菜单
Use when the user has a patent publication number, patent URL, or patent-search result and wants the PDF fetched into the configured patent inbox.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when the user wants to install, configure, diagnose, or troubleshoot ScholarAIO, including setup check, dependency status, API keys, and bilingual setup flow.
Use when the user explicitly asks for Nature Skills, nature-skills, Nature style, Nature-style, Nature Communications, Nature-family, CNS, high-impact journal, or Springer Nature workflows, including Nature figure work, polishing, writing, reviewer critique, high-impact journal major revision response, Nature/CNS citations, Nature data-sharing workflows, paper readers, reviewer response, paper-to-PPT, submission checklist, or Nature-specific academic-search workflows.
Use when the user wants to rebuild or refresh ScholarAIO keyword, full-text, FTS5, FAISS, or semantic search indexes after data or metadata changes.
Use when the user wants to find academic papers, search the local library, run keyword or semantic search, search by author, explore topics, or federate across library, explore databases, and arXiv.
Use when the user wants to import papers from Endnote XML/RIS, Zotero Web API or local SQLite, attach PDFs, match PDFs to records, or supplement records with PDF content.
Use when the user wants to process new papers, patents, theses, documents, or proceedings from inbox queues into the knowledge base, run the ingest pipeline, or rebuild indexes.
| name | patent-fetch |
| description | Use when the user has a patent publication number, patent URL, or patent-search result and wants the PDF fetched into the configured patent inbox. |
优先通过 USPTO PPUBS 官方导出接口下载美国专利 PDF，并在必要时回退到 Google Patents 页面抓取，自动保存到 configured patent inbox（fresh 默认 data/spool/inbox-patent/），供后续 pipeline ingest 入库。旧版 data/inbox-patent/ 先用 scholaraio migrate upgrade --migration-id <id> --confirm 迁移。
常与 patent-search 配合使用：先用 patent-search 发现专利，再用 patent-fetch 或 --fetch 参数下载 PDF。
US20240176406A1），优先走 USPTO 官方导出scholaraio pipeline ingest 走专利入库流程scholaraio patent-fetch US20240176406A1
scholaraio patent-fetch "https://patents.google.com/patent/US20240176406A1"
# 方式一：搜索后根据提示手动下载
scholaraio patent-search "neural network" --count 5
# 输出中每条结果会显示：下载: scholaraio patent-fetch <公开号>
# 方式二：搜索时自动下载所有结果 PDF
scholaraio patent-search "neural network" --count 5 --fetch
已下载: /path/to/data/spool/inbox-patent/US20240176406A1.pdf (1679017 bytes)
已保存到: /path/to/data/spool/inbox-patent/US20240176406A1.pdf
如果文件已存在：
文件已存在: /path/to/data/spool/inbox-patent/US20240176406A1.pdf
已保存到: /path/to/data/spool/inbox-patent/US20240176406A1.pdf
如果页面没有 PDF 链接：
未在该页面找到 PDF 下载链接
# 1. 搜索专利
scholaraio patent-search "quantum computing" --count 10
# 2. 根据公开号下载目标专利 PDF
scholaraio patent-fetch US20230123456A1
# 3. 走正常专利入库流程（自动按公开号去重、标记 patent 类型）
scholaraio pipeline ingest
# 4. 本地检索
scholaraio search "voltage overshoot"
# 1. 搜索并自动下载前 5 条结果的 PDF
scholaraio patent-search "quantum computing" --count 5 --fetch
# 2. 直接入库
scholaraio pipeline ingest
页面请求超时或下载失败
未在该页面找到 PDF 下载链接
下载失败
data/spool/inbox-patent/）是否有写入权限scholaraio patent-search — USPTO 专利搜索（发现专利公开号，支持 --fetch 自动下载）scholaraio pipeline ingest — 将 inbox-patent 中的 PDF 入库scholaraio search / scholaraio vsearch — 本地知识库检索