BAIKEMARK

Use when 用户想根据论文、科研文档、研究文本、图注、开题/答辩材料或具备读图条件的参考图生成可复制的 AI 科研绘图提示词；触发场景包括论文配图、科研绘图、图形摘要、Graphical Abstract、机制图、技术路线图、实验装置图、模型架构图、多面板对比图、汇报总览图、参考图风格迁移、未知领域母版生成，或上传/引用 PDF、Word、LaTeX、Markdown、摘要、方法段、图注、课题说明、研究方案、参考图片。Also use when the user asks for scientific figure prompts, research illustration prompts, graphical abstract prompts, mechanism diagrams, technical roadmaps, experimental setup diagrams, model architecture diagrams, multi-panel scientific figures, paper/conference figures, or AI image prompts based on papers, research documents, abstracts, methods sections, figure captions, proposals, reference images, PDFs, Word docs, LaTeX files, Markdown files, or research plans.

Convert existing bitmap figures into editable SVG and PPTX. Use when Codex needs to rebuild, vectorize, editabilize, or redraw scientific figures, workflow diagrams, architecture diagrams, AI-generated diagrams, screenshots, or slide-like graphics while preserving dense raster regions such as logos, icons, photos, heatmaps, screenshots, and plots.

This skill should be used when the user asks to 'reroll buddy', 'change buddy', '刷宠物', '换宠物', 'reset buddy', 'reroll /buddy', '想要一只新的宠物', '看看有什么宠物', or mentions Claude Code buddy/companion customization. Helps users search for a specific buddy combination and apply it to their config.

处理 B 站（哔哩哔哩）视频字幕的完整工作流。能力包括：（1）引导用户扫码登录获取 Cookie；（2）自动获取视频字幕（优先 AI 字幕，自动回退 CC 字幕）；（3）生成视频内容摘要；（4）当用户询问"某内容在哪个时间段"时，从字幕文件中精准定位时间戳。当用户提供 B 站视频链接、BVID，或提到"b站字幕""帮我看视频""视频摘要""视频哪里讲到了""字幕提取"等任何与 B 站视频内容理解相关的场景时，务必使用此 skill。即使用户只是随口提到一个 bilibili 链接，也应该触发此 skill。