notebooklm
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.
Author
Category
Development ToolsInstall
Download and extract to your skills directory
Copy command and send to OpenClaw for auto-install:
NotebookLM Skill - Query Your NotebookLM Notes in Claude Code
Skill Overview
The NotebookLM Skill lets you query your Google NotebookLM notes directly in Claude Code. Using Gemini, it provides high-quality, citation-backed answers based on your source documents, effectively reducing AI hallucinations.
Use Cases
When you need to search technical documentation, API docs, or development guides, upload the documents to NotebookLM. Then use this skill to get precise answers grounded in the document contents, with each answer including citation sources.
Upload research materials, study notes, or your company knowledge base to NotebookLM. Use this skill to retrieve documents and answer questions, ensuring responses come only from the trusted content you provided.
If you need to verify the accuracy of AI responses, this skill restricts answers to information from the source documents, helping avoid fabricated content that traditional AI might produce.
Core Features
Supports adding, searching, activating, and deleting NotebookLM notes. Set a name, description, and topic tags for each note to manage multiple document libraries conveniently.
Each query automatically opens a browser session, asks NotebookLM questions, and retrieves document-based answers. After completion, the browser closes automatically. Supports follow-up questions to get complete information.
After a one-time login, the authenticated state is kept, so you don’t have to manually log in to your Google account each time. Supports checking authentication status and re-authentication.
Frequently Asked Questions
How do I use the NotebookLM Skill in Claude Code?
First run python scripts/run.py auth_manager.py setup once to perform Google login authentication (the browser needs to be visible for manual login). Then use notebook_manager.py add to add your NotebookLM note links. After that, you can use ask_question.py to query your notes.
How can I add NotebookLM notes to the skill library?
Use the command python scripts/run.py notebook_manager.py add --url "note link" --name "name" --description "description" --topics "topics" to add notes. If you’re not sure what the note contains, you can first use the smart add method: query the note content with ask_question.py, then add it to the library based on the returned information.
What are the query limitations when using the NotebookLM Skill?
Free Google accounts have a limit of 50 queries per day. Each query opens a new browser session, so there will be a few seconds of browser startup time. The skill does not support session persistence; each question is an independent query.