Cn Patent Drafter logo

Cn Patent Drafter

Community
handsomeZR-netizen
cn-patent-drafter

起草、修订或合规自检中国发明专利(CNIPA 发明专利)申请文件——请求书、说明书摘要、权利要求书、说明书、说明书附图。当用户提及"发明专利""权利要求""说明书""CNIPA""[0001]""分案""答复审查意见",或要求修改 patent-tex 项目下任意 .tex 文件时触发。仅处理 CN 发明专利申请材料;软件著作权 / 实用新型 / 外观设计不在范围内。

Overview

PublisherhandsomeZR-netizen
Repositorycn-patent-drafter
Skill namecn-patent-drafter
Stars
64
Forks
8
Bundled files
6
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.

  • 6 bundled files

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

  • Open source

    Published by handsomeZR-netizen on GitHub. Read the source before you install it.

Installation

Install the Cn Patent Drafter 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/handsomeZR-netizen/cn-patent-drafter/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/handsomeZR-netizen/cn-patent-drafter.git \
  .claude/skills/cn-patent-drafter
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cn Patent Drafter 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 Cn Patent Drafter 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 Cn Patent Drafter 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.

CN 发明专利起草助手

本 Skill 帮助起草符合 CNIPA 2025–2026 现行规范的中国发明专利申请文件。Skill 内置:

  • 4 套 LaTeX 模板(请求书 / 摘要 / 权利要求书骨架 / 说明书六小节段号阶梯)
  • 1 套 10 大类 CNIPA 2026 合规清单
  • 1 套结构化工作流,把"读清单 → 援引代码事实 → 套模板 → 写前自检 → 出 PDF"串起来

工作流

任何专利章节起草/修订任务都按以下顺序执行:

  1. 加载合规清单 — 读本 Skill 目录下的 checklists/cnipa-2026.md,把每条要求加载到工作记忆里。
  2. 定位目标章节 — 用户的请求映射到下列文件之一(约定项目里 LaTeX 源放在 docs/patent-tex/sections/):
    • 请求书:docs/patent-tex/sections/01-request.tex
    • 摘要 + 摘要附图:docs/patent-tex/sections/02-abstract.tex
    • 权利要求书:docs/patent-tex/sections/03-claims.tex
    • 说明书:docs/patent-tex/sections/04-specification.tex
    • 说明书附图:docs/patent-tex/sections/05-drawings.tex 先 Read 该文件再决定改动范围。如果项目里还没有这些文件,按本 Skill 目录下的 templates/ 与下方"项目脚手架"小节自建。
  3. 援引代码事实 — 任何对算法、数据结构、阈值、参数的描述都要直接对应实际源码。Grep 用户项目里的实现文件,把函数名、变量名、常量取值原样写入"具体实施方式"小节,最大化"充分公开"防绕设计。如果项目尚无实现,提示用户先实现再写专利。
  4. 使用模板 — 生成新内容时优先以下骨架(位于本 Skill 目录下的 templates/),按需替换 __PLACEHOLDER__:
    • templates/claim-skeleton.tex — 独立权 + 从权 + 系统权骨架
    • templates/spec-section-headers.tex — 说明书六小节 + 段号 [0001] 阶梯
    • templates/abstract-skeleton.tex — 摘要 ≤ 300 字范本
    • templates/request-form.tex — 请求书表格
  5. 写前自检 — 把草稿对照 checklists/cnipa-2026.md 逐条核验,特别关注:
    • 五文档顺序:请求书 → 摘要 → 权利要求书 → 说明书 → 附图
    • 说明书段号 [0001] 全文连续,不按小节重置
    • 摘要 ≤ 300 汉字、摘要附图最多 1 张
    • 权利要求逐条阿拉伯数字编号,禁用"如权利要求……所述"循环引用
    • 不出现商标、第三方品牌、竞品截图、源码 URL
    • AI 不得列发明人;起草中如使用 AI 辅助应限于排版/润色,技术构思与参数由发明人独立完成
  6. 写入并提示编译 — 用 Write/Edit 落盘后,告知用户用 xelatex/latexmk -xelatex 重新出 PDF;若用户尚未填发明人/申请人等字段,提示在项目根的本地配置(如 docs/soft-copyright.local.json 或自定义路径)填 inventionTitle / inventor / applicant / filingDate 四项。

