China Patent Skill
中国专利 Skill 架构：扫描、挖点、查新、成文与知识图谱
拆解专利交底与通俗解读两条管线，以及来源、图稿、Word 和 Obsidian 的边界。
What you will learn
- Distinguish discovery, research, and drafting stages
- Produce a traceable disclosure draft
- Identify confidentiality and evidence boundaries
Before you start
- Basic Git and command-line usage
- Comfort reading a project README
You can explain the project, run its documented first step, and decide what to verify before adopting it.
Key takeaways
- 交底和解读共享证据但输出不同。
- 图稿计划是可复现接口。
- 人工复核是架构层而非末尾备注。
两条主线
交底主线是材料扫描→类型 Schema→专利点→查新→图稿计划→Markdown/Word；解读主线是 PDF/全文抽取→权要树→术语和附图→Canvas/Obsidian。
Use the pinned source evidence, record versions and assumptions, and ask a qualified reviewer to validate the result before adopting it.
证据契约
每个技术特征应能回到材料、说明书或附图；公开线索必须标注为语境而非权要证据。图稿用 figure_plan.yaml 固定顺序，避免临场挑图。
人机协作
Agent 负责结构化草稿、链接和自检，研发人员确认事实，代理师确认法律表达；审查答复和政策雷达默认只产出草稿。
Use the pinned source evidence, record versions and assumptions, and ask a qualified reviewer to validate the result before adopting it.
Decision guide
| Criterion | Option A | Option B |
|---|---|---|
| Best when | You need predictable behavior and easy auditing | You need adaptive optimization and have reliable telemetry |
| Main risk | May leave performance on the table | Can become difficult to explain or debug |
Implementation steps
- 1
绘制输入、处理、证据和输出边界。
- 2
追踪一个特征到来源与图稿。
- 3
验证 Word/Canvas 投影的一致性。
- 4
注入缺失材料和网络失败。
Copy-ready example
materials -> scan/schema -> points/prior art
-> figure_plan -> Markdown/Word
patent PDF -> claims/terms/figures -> Obsidian graphFrequently asked questions
公开专利摘要能代替原文吗？
不能；摘要和线索必须回链到原始公告与权利要求。
为什么要分发明、实用和外观模板？
三类专利的技术特征、图稿和法律要求不同，分模板能减少结构性遗漏。
Sources
- Patent Disclosure Skill README (captured 2026-08-31)Source checked 2026-08-31
- patent-disclosure-skill repositorySource checked 2026-08-31