Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

NotebookLM Automation (notebooklm-py)

Full command-line control of Google NotebookLM — create notebooks, add sources, generate podcasts/videos/quizzes, and download everything.

AutomationIntermediate★ 18,582⑂ 2,501AI score 8/10Last updated: Aug 9, 2026

What it does

Gives Claude complete programmatic access to Google NotebookLM: create notebooks, add sources (URLs, YouTube, PDFs, audio, video, images), chat with citations, and generate every artifact type — audio overview (podcast), video, slide deck, infographic, report, mind map, data table, quiz, flashcards — then download them in multiple formats.

It also unlocks things the web UI can't do: slide decks as editable .pptx, quiz/flashcard export to JSON/Markdown/HTML, mind-map JSON extraction, CSV data tables, natural-language revision of individual slides, retrieval of a source's indexed fulltext, and saving chat answers as notebook notes. The doc covers profiles, CI/CD auth via env vars, headless/sandboxed setups, and rules for safe parallel-agent use.

Who it's for

  • Researchers and newsletter writers who repeatedly turn reading lists into summaries or podcasts
  • Educators generating quizzes and flashcards from course material at scale
  • Developers piping NotebookLM output into other tooling (python-pptx, visualization libraries)
  • Claude Code users automating research workflows end to end

Examples

  1. Link dump → podcast: create a notebook, source add each URL, wait until all sources are READY, generate audio "focus on the policy angle", then download audio ./podcast.m4a.
  2. Study pack: upload lecture PDFs, run generate quiz --difficulty hard and generate flashcards, then download quiz --format markdown for Notion/Obsidian.
  3. Vertical deck for mobile video: notebooklm generate slide-deck "exactly 8 pages, vertical 9:16 portrait layout" then download slide-deck ./slides.pptx --format pptx for further editing.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the SKILL.m folder from the GitHub repo teng-lin/notebooklm-py into my ~/.claude/skills/notebooklm/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

pip install "notebooklm-py[browser]" && notebooklm skill install

⚠ This is a third-party skill. Check the source repository before installing.

  1. Confirm Python is available (3.10+ recommended): python --version.
  2. Install the package: pip install "notebooklm-py[browser]" — the [browser] extra powers the interactive login flow.
  3. Register the skill with your agent: notebooklm skill install (or npx skills add teng-lin/notebooklm-py).
  4. Authenticate: notebooklm login — a browser opens; sign in with the Google account that has NotebookLM.
  5. Verify auth for real: notebooklm auth check --test --json and require both "status": "ok" and checks.token_fetch: true.
  6. Run notebooklm list to see your notebooks. Then just ask Claude: "/notebooklm" or "make a podcast from these links".
  7. (Optional) For headless servers or CI: log in on a machine with a display, copy the resulting storage_state.json over, and run notebooklm --storage /path/to/storage_state.json list. Treat that file as a password — chmod 600 it and never commit it.
View source on GitHub ↗License: MIT