What problem does it solve? Searching local documentation with an AI assistant consumes large token budgets, misses context across files, and often produces hallucinated APIs. This Skill lets Claude Code ask questions directly against Google NotebookLM notebooks, which answer exclusively from your uploaded documents with citations. ## Core Features & Use Cases - Source-Grounded Q&A: Sends questions to NotebookLM through Patchright browser automation and returns Gemini answers grounded only in your uploaded documents. - Notebook Library Management: Add, list, search, activate, and remove NotebookLM notebooks with names, descriptions, and topic tags stored locally. - Persistent Google Authentication: One-time manual Google login with a hybrid browser profile plus cookie-injection approach that keeps sessions valid across runs. - Use Case: Upload your framework documentation to a NotebookLM notebook, then ask Claude Code to build a feature; it queries the notebook, follows up on gaps, and writes code based on the real docs instead of guessed APIs. ## Quick Start Set up NotebookLM authentication, add my notebook link to the library, and ask it what topics the documentation covers.
