Math Proof logo

Math Proof

CommunityPopular
tradecatlabs
math-proof

严格自然语言数学证明。用于证明或审查 theorem/lemma/proposition、补齐证明草稿、构建证明义务与依赖图、寻找反例、检查量词/常数/边界情况,或判断命题是否必须削弱。

Overview

Publishertradecatlabs
Repositoryvibe-coding-cn
Skill namemath-proof
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 Proof 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-proof
  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-proof .claude/skills/math-proof
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Math Proof 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 Proof 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 Proof 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 Proof

产出可审计的证明包;命题不成立或条件不足时,优先反驳或修正,不制造漂亮假证明。

Position in the Method Map

本 skill 位于“演绎验证 / 定理证明”的 proof-engineering 阶段,前置是 FORMAL-METHODS-MAP.md 所定义的规格与语义边界。证明草稿、引理图和自然语言审查不会自动等同于 Lean kernel check;需要形式化时交给 math-formalization,需要有限反例或 SMT 路径时交给 math-computation。

When to Use This Skill

  • 用户要求证明、补全或检查一个数学命题。
  • 当前证明含“显然”“类似”“标准论证”等可能隐藏缺口的跳步。
  • 需要将大结论拆成引理、证明义务和依赖图。
  • 需要从边界值、退化情形或量词顺序寻找反例。

Not For / Boundaries

  • 候选库条目必须先形成精确用户请求或 active ProblemContract;来源状态、目录题面或 candidate formal file 不能触发研究证明或 Result 晋升。
  • 自然语言证明只能达到 proof-drafted 或经真实人工审查后的 human-reviewed。
  • kernel-checked 只由 math-formalization 的真实 proof assistant 成功证据产生。
  • 不静默强化假设、缩小定义域或改变结论量词。
  • 引用标准定理时必须说明名称、版本/来源和为何满足前提。
  • 证明义务图出现重复 ID、未知依赖、循环或未闭合节点时必须 fail-closed,不能 warning 后继续。
  • 子引理被反驳只否定当前证明路线;除非反例直接满足原命题的否定,不能把原命题标记 refuted。

Quick Reference

text
Claim:精确陈述与量词顺序。
Status:provable-as-stated / repaired / refuted / blocked。
Assumptions:显式、隐藏和最小必要条件。
Proof obligations:每个非平凡蕴含一个义务。
Dependency map:结论 -> 引理 -> 外部定理 -> 假设。
Graph gate:节点 ID 唯一、依赖存在、无环、所有终点可追溯到 Claim。
Attack pass:边界、退化、极端尺度、量词交换、等号条件。
Proof:编号步骤,每步绑定义务或已验证结果。
Open gaps:任何未闭合项都会阻止完成声明。
Route status:open / blocked / refuted / closed,与 Claim status 分开记录。

Examples

Example 1:命题为假

  • 输入:一个全称不等式。
  • 动作:先检查边界和小规模反例,再决定证明策略。
  • 验收:找到反例后停止写证明,输出最小反例和可能修正版。

Example 2:缺少紧致性

  • 输入:证明草稿在极值存在性处跳步。
  • 动作:隔离存在性义务,核查连续性、闭性和有界性。
  • 验收:条件不足时状态为 repaired/blocked,不写“显然存在”。

Example 3:完整证明草稿

  • 输入:陈述、假设与若干已知引理。
  • 动作:建立依赖图,逐项闭合证明义务并做反例攻击。
  • 验收:statement 与实际证明完全一致,仍标记 proof-drafted 而非 kernel-checked。

Example 4:路线引理为假

  • 输入:某条证明路线依赖一个可被反例推翻的辅助引理。
  • 动作:将该 route 标记 refuted,检查反例是否也反驳原 Claim,并保留其他独立路线。
  • 验收:没有原命题反例时,Claim 仍为 blocked/open,而不是 refuted。

References

  • references/source-map.md:证明、审稿、proof DAG 与批判性思考来源映射。
  • references/pressure-tests.md:错误命题、DAG 完整性、路线状态与隐藏缺口压力场景。

Maintenance

  • Sources:annals-of-mathematics-skills、kdense-scientific-skills、proofflow、leanprover-skills;上游图与 skill 只作方法/反例来源,不代表本项目已安装或验证。
  • Last updated:2026-08-26。
  • Verification:项目结构校验;数学正确性需要人工或 proof assistant 证据。

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 Proof AI skill do?

严格自然语言数学证明。用于证明或审查 theorem/lemma/proposition、补齐证明草稿、构建证明义务与依赖图、寻找反例、检查量词/常数/边界情况,或判断命题是否必须削弱。

Why use Math Proof on TypingMind?

Because you install it once and use it with any model. Math Proof 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 Proof 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-proof. 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 Proof?

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 Proof?

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

Is the Math Proof 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 👇