Agent skill

Modeling Paper Rubric and Model Selector

by yushui2022 in yushui2022/MathModel-Skill

Builds a scoring-aligned outline for a mathematical modeling paper and a model selection plan with baseline, improvement and validation experiments.

MITAuto-check passedEducation

SKILL.md written in Chinese; this summary is our English description.

Install Modeling Paper Rubric and Model Selector

skills CLI
$ npx skills add yushui2022/MathModel-Skill --skill modeling-paper-rubric-and-model-selector -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install yushui2022/MathModel-Skill modeling-paper-rubric-and-model-selector --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/yushui2022/MathModel-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/trae/.trae/skills/modeling-paper-rubric-and-model-selector .claude/skills/modeling-paper-rubric-and-model-selector && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
modeling-paper-rubric-and-model-selector
GitHub stars
454
Used in
1 other repo
Token cost
~1.8k tokens
SKILL.md length
349 words
Files
3 (incl. scripts, references)
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Builds a scoring-aligned outline for a mathematical modeling paper and a model selection plan with baseline, improvement and validation experiments.

  • Works in 6 steps: 预测类(时间序列/回归) → 分类/判别 → 评价/排序/综合指数 → …
  • Structuring a modeling paper to match a scoring rubric
  • SKILL.md covers 全局流程协作约束(长对话防漂移), 执行契约, 目标 and 何时调用, plus 10 more sections
  • Runs Python scripts from its folder; calls python

What it does

This skill, documented in Chinese, helps with mathematical modeling contest papers. From the problem statement it builds a paper outline tailored to each question, a table linking every scoring point to where the paper gives evidence, and a model selection plan with a baseline, improvements, validation and interpretation experiments.

It works inside a larger staged paper workflow. Before a formal task the agent runs a workflow guard script and stops if it fails, reads the upstream problem analysis file as the only source of sub-questions, and writes a model route JSON, a rubric alignment JSON and a scoring strategy file into the paper output folder. A Python script builds the model route, and a reference holds the default paper prompt.

Useful inputs include the contest name, the problem statement, your own reading of each question, data details such as fields, time span and missing share, the task type (predict, optimize, evaluate, classify, cluster, simulate or schedule) and the highlights you want to stress. Afterward the agent hands back to the orchestrator and records progress in workflow memory.

When your agent uses it

  • Structuring a modeling paper to match a scoring rubric
  • Choosing between candidate models for each sub-question
  • Planning baseline and comparison experiments
  • Worrying that the chosen model or metrics do not fit the question

Example prompts

  • “Build a paper outline aligned to the scoring rubric for this contest problem, then pick models for each question.”
  • “I'm unsure whether my model fits the question; propose a baseline, an improvement and validation experiments.”
  • “Create the model route and rubric alignment files from problem_analysis.json.”

Requirements

  • Python, to run the workflow guard and model route scripts
  • The upstream problem_analysis.json from the problem analysis step

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. 预测类(时间序列/回归)
  2. 分类/判别
  3. 评价/排序/综合指数
  4. 优化/调度/选址/路径
  5. 聚类/分群/画像
  6. 机理/仿真/系统动力学

What it can do on your machine

Read from SKILL.md and the folder at commit 7712876. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Modeling Paper Rubric and Model Selector loads about 1.8k tokens when it runs, and up to ~2.9k if it reads all its reference files. Until then it costs about 31 tokens; SKILL.md has 349 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from yushui2022/MathModel-Skill at commit 7712876, republished under its MIT licence (© yushui2022). 349 words, ~1,786 tokens.

Download SKILL.mdSave it as .claude/skills/modeling-paper-rubric-and-model-selector/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
modeling-paper-rubric-and-model-selector
description
按常见评分点生成建模论文结构与写作清单,并根据题目类型与数据条件给出模型选择与对照实验路线。Invoke when需要“论文格式/评分对齐/模型选型/路线不确定”。

评分对齐论文结构与模型选型(Paper Rubric & Model Selector)

全局流程协作约束(长对话防漂移)

