数学建模与论文工厂：从数据分析到竞赛论文的 Skill 流水线
SkillHub 社区 Skill「数学建模与论文工厂」（@user_0210c829/math-modeling-framework，v1.1.0）面向数据分析与 XGBoost/回归/分类/聚类建模，并覆盖 CUMCM、MCM、ICM 等竞赛与学术论文成稿。官方说明包含强制图表骨架、质量门禁、数据泄漏检查、LaTeX 与 GB/T 7714 规范及去 AI 味写作，需 OpenClaw 环境，腾讯文档交付使用 qclaw_tdoc_mcp_call。本文介绍定位、核心能力、skillhub 安装方式与适用注意，事实以 SkillHub 页面与安装文档为准。
Read More通用数学建模工作流：把赛题拆成可执行的建模流水线
SkillHub 社区 Skill「通用数学建模工作流」（@user_3937f0b6/math-modeling-solver，v1.0.0）面向华中杯、CUMCM 等多小问数学建模竞赛，用 SKILL.md 规定理解题意、架构设计、Python 求解实现、约束校验与结果分析五阶段，并给出数据结构、代价函数与交付物清单。无需 API Key。本文说明定位、核心能力、skillhub 安装命令及 Cursor 等 skills 路径，并给出可复现的启用方式与适用注意。
Read More数学建模全流程专家：竞赛五阶段与论文双引擎
本文介绍 SkillHub 社区 Skill「数学建模全流程专家」（@user_0210c829/mathmodel-workflow-v3，v3.0.0）。它覆盖吃透赛题、建模、编码求解、论文撰写与验收门禁五阶段，支持 Typst/LaTeX 双引擎与题型防错知识库，且无需 API Key。文章说明定位与核心能力，给出 skillhub CLI 安装命令及 Cursor、Claude Code、Codex 的 skills 目录示例，并说明在 Agent 中按阶段启用的方式与社区来源的使用注意。
Read Moreai数模科研绘图skill：把 CSV 与自然语言需求变成科研风图表
ai数模科研绘图skill（ModelViz，@user_147de1c0/modelviz-skill）是 SkillHub 上面向数学建模与科研可视化的 data-analysis 类 Skill。用户提供 CSV/XLSX/XLS 与自然语言绘图需求后，Skill 先分析趋势、对比、分布或相关性等表达意图，再从上百个内置科研模板中召回并选型，在不修改原始模板的前提下适配数据、检查 Python 依赖、输出 PNG/SVG/PDF 与可复现代码，并针对空白图、字体、标签重叠等问题自动修复。安装可参考 skillhub.cn/install/skillhub.md，使用 skillhub install 指向各客户端 skills 目录。
Read More数学建模 skill：把实际问题拆成可求解的建模流程
数学建模 skill（@user_b392afca/math-modeling）是 SkillHub 社区版 1.0.0 的 data-analysis 类 Skill，无需 API Key。它引导 Agent 完成问题界定、假设与变量、模型构建、求解分析、敏感性检查与报告式呈现，适用于优化、预测、仿真、评估与决策类建模，以及文字题转方程与结构化假设。安装需按 skillhub.cn/install/skillhub.md 安装指定坐标。
Read MoreDeepSeek Harness Mathematical Modeling Team Plugin Pack
The DeepSeek Harness plugin `dsh-math-team` provides a standardized collaboration framework for mathematical modeling competitions. The plugin includes two types of Agent presets: `model-code` for modeling programming and `paper` for paper writing, supporting multi-person collaboration in independent workspaces via GitHub/Gitee. Core features include quality gates such as M1-M2/P1-P2, particularly M2 robustness attacks, independent dual-model review, and mandatory figure review, ensuring the quality of both the model and the paper. The plugin requires DSH 0.2.0+ and is installed/configured via the `link:` method.
Read MoreGateCraft: A Gated Mathematical Modeling Skill Suite
GateCraft is a mathematical modeling plugin for DeepSeek Harness. It adopts a “gated” workflow that decomposes the solving process into five stages: problem reading, modeling, coding, analysis, and writing, with human involvement in stage decisions and acceptance. The plugin includes 9 Skills and 1 DSH Preset, covering national-award writing, LaTeX typesetting, and full-workflow orchestration. Its core is the `paper-gate` hard-constraint checking mechanism, which uses three layers of rules—facts, invariants, and observations—together with the `docgate.py` engine—to perform 13 automated document checks (including FAIL/WARN), ensuring controllable results. In addition, the plugin provides auxiliary tools for optimization, figures, and prompts. It is primarily designed for statistical and optimization problems, aiming to support human-machine collaboration and transform mathematical modeling from a “black box” into a controllable pipeline.
Read Moredsh-vision-edge-doubao: Adding Vision Capability to DSH via Edge and Doubao Web
dsh-vision-edge-doubao is a DSH visual plugin developed by iceBear662 (MIT, v0.1.1), which drives the local Edge...
Read Moredsh-ultramath: UltraMath Mathematical Modeling Contest Multi-Agent Solver Plugin
dsh-ultramath is a multi-agent solving plugin for DeepSeek Harness designed for mathematical modeling competitions, developed by Andiii208 and licensed under the MIT License. Through native Agent presets and skill packs, this plugin standardizes the mathematical modeling solution workflow into seven stages—"problem reading, framework, derivation, coding, verification, paper writing, and review"—thereby solving the fragmentation issue of single-turn prompt processes. Core features include providing the UltraMath master controller and four single-stage role presets (e.g., Mathematician, Engineer); integrating a built-in library of 33 models and paper templates to enable self-contained installation and idempotent local data synchronization. It establishes strict quality gates covering seven categories of controls: independent verification, review blockers, blind review mechanisms, and academic integrity, where any violation results in an immediate veto. Furthermore, it introduces a "digital freeze" mechanism to ensure the consistency between paper data and code.
Read MoreMathModelingAgent: An Evidence-Driven Verification Plugin for Mathematical Modeling and Competition Problems
MathModelingAgent is a DSH plugin designed for open-ended mathematical modeling, prediction, optimization, and other tasks, addressing the issue where code runs correctly but conclusions may still be erroneous. Its core mechanism registers key conclusions as Claims, which are then verified through Obligations and Evidence, explicitly distinguishing among three states: PASS, FAIL, and INCONCLUSIVE, with particular emphasis on retaining the INCONCLUSIVE state when evidence is insufficient to avoid forcing a definitive conclusion. The plugin provides two Skills: math-modeling-agent for advancing the model, and math-modeling-audit for independent auditing without modifying the original text. It supports optional tools such as Python, Lean, and Wolfram for numerical computation.
Read More