Multi-source content processor that automatically uploads articles, videos, PDFs, and more to NotebookLM, generating podcasts, slides, mind maps, and other formats.
Works with
Supports 11 content sources including WeChat articles, web pages, YouTube videos, Office documents (Word/PowerPoint/Excel), PDFs, EPUBs, Markdown, images with OCR, audio files with transcription, structured data (CSV/JSON/XML), ZIP archives, and web search results
Automatically converts all file types to text using markitdow
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionanything-to-notebooklmExecute the skills CLI command in your project's root directory to begin installation:
Fetches anything-to-notebooklm from joeseesun/anything-to-notebooklm and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate anything-to-notebooklm. Access via /anything-to-notebooklm in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
0
total installs
0
this week
665
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
665
stars
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。
通过 MCP 服务器自动抓取微信公众号文章内容（绕过反爬虫）
支持任何公开可访问的网页（新闻、博客、文档等）
自动提取 YouTube 视频的字幕和元数据
直接输入或粘贴的文本内容
通过 Web Search 搜索关键词，汇总多个来源的信息
MCP 服务器已安装在：~/.claude/skills/anything-to-notebooklm/wexin-read-mcp/
配置 MCP（需要手动添加到 Claude 配置文件）：
macOS: 编辑 ~/.claude/config.json
{
"primaryApiKey": "any",
"mcpServers": {
"weixin-reader": {
"command": "python",
"args": [
"/Users/joe/.claude/skills/anything-to-notebooklm/wexin-read-mcp/src/server.py"
]
}
}
}
配置后需要重启 Claude Code。
首次使用前必须认证：
notebooklm login
notebooklm list # 验证认证成功
/anything-to-notebooklm [微信文章链接]| 用户说的话 | 识别意图 | NotebookLM 命令 |
|---|---|---|
| "生成播客" / "做成音频" / "转成语音" | audio | generate audio |
| "做成PPT" / "生成幻灯片" / "做个演示" | slide-deck | generate slide-deck |
| "画个思维导图" / "生成脑图" / "做个导图" | mind-map | generate mind-map |
| "生成Quiz" / "出题" / "做个测验" | quiz | generate quiz |
| "做个视频" / "生成视频" | video | generate video |
| "生成报告" / "写个总结" / "整理成文档" | report | generate report |
| "做个信息图" / "可视化" | infographic | generate infographic |
| "生成数据表" / "做个表格" | data-table | generate data-table |
| "做成闪卡" / "生成记忆卡片" | flashcards | generate flashcards |
如果没有明确指令，默认只上传不生成任何内容，等待用户后续指令。
Claude 自动识别输入类型：
| 输入特征 | 识别为 | 处理方式 |
|---|---|---|
https://mp.weixin.qq.com/s/ |
微信公众号 | MCP 工具抓取 |
https://youtube.com/... 或 https://youtu.be/... |
YouTube | 直接传递给 NotebookLM |
https:// 或 http:// |
网页 | 直接传递给 NotebookLM |
/path/to/file.pdf |
PDF 文件 | markitdown 转 Markdown → TXT |
/path/to/file.epub |
EPUB 电子书 | markitdown 转 Markdown → TXT |
/path/to/file.docx |
Word 文档 | markitdown 转 Markdown → TXT |
/path/to/file.pptx |
PowerPoint | markitdown 转 Markdown → TXT |
/path/to/file.xlsx |
Excel | markitdown 转 Markdown → TXT |
/path/to/file.md |
Markdown | 直接上传 |
/path/to/image.jpg |
图片（OCR） | markitdown OCR → TXT |
/path/to/audio.mp3 |
音频 | markitdown 转录 → TXT |
/path/to/file.zip |
ZIP 压缩包 | 解压 → markitdown 批量转换 |
| 关键词（无URL，无路径） | 搜索查询 | WebSearch → 汇总 → TXT |
微信公众号：
read_weixin_article/tmp/weixin_{title}_{timestamp}.txt网页/YouTube：
notebooklm source add [URL]Office 文档/电子书/PDF：
markitdown /path/to/file.docx -o /tmp/converted.md/tmp/{filename}_converted_{timestamp}.txt本地 Markdown：
notebooklm source add /path/to/file.md图片（OCR）：
音频文件：
ZIP 压缩包：
搜索关键词：
/tmp/search_{keyword}_{timestamp}.txt调用 notebooklm skill：
notebooklm create "{title}" # 创建新笔记本
notebooklm source add /tmp/weixin_xxx.txt --wait # 上传文件并等待处理完成
等待处理完成很重要，否则后续生成会失败。
如果用户指定了处理意图，自动调用对应命令：
| 意图 | 命令 | 等待 | 下载 |
|---|---|---|---|
| audio | notebooklm generate audio |
artifact wait |
download audio ./output.mp3 |
| slide-deck | notebooklm generate slide-deck |
artifact wait |
download slide-deck ./output.pdf |
| mind-map | notebooklm generate mind-map |
artifact wait |
download mind-map ./map.json |