  • 本 skill 不得作为孤立入口。用户要求完整论文、生成 Word、继续流程或不确定阶段时,先回到 paper-workflow-orchestrator 判断当前 S0-S8 阶段。
  • 启动或继续本 skill 的正式任务前,必须运行:
    bash
    python .trae/skills/paper-workflow-orchestrator/scripts/workflow_guard.py --skill modeling-paper-rubric-and-model-selector
  • 如果输出 [WORKFLOW FAIL] 或报告 status != "PASS",停止本 skill,按 paper_output/qa/workflow_guard_report.json 的失败项回补前置阶段,不得凭记忆继续。
  • 本 skill 只写入自己契约范围内的 paper_output/ 产物;完成后必须回到 paper-workflow-orchestrator 判断下一步,并用 context-memory-keeper 记录已完成产物、阻塞项和下一步。
  • 长对话中如果上下文变长、阶段不确定或用户分开调用 skill,先运行:
    bash
    python .trae/skills/paper-workflow-orchestrator/scripts/workflow_guard.py --status
    再读取 paper_output/qa/workflow_guard_report.json、paper_output/preflight_report.json、paper_output/input_manifest.json、paper_output/results/run_manifest.json 和本 skill 的上游 JSON 契约,按报告里的 recommended_skill 与 next_action 继续。
  • 继续流程前,必须把 paper_output/context/workflow_memory.json 视为长期断点记录;若其中的 current_step、next_step、recommended_skill 与 workflow_guard.py --status 不一致,以 guard 报告为准。
  • 每次完成本 skill 的产物后,先回到 paper-workflow-orchestrator 或运行 workflow_guard.py --status,再更新 workflow memory:
    bash
    python .trae/skills/context-memory-keeper/scripts/update_workflow_memory.py
    更新后读取 paper_output/context/workflow_memory.json / .md,确认下一步和推荐 skill 已记录。

执行契约

  • 上游输入:优先读取 paper_output/step1/problem_analysis.json。
  • 必须输出:paper_output/plan/model_route.json、rubric_alignment.json、scoring_strategy.md。
  • 下游交接:数据、建模与证据门禁读取模型路线;S7 的 paper-formal-writer 将模型、验证和评分字段写入正式写作计划。tasks.json 仅供 legacy/quickstart。
  • 推荐下一步:若需要外部数据,进入 authoritative-data-harvester;否则进入 data-cleaning-and-visualization。完整论文目标应回到 paper-workflow-orchestrator 判断后续阶段。
  • 失败回退:若 problem_analysis.json 缺失,先运行 problem-doc-model-selector;完整 workflow 中本步骤失败时,QA 应回退到 problem_analysis.json。

目标

把“能拿分”的写作结构与“贴题可落地”的模型选型融合成一套可复用流程,输出:

  • 一份可直接套用的论文大纲(按题目问法定制)
  • 评分点对齐表(每个评分点对应你论文中的证据位置)
  • 模型选型与对照实验路线(含基线、改进、验证与解释)

何时调用

  • 需要快速搭建符合评分标准的论文结构与写作顺序
  • 不确定模型是否贴题、是否过度复杂或解释不足
  • 已有方案但担心“答非所问/指标口径不对/验证不充分”

输入(尽量提供)

  • 比赛名称/年份/题号(可选)
  • 题面原文或关键要求(必须)
  • 你对每问的理解(可选,但强烈建议)
  • 数据情况:来源、字段、时间跨度、样本量、缺失比例(可选)
  • 约束与输出:需要预测/优化/评价/分类/聚类/仿真/调度等(必须)
  • 你想强调的亮点:创新点/可解释性/可复现性(可选)

输入契约(推荐)

执行前优先读取:

  • paper_output/step1/problem_analysis.json

如果该文件存在,必须以其中的 questions[] 作为唯一子问题来源,不得自行臆造、合并或丢弃子问题。

输出契约(推荐)

本 skill 应生成:

  • paper_output/plan/model_route.json:每一问的模型路线、验证计划、图表证据与章节落点。
  • paper_output/plan/rubric_alignment.json:评分点、证据形式和 QA 规则映射。
  • paper_output/plan/scoring_strategy.md:给人和 Agent 阅读的评分闭环说明。

这些 JSON 是项目自定义 workflow contracts,不是平台内置标准。详细规则见 docs/workflow-contracts.md。

脚本入口(推荐)

bash
python .trae/skills/modeling-paper-rubric-and-model-selector/scripts/build_model_route.py

