菜单
Use when the user wants LLM-based metadata enrichment, table-of-contents extraction, L3 conclusion extraction, or abstract backfilling for library papers.
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 | enrich |
| description | Use when the user wants LLM-based metadata enrichment, table-of-contents extraction, L3 conclusion extraction, or abstract backfilling for library papers. |
通过 LLM 提取论文的目录结构（TOC）或结论段（L3），丰富论文元数据。
注意：
import-endnote/import-zotero导入时默认自动执行 toc + l3 + abstract backfill。以下命令用于选择性富化（如重新提取、补充特定论文、或处理全库）。引用量补查：使用
/citationsskill 中的scholaraio refetch命令。
解析用户意图：
enrich-tocenrich-l3backfill-abstract（从 .md 提取 + LLM 校验）确定处理范围：
--all--force 覆盖已有结果批量模式说明：
--all会按config.llm.concurrency做多篇并发处理- 并发只发生在“论文之间”，单篇内部提取逻辑不拆分并发
- 批量模式会对单篇失败自动做指数退避重试
提取目录：
scholaraio enrich-toc [<paper-id> | --all] [--force] [--inspect]
提取结论：
scholaraio enrich-l3 [<paper-id> | --all] [--force] [--inspect] [--max-retries N]
补全摘要：
scholaraio backfill-abstract [--dry-run] [--doi-fetch]
参数说明：
--inspect — 展示提取过程详情（调试用）--max-retries N — L3 单篇提取最大重试次数（默认 2）；--all 时也作为每篇论文的批量重试预算--doi-fetch — 从出版商网页抓取官方 abstract（覆盖现有，需联网）enrich-toc 现在会显示开始提取、是否成功、以及提取出的 TOC 节数用户说："帮我提取所有论文的结论"
→ 执行 enrich-l3 --all
用户说："重新提取 Smith-2023-Survey 的目录"
→ 执行 enrich-toc "Smith-2023-Survey" --force
用户说："帮我看看这篇论文 TOC 提取成功没有"
→ 执行 enrich-toc "<paper-id>" --force，并根据终端输出确认 TOC 提取完成: N 节
用户说："补全摘要"
→ 执行 backfill-abstract，然后提示 embed --rebuild
用户说："补查引用量"
→ 转交 /citations skill（使用 refetch 命令）