| quiz | notebooklm generate quiz |
artifact wait |
download quiz ./quiz.md --format markdown |
| video | notebooklm generate video |
artifact wait |
download video ./output.mp4 |
| report | notebooklm generate report |
artifact wait |
download report ./report.md |
| infographic | notebooklm generate infographic |
artifact wait |
download infographic ./infographic.png |
| flashcards | notebooklm generate flashcards |
artifact wait |
download flashcards ./cards.md --format markdown |
生成流程：
artifact wait <task_id>）用户输入：
把这篇文章生成播客 https://mp.weixin.qq.com/s/abc123xyz
执行流程：
generate audio）输出：
✅ 微信文章已转换为播客！
📄 文章：深度学习的未来趋势
👤 作者：张三
📅 发布：2026-01-20
🎙️ 播客已生成：
📁 文件：/tmp/weixin_深度学习的未来趋势_podcast.mp3
⏱️ 时长：约 8 分钟
📊 大小：12.3 MB
用户输入：
这个视频帮我画个思维导图 https://www.youtube.com/watch?v=abc123
执行流程：
generate mind-map）输出：
✅ YouTube 视频已转换为思维导图！
🎬 视频：Understanding Quantum Computing
⏱️ 时长：23 分钟
🗺️ 思维导图已生成：
📁 文件：/tmp/youtube_quantum_computing_mindmap.json
📊 节点数：45 个
用户输入：
搜索 'AI发展趋势 2026' 并生成报告
执行流程：
generate report）输出：
✅ 搜索结果已生成报告！
🔍 关键词：AI发展趋势 2026
📊 来源：5 篇文章
📄 报告已生成：
📁 文件：/tmp/search_AI发展趋势2026_report.md
📝 章节：7 个
📊 大小：15.2 KB
用户输入：
把这篇文章、这个视频和这个PDF一起做成PPT：
- https://example.com/article
- https://youtube.com/watch?v=xyz
- /Users/joe/Documents/research.pdf
执行流程：
输出：
✅ 多源内容已整合为PPT！
📚 内容源：
1. 网页文章：AI in 2026
2. YouTube：Future of AI
3. PDF：Research Notes (12 页)
📊 PPT 已生成：
📁 文件：/tmp/multi_source_slides.pdf
📄 页数：25 页
📦 大小：3.8 MB
用户输入：
把这本电子书做成播客 /Users/joe/Books/sapiens.epub
执行流程：
输出：
✅ EPUB 电子书已转换为播客！
📚 电子书：Sapiens: A Brief History of Humankind
📄 页数：约 450 页
📊 字数：约 15 万字
🎙️ 播客已生成：
📁 文件：/tmp/sapiens_podcast.mp3
⏱️ 时长：约 45 分钟（精华版）
📊 大小：48.2 MB
用户输入：
这个Markdown生成Quiz /Users/joe/notes/machine_learning.md
执行流程：
generate quiz）输出：
✅ Markdown 已转换为Quiz！
📄 文件：machine_learning.md
📊 大小：8.5 KB
📝 Quiz 已生成：
📁 文件：/tmp/machine_learning_quiz.md
❓ 题目：15 道（10选择 + 5简答）
❌ 错误：URL 格式不正确
必须是微信公众号文章链接：
https://mp.weixin.qq.com/s/xxx
你提供的链接：https://example.com
❌ 错误：无法获取文章内容
可能原因：
1. 文章已被删除
2. 文章需要登录查看（暂不支持）
3. 网络连接问题
4. 微信反爬虫拦截（请稍后重试）
建议：
- 检查链接是否正确
- 等待 2-3 秒后重试
- 或手动复制文章内容
❌ 错误：NotebookLM 认证失败
请运行以下命令重新登录：
notebooklm login
然后验证：
notebooklm list
❌ 错误：播客生成失败
可能原因：
1. 文章内容太短（< 100 字）
2. 文章内容太长（> 50万字）
3. NotebookLM 服务异常
建议：
- 检查文章长度是否适中
- 稍后重试
- 或尝试其他格式（如生成报告）
用户可以一次性指定多个处理任务：
这篇文章帮我生成播客和PPT https://mp.weixin.qq.com/s/abc123
Skill 会依次执行：
默认每篇文章创建新 Notebook，也可以指定已有 Notebook：
把这篇文章加到我的【AI研究】笔记本 https://mp.weixin.qq.com/s/abc123
Skill 会：
为生成任务添加具体要求：
这篇文章生成播客，要求：轻松幽默的风格，时长控制在5分钟
Skill 会将要求作为 instructions 传给 NotebookLM。
频率限制：
内容长度：
版权遵守：
生成时间：
文件清理：
/tmp/，系统重启后自动清理/tmp/notebooklm - NotebookLM 核心功能notebooklm-deep-analyzer - 深度分析 NotebookLM 内容markitdown - 转换其他格式文档⚠️ 第一次使用前必须配置
编辑 ~/.claude/config.json：
{
"primaryApiKey": "any",
"mcpServers": {
"weixin-reader": {
"command": "python",
"args": [
"/Users/joe/.claude/skills/anything-to-notebooklm/wexin-read-mcp/src/server.py"
]
}
}
}
配置后重启 Claude Code！
# 测试 MCP 服务器
python ~/.claude/skills/anything-to-notebooklm/wexin-read-mcp/src/server.py
# 如果报错，检查依赖
cd ~/.claude/skills/anything-to-notebooklm/wexin-read-mcp
pip install -r requirements.txt
playwright install chromium
# 检查认证状态
notebooklm status
# 重新登录
notebooklm login
# 验证
notebooklm list
# 确保临时目录可写
chmod 755 /tmp
# 测试写入
touch /tmp/test.txt && rm /tmp/test.txt
# 检查任务状态
notebooklm artifact list
# 如果显示 "pending" 超过 10 分钟，取消重试
# （目前 CLI 不支持取消，需要在网页端操作）
我想学习这篇文章，帮我生成播客，上下班路上听
链接：https://mp.weixin.qq.com/s/abc123
→ 生成 8 分钟播客，通勤时间听完
✓Make data-driven prioritization decisions faster
Stakeholder Communication
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
✓Save 3-5 hours/week on communication overhead
Implementation Guide
Prerequisites
- ›Claude Desktop or compatible AI client
- ›Access to product documentation and roadmap tools (Jira, Notion, etc.)
