Updated 1mo ago
by mantou6666
Math-Modeling-Agent-Flow
Math Modeling AI Agent Flow | 数学建模全流程 AI 助手（国赛 CUMCM / 美赛 MCM-ICM）。四阶段流水线 Solver→Paper→Finalizer→Growth：解题认证、论文写作、提交终检、赛后复盘。防 AI 幻觉、防版本冲突，可安装到 Claude Code / Codex。
27 GitHub stars (27)
| Period | New stars |
|---|---|
| Sep 27 | 0 |
| Sep 28 | 0 |
| Sep 29 | 0 |
| Sep 30 | 0 |
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | −1 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | +1 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | 0 |
- 10 skills (10 skills found in its SKILL.md files)
- 0 forks (0 forks)
- 1mo ago last update (Last updated 1mo ago)
Install
Skills CLI
npx skills add mantou6666/Math-Modeling-Agent-Flow
Asks which skills and agents to install. Just one: npx skills add mantou6666/Math-Modeling-Agent-Flow --skill math-modeling-finalizer — add -g for every project.
Claude Code
git clone https://github.com/mantou6666/Math-Modeling-Agent-Flowcp -r "Math-Modeling-Agent-Flow/math-modeling-finalizer" ~/.claude/skills/
Copies the math-modeling-finalizer skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add mantou6666/Math-Modeling-Agent-Flow
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
math-modeling-finalizer
数学建模项目收口与终审 Skill。用于正式结果已基本冻结后的参赛者尺度代码简化与行为回归、最终完整复审、AI 工具使用详情 DOCX、Word/PDF 排版检查、支撑材料 ZIP 与提交前卫生检查。典型请求包括“结果已经定了，把代码改得更像学生项目”“最后完整审一遍”“检查最终 Word/PDF”“生成 AI 使用详情和支撑材料”。若需要重新建模、修改 evaluator 或正式结果，路由回 math-modeling-solver；正文、摘要、引用语义或公式写作问题路由回 math-modeling-paper；提交后的项目复盘/教学交给 math-modeling-growth。
math-modeling-finalizer/SKILL.md on GitHub (opens in a new tab) -
math-modeling-growth
把真实项目的阶段结果、决策、证据、失败记录和当前进度，转化为通俗、循序渐进、可执行的学习解释与赛后成长报告。用户要求复盘项目、理解自己学到了什么、解释某次决策、生成赛后报告、从项目进度推进学习，或需要按接受度逐步教学时使用；优先读取 Solver、Paper、Finalizer 等上游阶段产物和当前冻结结果。
math-modeling-growth/SKILL.md on GitHub (opens in a new tab) -
math-modeling-paper
数学建模竞赛证据约束论文写作 Skill。用于论文结构、正文、摘要、引用语义位置、canonical LaTeX、图表叙事、附录/README 与论文内 AI 披露；正式数字只消费 Solver Result Certificate，不重新计算或改写科学结果。适合“重写摘要”“优化正文”“处理引用/公式/图表”“让论文更像竞赛论文”等任务。若问题会改变模型、evaluator 或正式结果，路由回 math-modeling-solver；已冻结结果后的代码人味化、最终 Word/PDF/ZIP 与独立 AI 使用详情交给 math-modeling-finalizer。
math-modeling-paper/SKILL.md on GitHub (opens in a new tab) -
math-modeling-solver
数学建模竞赛通用协作求解与结果认证 Skill。用于新题理解、Problem Contract、独立建模发散、Web Research 接入、模型/算法选择、formal evaluator、复杂优化搜索空间审计、程序求解、结果验证与 Result Certificate。尤其适用于“怎么建模”“为什么搜不到更好结果”“evaluator 是否正确”“代码是否真正符合题意”等会改变科学结果的问题。论文措辞、引用与 DOCX 版式交给 math-modeling-paper；已冻结结果后的代码人味化与最终交付交给 math-modeling-finalizer。
math-modeling-solver/SKILL.md on GitHub (opens in a new tab) -
modeling-abstract-finalizer
Final abstract consistency check against current Result Certificates and Paper Handoff. Does not create new scientific claims.
math-modeling-finalizer/skills/modeling-abstract-finalizer/SKILL.md on GitHub (opens in a new tab) -
modeling-behavior-refactor
Contestant-scale code simplification. Simplify unnecessary engineering structure while preserving mathematical/numerical behavior; any executable hash change requires result/evaluator regression.
math-modeling-finalizer/skills/modeling-behavior-refactor/SKILL.md on GitHub (opens in a new tab) -
modeling-delivery-gate
Final delivery checker for support archives, DOCX/static checks and exact-PDF visual review. Missing exact PDF remains NOT_VERIFIED.
math-modeling-finalizer/skills/modeling-delivery-gate/SKILL.md on GitHub (opens in a new tab) -
modeling-paper-compressor
Conditional paper length control. Run only when an explicit page limit is exceeded or the user asks to compress; preserve core claims, formulas, figures and evidence.
math-modeling-finalizer/skills/modeling-paper-compressor/SKILL.md on GitHub (opens in a new tab) -
modeling-repair-regression
Targeted repair/regression coordinator. After a confirmed defect is fixed by its owner, rerun the smallest affected downstream checks and behavior comparisons.
math-modeling-finalizer/skills/modeling-repair-regression/SKILL.md on GitHub (opens in a new tab) -
modeling-solution-auditor
Final cross-artifact audit using upstream Result Certificates and Paper Handoff. Detect inconsistencies and route them to the correct owner without creating a new scientific registry.
math-modeling-finalizer/skills/modeling-solution-auditor/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
cherry-studioby CherryHQ AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
-
ego-liteby citrolabs The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex…
-
one-skill-to-rule-them-allby rebelytics The meta-skill that builds and improves all your skills, including itself. Watches your work sessions (autonomous or human-led), captures p…
-
narrator-ai-cli-skillby NarratorAI-Studio AI 解说大师 — Agent skill；封装 narrator-ai-cli 供 Claude/Codex 等工具调用
-
J-Space-Cognition-Suiteby Tiger3807861189 J-Space Cognition Suite — a model-agnostic inference-time control suite for deep reasoning, long-horizon work, verification, and recovery.…
-
skillsby wondelai Wondel.ai Agent Skills — Business, Marketing, UX & Coding Frameworks from Bestselling Books. 50 skills + 12 guided journeys for Claude Code…