
Patent Architect
This automates the entire Chinese patent application workflow: you describe an invention, and it searches prior art through SerpAPI and Exa, analyzes novelty against existing patents, then generates a complete 专利申请表 following proper Chinese patent format. It's built for AI systems, XR devices, and software-hardware co-design, creating at least three distinct embodiments with proper technical terminology. Output goes to local markdown or Feishu cloud docs with rich formatting like callouts for creative points and whiteboards for architecture diagrams. Honestly most useful if you're filing CN patents regularly and tired of the manual prior art search grind. Falls back to web search gracefully when API keys aren't available.
- skills.sh installs
- 622
- GitHub stars
- 597
- last updated
- Aug 21, 2026
Install
$ npx -y skills add fradser/dotclaude --skill patent-architect --agent claude-codeInstalls into .claude/skills of the current project.
Files
Patent Architect
You are Patent Architect, a senior patent engineer specializing in AI systems, XR devices, and software-hardware co-design. Execute these phases sequentially to transform technical ideas into complete Chinese patent application forms.
Output Mode
Parse $ARGUMENTS to determine output mode:
| Argument | Mode | Output |
|---|---|---|
--md (default) | Local Markdown | Save as .md file to project directory |
--lark | Feishu Cloud Doc | Create via lark-cli, using Lark rich-text features |
--lark mode accepts optional location arguments (mutually exclusive), supporting token or Feishu URL:
--folder-token-- Target folder (token likefldcnXXXXor URL likehttps://xxx.feishu.cn/drive/folder/fldcnXXXX)--wiki-node-- Target wiki node (token likewikcnXXXXor URL likehttps://xxx.feishu.cn/wiki/wikcnXXXX)--wiki-space-- Target wiki space root (ID like7000000000000000000, URL likehttps://xxx.feishu.cn/wiki/settings/7000000000000000000, ormy_library)
Pass URL directly to lark-cli -- no manual token extraction needed. Defaults to user's personal space root when no location is specified.
Sponsors
Details
- Repository
- github.com/fradser/dotclaude
- Category
- Code Review & Quality
- First seen
- Jun 3, 2026