- ›Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
- ›Stakeholder contact information and communication channels
Time Estimate
30-60 minutes to see productivity improvements
Steps
- 1Install product management skill
- 2Start with user story generation for known feature
- 3Progress to competitive analysis: research 2-3 competitors
- 4Use for roadmap prioritization: apply RICE/ICE scoring
- 5Draft stakeholder communications and refine based on feedback
- 6Build template library for recurring PM tasks
- 7Share effective prompts with product team
Common Pitfalls
- ⚠Not validating competitive research—verify facts before sharing
- ⚠Accepting user stories without involving engineering team
- ⚠Over-relying on frameworks without qualitative judgment
- ⚠Not customizing outputs to company culture and communication style
- ⚠Skipping stakeholder validation of generated requirements
Best Practices
✓ Do
- +Validate research and competitive analysis with real data
- +Collaborate with engineering when generating technical requirements
- +Customize frameworks and templates to your company context
- +Use skill for first drafts, refine with stakeholder input
- +Document successful prompt patterns for PM tasks
- +Combine AI efficiency with human judgment and intuition
✗ Don't
- −Don't publish competitive analysis without fact-checking
- −Don't finalize user stories without engineering review
- −Don't make prioritization decisions solely on AI scoring
- −Don't skip customer validation of generated requirements
- −Don't ignore company-specific context and culture
💡 Pro Tips
- ★Provide context: company goals, constraints, customer feedback
- ★Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
- ★Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
- ★Use skill for 70% generation + 30% customization to company needs
When to Use This
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
Learning Path
- 1Basic: user stories, feature specs, status updates
- 2Intermediate: competitive analysis, prioritization frameworks, PRDs
- 3Advanced: product strategy, go-to-market planning, OKR setting
- 4Expert: product vision, market positioning, business model innovation
Related Skills
grill-me
702mattpocock/skills
Productivitysame categorypremortem
217parcadei/continuous-claude-v3
Productivitysame categorydeslop
163cursor/plugins
Productivitysame categorytravel-planner
142ailabs-393/ai-labs-claude-skills
Productivitysame categorynutritional-specialist
140ailabs-393/ai-labs-claude-skills
Productivitysame categoryframer-motion
138pproenca/dot-skills
Productivitysame categoryReviews
4.6★★★★★34 reviews- AAisha Patel★★★★★Dec 16, 2024
Solid pick for teams standardizing on skills: anything-to-notebooklm is focused, and the summary matches what you get after install.
- AAlexander Harris★★★★★Dec 12, 2024
anything-to-notebooklm reduced setup friction for our internal harness; good balance of opinion and flexibility.
- CChen Brown★★★★★Dec 8, 2024
I recommend anything-to-notebooklm for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
- CChen Thompson★★★★★Nov 27, 2024
Useful defaults in anything-to-notebooklm — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
- RRahul Santra★★★★★Nov 23, 2024
Solid pick for teams standardizing on skills: anything-to-notebooklm is focused, and the summary matches what you get after install.
- LLi Shah★★★★★Nov 3, 2024
anything-to-notebooklm has been reliable in day-to-day use. Documentation quality is above average for community skills.
- AAditi Menon★★★★★Oct 22, 2024
anything-to-notebooklm fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
- CChen Gupta★★★★★Oct 18, 2024
Registry listing for anything-to-notebooklm matched our evaluation — installs cleanly and behaves as described in the markdown.
- PPratham Ware★★★★★Oct 14, 2024
anything-to-notebooklm is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
- LLuis Gill★★★★★Sep 25, 2024
anything-to-notebooklm reduced setup friction for our internal harness; good balance of opinion and flexibility.
showing 1-10 of 34
1 / 4Discussion
Comments — not star reviews- No comments yet — start the thread.