Patent Disclosure logo

Patent Disclosure

Community
fuyuxiang
patent-disclosure

生成专利技术交底书。当用户提到"专利"、"交底书"、"发明"、"技术方案"、"权利要求"时触发。通过多轮对话采集发明信息,生成符合规范的完整交底书文档和附图。

Overview

Publisherfuyuxiang
Repositorypatent-disclosure-skill
Skill namepatent-disclosure
Stars
84
Forks
10
Bundled files
14
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.

  • 14 bundled files

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

  • Open source

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

Installation

Install the Patent Disclosure 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/fuyuxiang/patent-disclosure-skill/tree/main
  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/fuyuxiang/patent-disclosure-skill.git \
  .claude/skills/patent-disclosure
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Patent Disclosure 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 Patent Disclosure 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 Patent Disclosure 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.

专利技术交底书生成

通过多轮自适应对话引导用户生成高质量的专利技术交底书。

触发条件

用户提到以下关键词时激活:

  • 专利、交底书、技术交底、发明专利
  • 写专利、生成交底书、专利申请

工作流程

Phase 0: 读取参考文件

根据后续识别的领域,读取对应参考文件:

  • 始终读取:references/patent-style-guide.md
  • 需要生成附图时:references/patent-diagram-style.md
  • 按领域读取:references/{domain}.md 和 references/examples/{domain}-example.md

Phase 1: 破冰与评估(1-2 轮)

目标: 判断对话策略和深度。

第一条消息询问:

"我来帮你生成专利技术交底书。先了解几个基本情况:

  1. 你的角色是?

    • A) 发明人/工程师(我来引导你梳理技术方案)
    • B) 专利代理人(我帮你加速撰写)
  2. 你现在有什么输入材料?

    • A) 口头描述(脑子里有想法,还没落纸)
    • B) 已有文档(技术文档、论文、PPT等)
    • C) 代码仓库(功能已实现,需要转化为交底书)
  3. 发明属于哪个技术领域?

    • A) 计算机/软件/互联网
    • B) 机械/制造
    • C) 电子/通信/半导体
    • D) 其他(请说明)"

自适应规则:

  • 发明人 + 口头描述 → 深度引导模式(15-20 轮)
  • 发明人 + 已有文档 → 确认补充模式(8-12 轮)
  • 代理人 → 快速模式(5-8 轮)
  • 有代码仓库 → 先读取代码结构,提取技术方案,再向用户确认

Phase 2: 核心信息采集(自适应 5-15 轮)

每轮只问一个问题,按优先级推进:

必采信息(按顺序):

  1. 发明名称 — "你的发明想叫什么名称?要求:反映主题和类型,不超过25字。例如:一种基于深度学习的图像去噪方法及系统"

  2. 技术问题 — "现有技术存在什么问题?你的发明要解决什么?尽量具体。"

  3. 技术方案概述 — "用一两段话概括你的解决方案。重点说:你用了什么技术手段来解决上面的问题?"

  4. 核心创新点 — "跟现有技术比,你的方案最关键的不同在哪里?(1-3 个点即可)"

  5. 系统组成或方法步骤 — 根据类型分别提问:

    • 系统类:"你的系统包含哪些模块/组件?它们之间怎么交互?"
    • 方法类:"实现目标功能的步骤是什么?请按顺序列出。"
  6. 有益效果 — "相比现有方案,你的发明带来了哪些好处?最好有量化数据。"

  7. 具体实施方式 — "能举一个实际的应用场景吗?在这个场景下,系统/方法是怎么一步步工作的?"

