从 arXiv ID/link、公开直接 PDF URL 或本地论文 PDF 提取架构图、方法图和实验图，保存到 Obsidian images 目录并生成索引。Use when the user asks to extract figures or another research skill needs embeddable images.
深度分析 arXiv 论文、公开 PDF URL、本地 PDF、研究项目页、技术博客或普通网页，自动识别来源类型并生成带证据与图片的 Obsidian 笔记。Use when the user provides an arXiv ID/link、public PDF URL、company research page、blog URL、local PDF or existing note and asks for analysis, summary, evaluation, or knowledge-base…
通过 DBLP 与 Semantic Scholar 搜索 CVPR、ICCV、ECCV、ICLR、AAAI、NeurIPS、ICML 等顶会论文，评分后生成 Obsidian 年度推荐笔记。Use when the user asks for a conference/year paper list, top-conference recommendations, or papers filtered by venue.
在本地 Obsidian Vault 的论文笔记中按标题、作者、关键词、标签、领域或 arXiv ID 搜索并排序结果。Use when the user asks to find, filter, or revisit papers already captured in local notes; do not use for downloading new papers.
生成每日 arXiv 与 Semantic Scholar 论文推荐并写入 Obsidian Vault。Use when the user asks to start the day, create today's paper brief, or generate recommendations for a specified date.