NotebookLM skill for Claude Code
NotebookLM Claude Code Skill
Lets Claude Code query your Google NotebookLM notebooks and get answers grounded only in your uploaded documents
- 7,791 ★ on the repository
- Last commit
- MIT
Broad access
Why this level
- Automates a browser logged into your Google account and stores the session
- Installs Chrome and Python dependencies
- The project is archived and receives no fixes
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/notebooklm-claude-code-skillDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- Automates a browser logged into your Google account and stores the session
- Installs Chrome and Python dependencies
- The project is archived and receives no fixes
This is third-party code. Review the repository files before installing.
What it does
Using Chrome browser automation, the skill opens NotebookLM, asks the selected notebook a question and returns a source-grounded answer inside Claude Code. It keeps a local library of notebooks with descriptions and topics and picks the right one for the task. Google login happens once and persists across sessions. On first use it creates an isolated Python environment and installs dependencies, including Chrome.
Who it is for. Developers who already keep documentation in NotebookLM and want to query it from Claude Code.
Good fit when
- Your project or library docs are already in NotebookLM
- You need answers strictly from sources without model guesses
- You want to stop copy-pasting between the browser and the editor
Not a fit when
- You need multi-turn conversations with preserved context
- You cannot share notebooks publicly by link
- You use the Claude web UI rather than local Claude Code
Example request
Ask my API docs notebook how pagination worksLimitations
Since September 2026 the repository is archived and unmaintained, and the skill may break when the service changes. Works only in local Claude Code. Each question is independent and cannot reference a previous answer. Notebooks must be shared by link, and the NotebookLM free tier has daily query limits.
How to disable. Delete the ~/.claude/skills/notebooklm folder. The Clear NotebookLM data command resets data while keeping the library.
FAQ
How does it differ from the MCP version?
The skill runs only in Claude Code and opens a fresh browser per question. The notebooklm-mcp server keeps persistent sessions and also works in Codex and Cursor.
Discussion
No questions or reviews yet.
Related
SkillsA set of three research skills: paper writing, academic Word and PowerPoint documents, scientific computing and figures
Learn from materials
learn-from-materials
A skill that turns books, PDFs, slides and documents into a traceable knowledge base and an interactive learning page with sources, maps and self-check
A skill that translates whole books in PDF, DOCX and EPUB into any language using parallel subagents
A Claude Code skill: describe a document in plain words and get a compiled LaTeX PDF. Templates, build scripts and OCR of PDFs and handwritten notes
A ready-to-fork Claude Code template for academic work: slides, papers and data analysis with multi-agent review and quality gates
Claude Code skills for the academic pipeline: research, paper drafting, peer review and citation checks
README in short
The skill connects Claude Code to Google NotebookLM so the agent answers from the user's uploaded documents and hallucinates less. The README compares this with feeding docs into context, web search and local RAG. Installation is a clone into ~/.claude/skills; the rest is set up on first use. It documents natural-language commands, the Python script architecture and limitations. The author archived the project in September 2026.
README badge
Original SKILL.md
--- name: notebooklm description: Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses. --- # NotebookLM Research Assistant Skill Interact with Google NotebookLM to query documentation with Gemini's source-grounded answers. Each question opens a fresh browser session, retrieves the answer exclusively from your uploaded documents, and closes. ## When to Use This Skill Trigger when user: - Mentions NotebookLM explicitly - Shares NotebookLM URL (`https://notebooklm.google.com/notebook/...`) - Asks to query their notebooks/documentation - Wants to add documentation to NotebookLM library - Uses phrases like "ask my NotebookLM", "check my docs", "query my notebook" ## ⚠️ CRITICAL: Add Command - Smart Discovery When user wants to add a notebook without providing details: **SMART ADD (Recommended)**: Query the notebook first to discover its content: ```bash # Step 1: Query the notebook about its content python scripts/run.py ask_question.py --question "What is the content of this notebook? What topics are covered? Provide a complete overview briefly and concisely" --notebook-url "[URL]" # Step 2: Use the discovered information to add it python scripts/run.py notebook_manager.py add --url "[URL]" --name "[Based on content]" --description "[Based on content]" --topics "[Based on content]" ``` **MANUAL ADD**: If user provides all details: - `--url` - The NotebookLM URL - `--name` - A descriptive name - `--description` - What the notebook contains (REQUIRED!) - `--topics` - Comma-separated topics (REQUIRED!) NEVER guess or use generic descriptions! If details missing, use Smart Add to discover them. ## Critical: Always Use run.py Wrapper **NEVER call scripts directly. ALWAYS use `python scripts/run.py [script]`:** ```bash # ✅ CORRECT - Always use run.py: python scripts/run.py auth_manager.py status python scripts/run.py notebook_manager.py list python scripts/run.py ask_question.py --question "..." # ❌ WRONG - Never call directly: python scripts/auth_manager.py status # Fails without venv! ``` The `run.py` wrapper automatically: 1. Creates `.venv` if needed 2. Installs all dependencies 3. Activates environment 4. Executes script properly ## Core Workflow