对话策略:

  • 用户回答精简 → 追问:"能展开说说{X}的具体实现方式吗?比如用了什么算法/结构/协议?"
  • 用户回答详尽 → 跳过可推导的问题,加快节奏
  • 用户提供了文档 → 从文档提取关键信息,向用户确认:"我从文档中理解到{X},这个对吗?"
  • 用户不确定 → 给出选项或示例辅助

Phase 3: 大纲确认(1 轮)

生成交底书大纲:

"基于我们的讨论,交底书大纲如下:

一、发明名称:{title} 二、技术领域:{field} 三、背景技术:{background_summary} 四、发明内容:

  • 技术问题:{problem}
  • 技术方案:{solution_summary}
  • 有益效果:{effects_summary} 五、附图说明:(预计生成 {N} 张图)
  • 图1:{diagram_1_desc}
  • 图2:{diagram_2_desc} 六、具体实施方式:{embodiment_summary}

这个结构可以吗?需要调整的地方请告诉我。"

Phase 4: 分章节生成

核心章节逐个生成确认:

生成顺序:技术问题 → 技术方案 → 有益效果 → 具体实施方式

每个核心章节生成后:

  • 展示完整内容
  • 请用户确认:"这部分内容准确吗?有需要修改的地方请指出。"
  • 用户确认后锁定,继续下一章节

写作要求(必须遵循):

  • 读取 references/patent-style-guide.md 中的规则
  • 使用该领域 references/{domain}.md 中的术语和句式
  • 参考 references/examples/{domain}-example.md 的风格
  • 禁止使用风格指南中"禁止用语清单"中的任何表达
  • 技术名词全文统一,首次出现时定义
  • 系统类方案按模块阐述功能和连接关系
  • 方法类方案按步骤阐述,标记为 S1、S2...

辅助章节批量生成:

核心章节全部确认后,一次性生成:

  • 技术领域(从发明名称和技术方案推导)
  • 背景技术(从技术问题反向构建)
  • 附图说明(根据已生成附图填写)

展示后请用户统一审阅。

Phase 5: 附图生成

在"发明内容-技术方案"确认后触发:

  1. 分析技术方案,识别需要的图表类型:

    • 有模块/组件描述 → 生成系统架构图
    • 有步骤描述 → 生成方法流程图
    • 有数据流转描述 → 生成数据流图
  2. 从技术方案提取节点和边的数据,构造 JSON:

json
{
  "title": "图1 系统架构示意图",
  "nodes": [{"id": "101", "label": "数据采集模块"}],
  "edges": [{"from": "101", "to": "102", "label": "原始数据"}]
}
  1. 调用生成脚本:
bash
python3 scripts/generate-patent-diagram.py <type> diagrams/figure-<N>.svg '<json>'
  1. 读取 references/patent-diagram-style.md 确保符合规范

  2. 无法自动生成的图,提醒用户: "以下附图需要你手动准备:

    • {图类型}:{原因} 请提供后我可以帮你编写对应的附图说明。"

Phase 6: 组装输出

  1. 按章节顺序组装完整 Markdown 文件
  2. 一级标题使用中文数字:"一、发明名称"、"二、技术领域"...
  3. 附图引用格式:"如图1所示,所述{组件}(101)..."
  4. 保存到 output/patent-disclosure-{title}.md
  5. 附图保存到 output/diagrams/

告知用户: "交底书已生成,文件保存在:

  • 正文:output/patent-disclosure-{title}.md
  • 附图:output/diagrams/figure-*.svg

需要导出为 Word 文档吗?(会按 A4、宋体小四、1.5倍行距格式排版)"

如果用户需要 docx:

bash
python3 scripts/export-docx.py output/patent-disclosure-{title}.md

质量检查清单

生成完成后自动执行:

  • 技术问题和有益效果一一对应
  • 附图标记在正文和附图中一致
  • 无风格指南禁止用语
  • 技术名词全文统一
  • 系统类方案所有模块都有功能描述
  • 方法类方案步骤可实施(本领域技术人员能复现)
  • 无空洞总结或评价性段落

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 Patent Disclosure AI skill do?

生成专利技术交底书。当用户提到"专利"、"交底书"、"发明"、"技术方案"、"权利要求"时触发。通过多轮对话采集发明信息,生成符合规范的完整交底书文档和附图。

Why use Patent Disclosure on TypingMind?

Because you install it once and use it with any model. Patent Disclosure 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 Patent Disclosure in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/fuyuxiang/patent-disclosure-skill/tree/main. 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 Patent Disclosure?

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 Patent Disclosure?

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

Is the Patent Disclosure AI skill free?

It is published on GitHub by fuyuxiang. Check the repository for licensing terms. 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 👇