Math Discovery logo

Math Discovery

CommunityPopular
tradecatlabs
math-discovery

数学问题发现与证据检索。用于界定研究问题、查定义/定理谱系、检索 arXiv/Scholar/OpenAlex/Crossref、建立来源账本、证据图、查新或从证据缺口生成可证伪猜想。

Overview

Publishertradecatlabs
Repositoryvibe-coding-cn
Skill namemath-discovery
Stars
17.4K
Forks
1.8K
Bundled files
5
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.

  • 5 bundled files

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

  • Open source

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

Installation

Install the Math Discovery 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/tradecatlabs/vibe-coding-cn/tree/develop/research/vibe-mathing-cn-public/.codex/skills/math-discovery
  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/tradecatlabs/vibe-coding-cn.git /tmp/vibe-coding-cn
mkdir -p .claude/skills
cp -r /tmp/vibe-coding-cn/research/vibe-mathing-cn-public/.codex/skills/math-discovery .claude/skills/math-discovery
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Math Discovery 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 Discovery 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 Discovery 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.

Math Discovery

把模糊兴趣变成可界定、可检索、可证伪的数学问题,并产出来源可追溯的证据图。

Position in the Method Map

本 skill 负责方法地图第一层的“规格与语义”前置:在选择 Lean、SMT、model checking 或 abstract interpretation 之前,先冻结对象、定义域、量词、来源和可接受结论。对应的机器边界是 ProblemContract;地图总览见 FORMAL-METHODS-MAP.md。

When to Use This Skill

  • 需要查询某个定义、定理、证明技术或问题的前人工作。
  • 需要从本地 admitted/candidate 问题语料发现研究方向,并判断来源成熟度或准入缺口。
  • 需要建立关键词、别名、MSC/领域分类和检索式。
  • 需要判断“是否已有类似结果”,或从冲突/空白形成候选猜想。
  • 需要阅读论文并区分作者原始主张、证明依赖和当前综合判断。

Not For / Boundaries

  • “没搜到”不等于“从未有人研究”。
  • 搜索摘要不能替代读取定理陈述与证明正文。
  • 不把博客、搜索摘要或模型总结当作原始证据。
  • 不在没有证明/计算证据时把候选猜想提升为结果。
  • CandidateObservation 是来源发现材料,research_eligible=false;不得直接创建 Attempt,也不得把来源的 answered/resolved/solved 当作数学 Result。
  • 默认只查询 admitted;只有用户明确需要扩展发现面时才使用 --collection candidates|all,并在输出中保留 collection、来源和许可边界。

Quick Reference

text
1. 固定对象、领域、问题和非目标。
2. 先查 `query_problem_library.py --collection admitted`;需要扩面时再显式查 candidates。
3. 建立术语:正式名、别名、旧名、符号、MSC、相邻领域术语。
4. 冻结检索式、来源、日期、语言和停止条件。
5. 优先原始论文、正式出版物、arXiv 原文和官方数据库记录。
6. 为每个来源记录稳定 ID、URL/DOI/arXiv ID、版本、raw locator 和证据位置。
7. 将关系标为 supports / contradicts / limits / extends / unknown;候选身份匹配只进入 review queue。
8. 输出已知事实、冲突、空白、候选猜想和下一步取证。

默认 provider 顺序:项目资源/MCP → SearXNG arxiv,semantic scholar,openalex,crossref →通用 Web。429/CAPTCHA 时记录失败并切换 provider;不无限重试。

Examples

Example 1:定理谱系

  • 输入:“找 Szemerédi 正则性引理的主要变体。”
  • 动作:冻结术语与范围,检索原论文和后续正式变体,构建依赖图。
  • 验收:每项结论带稳定来源和定理位置;未读全文项标记未核验。

Example 2:序列查新

  • 输入:一组整数项和生成规则。
  • 动作:先确认规则与索引,再用 OEIS/论文检索,区分序列匹配与定理匹配。
  • 验收:不会因 OEIS 命中直接声称生成机制相同。

Example 3:候选问题库选题

  • 输入:“从新增问题库里找适合图论计算的开放问题。”
  • 动作:显式查询 candidates,保留 source status、许可和 admission 状态;只生成待审 shortlist,不启动计算。
  • 验收:每项均标为 research_eligible=false,唯一下一步是来源/陈述准入或 ProblemContract 冻结。

References

  • references/source-map.md:研究方法与检索供应链映射。
  • references/pressure-tests.md:查新与摘要误用压力场景。

Maintenance

  • Sources:rw-research-skill、wentor-research-plugins、kdense-scientific-skills。
  • Last updated:2026-08-13。
  • Verification:供应链检查 + 搜索 provider smoke;外部数据库状态每次使用时重新核验。

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 Discovery AI skill do?

数学问题发现与证据检索。用于界定研究问题、查定义/定理谱系、检索 arXiv/Scholar/OpenAlex/Crossref、建立来源账本、证据图、查新或从证据缺口生成可证伪猜想。

Why use Math Discovery on TypingMind?

Because you install it once and use it with any model. Math Discovery 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 Discovery in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tradecatlabs/vibe-coding-cn/tree/develop/research/vibe-mathing-cn-public/.codex/skills/math-discovery. 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 Discovery?

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 Discovery?

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

Is the Math Discovery AI skill free?

Yes. It is published on GitHub by tradecatlabs 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 👇