PDF layout problems. Supports Typst and LaTeX, fixes directly repairable issues, and produces a verification report with remaining submission tasks.