该脚本会读取 paper_output/step1/problem_analysis.json,并将模型路线与评分闭环写入 paper_output/plan/。若该文件不存在,应先运行 problem-doc-model-selector。

外部“论文结构提示词”资源(可选)

支持把你预先准备的论文结构提示词文件(或文本)附加到本技能中,用于生成与评估。

分层目录约定(推荐)
  • SKILL.md:技能定义与用法说明
  • references/:可复用的参考材料与提示词资源(默认模板、评分点清单等)
使用方式(任选其一)
  1. 路径引用(推荐)
  • 在调用时提供:paper_prompt_path
  • 规则:若提供该路径,则优先读取其内容作为“论文结构提示词”;若未提供,则使用本技能自带的默认提示词文件。
  1. 直接粘贴
  • 在调用时提供:paper_prompt_text
  • 规则:若提供该文本,则优先使用该文本;否则使用 paper_prompt_path;若两者都没有,则使用默认提示词文件。
调用示例
  • 方式1(路径):
    • paper_prompt_path: <项目根目录>\paper_output\plan\paper_prompt.md
  • 方式2(粘贴):
    • paper_prompt_text: <把你的论文结构提示词全文粘贴在这里>
运行时整合机制(推荐参考)

在生成 A/B/C/D 任一产出前,建议读取 references/paper_prompt_default.md 作为“结构参考”:

  1. 参考优先级:此文件作为写作模板的参考,但不强制阻塞生成。生成的论文大纲应尽量对应此文件的章节要求,但允许模型根据实际语境发挥。
  2. 防遗忘机制:
    • 建议在 Prompt 中提及此文件的核心结构(如六段式摘要),引导模型生成。
    • 若用户提供了额外的 prompt,则以用户的要求为主,此文件为辅。
  3. 鼓励扩写:在保证逻辑通顺的前提下,鼓励使用学术化的“万金油”语句(如“随着…的发展”、“综上所述”)来丰富篇幅,增强文章的连贯性与体量感。

然后把 PAPER_PROMPT 作为强约束与写作风格来源,融入到:

  • 论文大纲的章节命名、写作顺序、字数分配与语体要求
  • 评分点对齐表中的“证据形态”(哪些图、哪些表、哪些检验)
  • 模型路线与对照实验设计(尤其是“模型检验/鲁棒性/敏感性/可复现”要求)
向后兼容

不提供 paper_prompt_path / paper_prompt_text 时,本技能维持原有默认行为正常输出。

约束(必须遵守)

  • Memory Interaction (必做):
    • 开始前,检查 memoryskill.md 中的 External Resources / Literature,若存在相关文献,必须将其融入“参考文献”章节及“模型建立”部分的背景综述中。
    • 完成后,将生成的“论文大纲”与“模型路线”更新至 memoryskill.md。

产出(固定结构)

A. 一页纸题意对齐
  • 每一问:输入、输出、评价指标、关键约束、边界条件、可行验证方式
Show full SKILL.md (145 more words)Show less
B. 论文大纲(按评分友好顺序)

必须包含并按题目调整比重:

  1. 摘要(中英文按要求):问题、方法、结果、贡献、关键词
  2. 问题重述:用你自己的话把每问变成可计算任务
  3. 模型假设:必要且可辩护,逐条说明合理性与影响
  4. 符号与变量说明:表格化,含单位与范围
  5. 数据说明与预处理:来源、清洗规则、缺失/异常处理、可复现步骤
  6. 模型建立(按问分小节):目标函数/约束/损失、推导或结构说明
  7. 求解方法与实现:算法步骤、复杂度/收敛、参数设置
  8. 结果与分析:主结果、可视化、对比、误差/收益解释
  9. 模型检验:对照实验、敏感性分析、鲁棒性测试、极端情景
  10. 结论与建议:对应每问给结论与可执行建议
  11. 不足与展望:诚实但不自毁,指出改进方向
  12. 参考文献:规范引用题面、数据源与关键方法
  13. 附录:关键代码、额外图表、符号补充(按比赛要求取舍)
C. 评分点对齐表(以“证据”为核心)

输出一张表:评分点 → 你提供的证据 → 论文位置(章节/图表/表格/实验)。 常见评分点映射(按比赛可增删):

