数学建模的 Python 或 MATLAB 实现、运行、表格输出、可视化和复现阶段。
Send this to Claude Code, Codex or Cursor. The agent checks the Skill for safety first and installs it only after you confirm.
读取 https://funcoding.ai/skills/xiaomacoltai/math-modeling-skill/skill-2/install.md ，按里面的步骤帮我安装这个 Skill。
ROLE_ROOT：本文件所在目录。SKILL_ROOT：ROLE_ROOT/../../..，只读。PROJECT_ROOT：用户项目目录，所有代码、结果和图只写这里。优先读取 PROJECT_ROOT/题目分析报告.md、PROJECT_ROOT/术语表格.md 和题目附件。若用户只执行本阶段，可从用户提供的模型说明开始；若说明不足以实现，先反馈缺项。
.py、MATLAB .m，或用户要求的两套实现。results/ 中的运行结果表格和必要文本结果。figures/ 中的原始数据图、模型运行过程图、模型最终结果图，每类至少 3 张逻辑候选图、合计至少 9 张，并覆盖全部子问题：每个子问题在三类中各至少 1 张。文件名使用 raw_q1_*、process_q1_*、result_q1_* 等格式，不设上限；同一图的 SVG、PNG 和灰度预览只计 1 张。允许继续多生成，不机械删除有效备选视角。flow_overall_model.*，覆盖输入、子问题依赖、模型、求解、验证与输出；子问题存在独立分支、循环或三步以上求解链时，补充 flow_qN_model.*。与三类候选图分开，不计入其配额，也不替代结果图。results/复现清单.json。python scripts/check_env.py --features data visualization optimizationcheck_matlab_env(["data","visualization","optimization"])PROJECT_ROOT 执行的最小命令；任何结论必须来自真实输出。P1 最小可运行结果门禁；实现问题由编程手修正，模型合同问题携证据返回建模手。未返回 PASS 不得继续扩展。q1…qN。绘图前加载 tools/figure/SKILL.md 并完成数据剖析与图表契约，按子问题核对行列、类型、缺失、分组样本量、分布、异常值和单位；先用一句话写出核心结论，再选择图型、证据面板、主次比例、统计口径、图例策略与最终尺寸。无法判断图型或用户指定图型存在误导风险时，读取 tools/figure/references/chart-types/chart_selection.md。scripts/plot_style.py 或 MATLAB 的三个出版绘图工具复制到 PROJECT_ROOT/utils/ 后使用。按 tools/figure/SKILL.md 的 Nature/SCI 视觉论证流程生成三类候选图，每类至少 3 张、合计至少 9 张，且每个子问题在三类中各至少 1 张：不把不同重要性的面板机械等分，不用长标题、密集逐点标记、装饰性纹理或面板内重复图例堆成仪表盘；统计标注必须由代码计算，官方模板要求优先于内置基线。tools/figure/scripts/export_figure.py 或 export_publication_figure() 的布局与设计门禁，同时输出 SVG 与至少 300 DPI PNG；再运行 python "<SKILL_ROOT>/references/roles/编程手/scripts/figure_audit.py" "<PROJECT_ROOT>/figures" --questions q1 q2 ... qN --strict，实际打开彩色 PNG 和灰度预览，在论文预计尺寸下检查视觉层级、缺字、裁切、遮挡、颜色、尺度和面板一致性。有问题则改代码、重跑、重审，不能关闭门禁后继续，也不能直接修改位图。flow_qN_model。节点与连线必须来自已确认的模型和真实代码，用已安装的 Matplotlib/MATLAB 原生绘图能力生成（不新增依赖），保留可运行生成代码；样式、命名、导出与自检见 tools/figure/references/chart-types/flowchart.md。python scripts/repro_manifest.py --project-root <PROJECT_ROOT> ...。references/质检清单.md 完成作者自检，再派发独立质检 Subagent 执行 P2 编程终检；未返回 PASS 不得进入论文阶段或宣称编程交付完成。P1：质检 Subagent 在隔离环境或只读副本中执行最小命令，核对退出码、输入到结果的追溯、单位、数值范围、关键约束和 M1 模型合同。它是纵向切片，不要求完整图表或最终性能。P2：代码、结果、每类至少 3 张且覆盖全部子问题的三类图和复现清单冻结后，质检 Subagent 独立运行唯一复现命令并核对输入哈希、种子、关键数值、边界、量纲、各子问题图表语义及文件完整性。机械图审继续使用带全部 --questions 的 figure_audit.py --strict，Subagent 负责实际读图，检查单图核心结论、主次面板、图例、统计区间和最终尺寸可读性，而不是只确认文件能打开；并核对建模流程图与真实模型/代码一致、覆盖全部子问题且未替代结果图。两次门禁均按 ../../../references/Subagent调度.md 返回证据；被审代码、数据或参数发生实质变化时重跑受影响门禁。
| 情形 | 读取 |
|---|---|
| 开始实现 | references/工作流程.md |
| 使用 MATLAB | references/MATLAB规范.md |
| 画图 | tools/figure/SKILL.md |
| 不确定用什么图，或需审查指定图型 | tools/figure/references/chart-types/chart_selection.md |
| 需要图表函数 | tools/figure/references/api-templates/plot_recipes.md |
| 需要具体算法 | ../../../references/算法索引.md，再读取匹配的 ../../../assets/*.md |
| 处理 Excel | ../../../tools/xlsx/SKILL.md |
| 交付前 | references/质检清单.md |
| 阶段内独立验收 | ../../../references/Subagent调度.md |
若实际运行证明模型公式、约束或参数定义冲突，停止通过改算法规避问题，把证据反馈给建模手。
anthropics/skills180kApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
AI & agents
anthropics/skills180kA set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
AI & agents
anthropics/skills180kanthropics/skills180kGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
AI & agents
anthropics/skills180kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
AI & agents
anthropics/skills180kStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.
AI & agents