#417417th of 455 in Skills, plugins and prompts
qiaomu-anything-to-notebooklm
Claude Code skill that turns URLs and files into NotebookLM podcasts, slides and mind maps
- Stars
- 6.5k
- License
- MIT
- Last commit
- Apr 2026
- Last release
- Jan 2026
- Language
- Python
1,384 on 22 Apr 20266,500 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A Claude Code skill that fetches content from WeChat articles, X/Twitter, YouTube, podcasts, web pages, PDFs, EPUBs and Office files, uploads it to Google NotebookLM, and downloads generated output such as audio, slides, mind maps, quizzes and reports. Paywalled pages are fetched through a six-level fallback chain (proxies, bot user agents, archive.today, Google Cache). A deep-analysis mode asks NotebookLM 12 staged questions and writes structured JSON.
Who it is for: Claude Code users wanting NotebookLM audio, slides or analysis from any source
Strengths
- Handles 15+ input types, including WeChat, EPUB, scanned PDF OCR, audio and ZIP archives
- Six-level paywall fallback chain for 300+ listed news sites
- Deep-analysis mode runs 12 staged questions in one NotebookLM session and outputs JSON
- install.sh and check_env.py (13 checks) set up dependencies
Weaknesses
- Depends on Google NotebookLM and a notebooklm-py login; generation is not local
- Podcast transcription for Xiaoyuzhou, Ximalaya and Bilibili needs a Get笔记 API key
- Paywall bypass is unreliable on hard paywalls and archive.today may need manual CAPTCHA
- README restricts use to personal study; paywall bypass raises terms-of-service issues
What it needs
- no GPU
- Needs Google NotebookLM, notebooklm-py, Python 3.9+, Playwright (Chromium), markitdown, Get笔记 API (optional)
- Models: Google NotebookLM
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Skills, plugins and prompts
See all 455| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |