anything-to-notebooklm
多源内容 → NotebookLM 智能处理器
自动从多种来源获取内容，上传到 NotebookLM，并根据自然语言指令生成播客、PPT、思维导图等多种格式。
支持的内容源
1. 微信公众号文章
通过 MCP 服务器自动抓取微信公众号文章内容（绕过反爬虫）
2. 任意网页链接
支持任何公开可访问的网页（新闻、博客、文档等）
3. YouTube 视频
自动提取 YouTube 视频的字幕和元数据
4. Office 文档
- Word (DOCX) - 保留表格和格式
- PowerPoint (PPTX) - 提取幻灯片和备注
- Excel (XLSX) - 表格数据
More from erafat/skills
md-to-xhs-cards
Convert a Markdown file into Xiaohongshu (Little Red Book) image cards with deterministic layout, preserving markdown structure order and embedded local images. Use when users ask for direct MD-to-XHS card conversion, markdown poster cards, 图文卡片拆分, or preserving original markdown text/format in social image outputs.
17gmail-invoice-processor
Process invoice PDFs from Gmail inbox and create Excel summaries. Use this skill when the user wants to: (1) Download PDF invoices from Gmail, (2) Extract vendor names and amounts from invoice PDFs, (3) Create or update Excel spreadsheets summarizing invoice data, (4) Search for invoices in Gmail by subject line (containing 'invoice' or 'invoices'), (5) Automate invoice tracking or expense reporting from email. Trigger when user mentions Gmail invoices, PDF invoices in email, expense tracking from Gmail, or creating invoice summaries in Excel.
7cite-them-all
Academic reference agent that identifies claims needing citations, searches PubMed/bioRxiv/medRxiv via MCP tools, and adds properly formatted references to Markdown manuscripts
6academic-lectures
>
3baoyu-post-to-x
Posts content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown). Uses real Chrome with CDP to bypass anti-automation. Use when user asks to "post to X", "tweet", "publish to Twitter", or "share on X".
2baoyu-image-gen
AI image generation with OpenAI and Google APIs. Supports text-to-image, reference images, aspect ratios, and parallel generation (recommended 4 concurrent subagents). Use when user asks to generate, create, or draw images.
2