  • 题意理解准确:一页纸题意对齐 + 问题重述逐问可计算
  • 模型合理性:目标/约束与题面一致,假设可辩护
  • 方法创新/改进:在基线之上有明确改进点,并说明为何有效
  • 结果可信:有验证、有对比、有误差分析或约束满足证明
  • 表达清晰:符号统一、图表自解释、结论逐问对应
  • 可复现:数据来源与处理、参数设置、算法步骤完整
D. 模型选型与路线(先贴题再高级)

对每一问输出:

  • 任务类型判定:预测/分类/聚类/评价/优化/仿真/机理建模
  • 最小可用基线:能跑通、可解释、可对照
  • 一到两条改进路线:提升精度/鲁棒/效率/解释
  • 验证计划:指标、交叉验证/留出法/回测、消融、敏感性
  • 风险点:数据不足、口径不一、过拟合、不可解释、计算超时

模型选型速查(按题目常见问法)

1) 预测类(时间序列/回归)

适用:给定历史,预测未来或估计参数。

  • 基线:移动平均/指数平滑/线性回归/ARIMA(能解释趋势与季节)
  • 改进:特征工程 + 树模型;或 LSTM/Transformer(样本量足够再上)
  • 验证:滚动回测、MAPE/RMSE、置信区间/误差分解
2) 分类/判别

适用:判定类别、风险等级、是否发生。

  • 基线:逻辑回归/朴素贝叶斯(可解释)
  • 改进:随机森林/梯度提升;代价敏感学习(类别不平衡)
  • 验证:AUC/F1/PR 曲线、混淆矩阵、阈值敏感性
3) 评价/排序/综合指数

适用:多指标打分、排序、择优。

  • 基线:规范化 + 加权和(权重可来自题面或专家)
  • 改进:熵权/CRITIC/AHP/TOPSIS/VIKOR(明确权重来源与意义)
  • 验证:权重敏感性、排名稳定性、与已知事实对照
4) 优化/调度/选址/路径

适用:资源分配、成本最小/收益最大、满足约束。

  • 基线:线性规划/整数规划(目标与约束写清楚)
  • 改进:多目标(加权/ε-约束)、启发式(遗传/模拟退火)用于大规模
  • 验证:可行性检查、对照基准策略、约束违背率、复杂度与时间
5) 聚类/分群/画像

适用:无标签分组、模式发现。

  • 基线:K-means/层次聚类
  • 改进:GMM/DBSCAN(噪声与形状复杂时)
  • 验证:轮廓系数/稳定性、可解释的群体差异描述
6) 机理/仿真/系统动力学

适用:强调机制解释、情景推演。

  • 基线:微分方程/差分方程/系统动力学
  • 改进:参数校准 + 不确定性分析;与数据驱动模型对照
  • 验证:历史拟合、情景一致性、参数敏感性

防跑偏硬规则(必须检查)

  • 每一问至少给出一个“可量化输出”和一个“可验证指标/检验方式”
  • 模型中的每个关键变量都能在题面/数据里找到定义与单位
  • 图表和结论逐问对应,不出现“做了很多但没回答问题”
  • 至少一个基线对照:证明你的方法相对简单方案有提升或更合理

最终交付(你需要让我生成时,我会给出)

  • 可直接粘到论文里的大纲与小节标题(按题目问法编号)
  • 评分点对齐表(含你该补的图表/实验清单)
  • 每问模型路线:基线 + 改进 + 验证 + 风险与备选

默认提示词文件(可复用)

当未提供 paper_prompt_path / paper_prompt_text 时,默认从以下文件读取论文结构提示词:

  • references/paper_prompt_default.md

目录约定(与项目全局对齐)

  • 赛题与附件统一放在 problem_files/,补充数据放在 crawled_data/。
  • 建议把本技能的输出(大纲/评分点对齐/模型路线)归档到 paper_output/plan/,供后续生成正文时引用。
  • 上面的 paper_prompts/... 仅为历史路径示例;当前项目推荐把自定义提示词文件也归档到 paper_output/plan/,或直接使用本技能自带的 references/paper_prompt_default.md。

前后衔接

  • 前置:无(拿到题面就能用)。
  • 后续:problem-doc-model-selector(更细的逐问解析)或回到 paper-workflow-orchestrator 继续论文 workflow。

约束(必须遵守)

