Math Table logo

Math Table

Community
capwitf
math-table

Use when 高教社杯/CUMCM 数学建模论文需要格式化、修复、压缩或审查符号表、记号表、结果表,包括单位清理、longtable、列宽平衡或按截图修排版。

Overview

Publishercapwitf
RepositoryMy-MathModeling-skills
Skill namemath-table
Stars
57
Forks
1
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by capwitf on GitHub. Read the source before you install it.

Installation

Install the Math Table AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/capwitf/My-MathModeling-skills/tree/main/math-table
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/capwitf/My-MathModeling-skills.git /tmp/My-MathModeling-skills
mkdir -p .claude/skills
cp -r /tmp/My-MathModeling-skills/math-table .claude/skills/math-table
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Math Table in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Math Table on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Math Table is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

符号表与结果表

用途

Format notation tables without changing mathematical meaning.

核心规则:先保护符号和定义。排版修改不能悄悄重命名变量、改变定义域或修改单位。

国一候选门槛:表格必须让题目贴合、建模洞察、证据可信、可复现、边界清楚变得更可核验;这是提交质量门槛,不承诺获奖。符号、单位、来源和场景标签不清楚时,排版再紧凑也不能进入论文就绪状态。

硬门禁:单位是模型的一部分,不是装饰。单位未知或冲突时,符号表不能进入论文就绪状态。

流程

  1. Read the current notation source and the first-use locations when available.
  2. Preserve the symbol list unless the user explicitly asks to add/remove rows.
  3. Normalize columns to: symbol, meaning, unit, and optionally domain/source.
  4. Use longtable when the table may cross pages.
  5. Use booktabs rules and avoid vertical lines.
  6. Put -- only for dimensionless or truly not-applicable units.
  7. Mark unknown, conflicting, or unstated units as blockers or pending confirmation; do not hide them with --.
  8. Wrap only long cells; do not shrink the whole table until unreadable.
  9. Compile or run the smallest available LaTeX check after editing.

一致性检查

  • Every formula symbol used in the body appears in the table or is locally defined.
  • Every table symbol has one meaning and one unit across the paper.
  • Indices, sets, parameters, variables, slack variables, and binary variables are distinguishable.
  • Units match the result tables and axis labels.
  • No stale symbols from old problems remain.

表格清单门禁

When auditing result tables as part of a paper pass, report table_count by subquestion and distinguish:

  • required result tables that answer a deliverable;
  • notation or parameter tables that make the model readable;
  • diagnostic or appendix tables that should not crowd the main body;
  • tables missing key data, units, scenario labels, baselines, source rows, or validation status.

Do not add tables just to show effort. If a result is exact, central, and short, prefer a table; if the table repeats a figure without adding exact values, remove, merge, or demote it. A main-body table is blocked when its units, source, or target subquestion are unknown.

红线

Stop and report a blocker when:

  • a symbol appears with two meanings or two units;
  • an engineering quantity has -- as a unit without being dimensionless;
  • a formula symbol is missing from both local definition and symbol table;
  • notation was changed to fit layout rather than preserving math;
  • stale symbols from another problem remain in the table.

推荐模式

tex
\begin{longtable}{p{0.18\linewidth} p{0.62\linewidth} p{0.12\linewidth}}
\caption{Core notation}\label{tab:symbols}\\
\toprule
Symbol & Meaning & Unit \\
\midrule
\endfirsthead
\toprule
Symbol & Meaning & Unit \\
\midrule
\endhead
$t$ & Time-step index & -- \\
$\Delta t$ & Time-step length & h \\
\bottomrule
\end{longtable}

输出规则

  • Keep edits minimal and reversible.
  • Preserve mathematical notation exactly unless asked otherwise.
  • Prefer compact spacing and balanced columns over decorative styling.
  • Do not insert \newpage or \clearpage solely to place the symbol table.
  • For paper table audits, include table_count, required tables missing, appendix candidates, and unit/source blockers.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Math Table AI skill do?

Use when 高教社杯/CUMCM 数学建模论文需要格式化、修复、压缩或审查符号表、记号表、结果表,包括单位清理、longtable、列宽平衡或按截图修排版。

Why use Math Table on TypingMind?

Because you install it once and use it with any model. Math Table is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Math Table in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/capwitf/My-MathModeling-skills/tree/main/math-table. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Math Table?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Math Table?

As many as you like. As long as a model supports skills, you can use Math Table with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Math Table AI skill free?

Yes. It is published on GitHub by capwitf under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