项目脚手架(首次使用时建议结构)

your-project/
├── docs/
│   └── patent-tex/
│       ├── main.tex                  # 用 ctexart + fontset=windows + xelatex 编译
│       ├── local-config.tex          # \renewcommand 覆盖默认占位宏(gitignore)
│       └── sections/
│           ├── 01-request.tex
│           ├── 02-abstract.tex
│           ├── 03-claims.tex
│           ├── 04-specification.tex
│           └── 05-drawings.tex
└── .claude/
    └── skills/
        └── cn-patent-drafter/        # 本 Skill clone 到这里

main.tex 主壳推荐 preamble:

latex
\documentclass[UTF8,fontset=windows,zihao=-4]{ctexart}
\usepackage[a4paper,left=22mm,right=22mm,top=24mm,bottom=22mm]{geometry}
\usepackage{graphicx,array,booktabs,longtable,tabularx,enumitem,fancyhdr}
\usepackage{hyperref,caption,float,setspace,xcolor,amsmath,amssymb}
\setstretch{1.45}\setlength{\parindent}{2em}

\newcommand{\paragraphno}[1]{\noindent[\textbf{#1}]\hspace{0.5em}\ignorespaces}
\newenvironment{claimitem}{\begin{enumerate}[label=\arabic*., leftmargin=2em, itemsep=0.4em]}{\end{enumerate}}
\newcommand{\zonecode}[1]{\texttt{#1}}
\newcommand{\redblank}[1]{{\color{red}\underline{\hspace{#1}}}}

完整 working 示例见 examples/sample-output.pdf,对应原仓库参考实现: handsomeZR-netizen/eldercare-monitor 智慧养老监护系统 的 docs/patent-tex/。

常见任务速查

  • 「补一条从权」→ 读 03-claims.tex,按现有 \item 节奏在 \begin{claimitem}…\end{claimitem} 内追加;从权必须明确"根据权利要求 N 所述"且 N 严格小于本条号
  • 「扩写 [0033] 段」→ 读 04-specification.tex,找到对应段号;若需新增段号,把后续所有段号顺次 +1(先 Grep 再 Edit 全替换确保一致)
  • 「换发明名称」→ 改本地配置(如 docs/soft-copyright.local.json 的 inventionTitle);不要直接改 main.tex(其只承担默认值)
  • 「画新附图」→ 把图文件放到 docs/diagrams/ 或 docs/screenshots/,再编辑 05-drawings.tex 增加 \begin{figure} 块,并在 04-specification.tex 的「附图说明」段追加一行 \paragraphno{...} 图 N 是…
  • 「合规自检」→ 直接对照 checklists/cnipa-2026.md 逐条核验当前 PDF;不通过项要在响应中明确列出

输出风格

  • 中文为主、术语规范:"实施方式"不写"实现方式";"特征在于"不写"特点是";"包括以下步骤"不写"包含如下步骤"
  • 段落首行缩进由 LaTeX \setlength{\parindent}{2em} 自动处理,正文不要手动空格缩进
  • 列号用 (1) (2) (3)(半角括号 + 阿拉伯数字),见现有 03-claims.tex 内 enumerate label=(\\arabic*) 用法
  • 不使用模糊词:"大约""等等""诸如此类"——必须给出确定范围或穷举集合

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 Cn Patent Drafter AI skill do?

起草、修订或合规自检中国发明专利(CNIPA 发明专利)申请文件——请求书、说明书摘要、权利要求书、说明书、说明书附图。当用户提及"发明专利""权利要求""说明书""CNIPA""[0001]""分案""答复审查意见",或要求修改 patent-tex 项目下任意 .tex 文件时触发。仅处理 CN 发明专利申请材料;软件著作权 / 实用新型 / 外观设计不在范围内。

Why use Cn Patent Drafter on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/handsomeZR-netizen/cn-patent-drafter/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 Cn Patent Drafter?

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 Cn Patent Drafter?

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

Is the Cn Patent Drafter AI skill free?

Yes. It is published on GitHub by handsomeZR-netizen 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 👇