  • Memory Interaction (必做):
    • 完成规划后,必须调用 context-memory-keeper,将“论文大纲结构”、“核心评分点”更新到 memoryskill.md。
  • 本技能必须输出“评分点 → 证据 → 论文位置”的映射清单;后续产文时必须能逐条落到具体章节/图表/表格,否则视为未对齐。
  • 若输出中要求“数据预处理/可视化证据”,后续必须调用 data-cleaning-and-visualization 产出 paper_output/figures/,否则该评分点缺证据。
  • 若用户目标是“论文生产完整”,本技能结束后必须明确下一步:进入数据/图表阶段,或回到 paper-workflow-orchestrator 继续完整 workflow。

© yushui2022, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts, references) in packages/trae/.trae/skills/modeling-paper-rubric-and-model-selector of yushui2022/MathModel-Skill.

  • SKILL.md
  • references/paper_prompt_default.md
  • scripts/build_model_route.py

Open the folder on GitHubat commit 7712876

Used in 1 other repository

We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in yushui2022/MathModel-Skill, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Modeling Paper Rubric and Model Selector next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Modeling Paper Rubric and Model Selector compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Modeling Paper Rubric and Model Selector this skillyushui2022/MathModel-Skill4541 repos~1.8kAutomated safety check: PassMIT
Thesis CreatorStars-OC/thesis-creator230—~2.8kAutomated safety check: PassMIT
Aigc Detectorfree-revalution/AIGC-Detector-Pro142—~2.8kAutomated safety check: PassMIT
Lecture to Homeworkvect-G/lecture-to-hw127—~729Automated safety check: PassMIT
Synthesizeagentii-ai/agentii-investment-intelligence207—~3.2kAutomated safety check: PassApache-2.0
Latex Thesis Zhbrycewang-stanford/Auto-Empirical-Research-Skills4.6k—~1.5kAutomated safety check: PassCustom licence

Similar skills

  • Thesis Creator

    Stars-OC/thesis-creator

    Walks Chinese undergraduates through writing a graduation thesis from topic to Word export, with text-similarity reduction and AI-text rate rewriting and checks.

    230 GitHub stars~2.8k tokensUpdated 4 mo ago
    EducationAuto-check passed
  • Aigc Detector

    free-revalution/AIGC-Detector-Pro

    Academic paper AI content detection, rewriting, and thesis writing assistant.

    142 GitHub stars~2.8k tokensUpdated 4 mo ago
    EducationAuto-check passed
  • Lecture to Homework

    vect-G/lecture-to-hw

    Turns course slides, homework files, class code and earlier solutions into concise student-style Markdown answers, with optional subagents for solving and review.

    127 GitHub stars~729 tokensUpdated 5 mo ago
    EducationAuto-check passed
  • Synthesize

    agentii-ai/agentii-investment-intelligence

    Thesis report synthesis — turn a thesis's markdown artifacts into its letter-size thesis-report.html, then OPTIMIZE it against real page renders.

    207 GitHub stars~3.2k tokensUpdated 12 days ago
    EducationAuto-check passed
  • Latex Thesis Zh

    brycewang-stanford/Auto-Empirical-Research-Skills

    Chinese LaTeX thesis assistant for existing .tex degree thesis projects (XeLaTeX/LuaLaTeX/latexmk).

    4.6k GitHub stars~1.5k tokensUpdated 6 days ago
    Documents & OfficeAuto-check passed
  • Autonomous Research

    federicodeponte/opendraft

    An 18-agent pipeline that turns one topic line into a drafted research paper, literature review, or thesis chapter.

    507 GitHub stars~8.2k tokensUpdated 9 days ago
    Research & ScienceAuto-check passed

More from yushui2022/MathModel-Skill

All 10 skills in this repo
  • Modeling Code and Result Contracts

    yushui2022/MathModel-Skill

    Generates result-evidence contracts, tables and runnable q1 to q3 modeling code scaffolds for a math modeling paper from a model route, a data plan and cleaned data.

    454 GitHub stars~1.4k tokensUpdated 4 days ago
    Auto-check passed
  • Formal Modeling Paper Writer

    yushui2022/MathModel-Skill

    Plans, drafts, audits, formats and verifies a formal mathematical-modeling paper from an evidence chain, delivering audited Markdown and a Word file with native equations.

