Browser automation skill for controlling Google's NotebookLM. Use when the user wants anything done in NotebookLM (e.g., 'open NotebookLM', 'check my [name] notebook', 'ask my notebook about X', 'add [source] to NotebookLM', 'generate a Video Overview from my notebook', 'use NotebookLM Studio'). Handles reading and querying notebooks, adding sources (URLs, text, files, YouTube links, synthesized content), generating Studio outputs (Audio/Video Overviews, Mind Maps, Reports incl. Briefing Doc/Study Guide/FAQ, Flashcards, Quiz, slide decks, infographics — discover the exact set from the live Studio panel; the UI evolves fast), and creating new notebooks. Requires browser automation environment — fails gracefully when unavailable.
68
85%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
The canonical home for this skill is notebooklm in alirezarezvani/claude-skills
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The browser automation skill navigates to and interacts with NotebookLM, which can ingest arbitrary user-provided sources and web content, but requires the agent to actively search/fetch specific URLs or content supplied by the user/attacker rather than passively monitoring an unrequested external queue.
19392f7
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.