    454 GitHub stars~1.6k tokensUpdated 4 days ago
    Auto-check passed
  • Paper Micro-Unit Generator

    yushui2022/MathModel-Skill

    Repairs one failing section of a mathematical modeling paper from the repair queue, or builds a legacy or quickstart scaffold when you ask for one by name.

    454 GitHub stars~1.1k tokensUpdated 4 days ago
    Auto-check passed
  • Authoritative Data Harvester

    yushui2022/MathModel-Skill

    Finds authoritative public data sources for modeling tasks, prefers official APIs and bulk downloads, and outputs a reproducible fetch and cleaning plan with citations.

    454 GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed
  • Context Memory Keeper

    yushui2022/MathModel-Skill

    Maintains a two-layer persistent memory for a math-modeling paper workflow: long-term rules plus a short-term workbench, with finished tasks archived.

    454 GitHub starsUsed in 1 repo~893 tokens
    Auto-check passed
  • Math Modeling Data Cleaning and Charts

    yushui2022/MathModel-Skill

    Cleans raw or scraped competition data and produces exploratory charts and a figure plan as one stage of a mathematical modeling paper workflow.

    454 GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed

Works with

Questions about Modeling Paper Rubric and Model Selector

What does Modeling Paper Rubric and Model Selector do?

Builds a scoring-aligned outline for a mathematical modeling paper and a model selection plan with baseline, improvement and validation experiments. This skill, documented in Chinese, helps with mathematical modeling contest papers. From the problem statement it builds a paper outline tailored to each question, a table linking every scoring point to where the paper gives evidence, and a model selection plan with a baseline, improvements, validation and interpretation experiments.

When should I use Modeling Paper Rubric and Model Selector?

Modeling Paper Rubric and Model Selector fits situations like: structuring a modeling paper to match a scoring rubric; choosing between candidate models for each sub-question; planning baseline and comparison experiments; worrying that the chosen model or metrics do not fit the question.

How do I install Modeling Paper Rubric and Model Selector in Claude Code?

Run `npx skills add yushui2022/MathModel-Skill --skill modeling-paper-rubric-and-model-selector -a claude-code`. Or copy the skill folder (packages/trae/.trae/skills/modeling-paper-rubric-and-model-selector in yushui2022/MathModel-Skill) into .claude/skills/modeling-paper-rubric-and-model-selector in your project. Claude Code loads it when a task matches its description.

How do I install Modeling Paper Rubric and Model Selector in Codex?

Run `npx skills add yushui2022/MathModel-Skill --skill modeling-paper-rubric-and-model-selector -a codex`. Or copy the skill folder (packages/trae/.trae/skills/modeling-paper-rubric-and-model-selector in yushui2022/MathModel-Skill) into .agents/skills/modeling-paper-rubric-and-model-selector in your project. Codex loads it when a task matches its description.

Can I use Modeling Paper Rubric and Model Selector in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add yushui2022/MathModel-Skill --skill modeling-paper-rubric-and-model-selector -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/modeling-paper-rubric-and-model-selector, .gemini/skills/modeling-paper-rubric-and-model-selector, .github/skills/modeling-paper-rubric-and-model-selector and .opencode/skills/modeling-paper-rubric-and-model-selector in your project.

What does Modeling Paper Rubric and Model Selector need to run?

Going by SKILL.md and its folder, Modeling Paper Rubric and Model Selector needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python, to run the workflow guard and model route scripts; The upstream problem_analysis.json from the problem analysis step.

Does Modeling Paper Rubric and Model Selector access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Modeling Paper Rubric and Model Selector safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Modeling Paper Rubric and Model Selector use?

Modeling Paper Rubric and Model Selector is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Modeling Paper Rubric and Model Selector use?

About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.

What are the alternatives to Modeling Paper Rubric and Model Selector?

Skills that share tags, products or a category with Modeling Paper Rubric and Model Selector: Thesis Creator (Stars-OC/thesis-creator, 230 stars), Aigc Detector (free-revalution/AIGC-Detector-Pro, 142 stars), Lecture to Homework (vect-G/lecture-to-hw, 127 stars) and Synthesize (agentii-ai/agentii-investment-intelligence, 207 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Modeling Paper Rubric and Model Selector?

yushui2022 (a GitHub user) maintains it in yushui2022/MathModel-Skill, which has 454 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 7, 2026.

Source: yushui2022/MathModel-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.