notebooklm_skill

Overview

This skill lets you query and manage Google NotebookLM notebooks through automated browser interactions with persistent profile authentication. It supports registering notebooks, syncing and deduplicating sources, running single or batch queries, multi-notebook comparisons, and structured exports to JSON or Markdown. Designed for reproducible workflows, it writes machine-friendly JSON to stdout and exits nonzero on error.

How this skill works

The skill uses Playwright-driven headless Chrome with persistent profiles to authenticate and interact with NotebookLM web UI. Scripts run from the skill directory, accept command-line flags for all operations, and emit JSON output. Key features include hash-based dedupe for source uploads, dry-run and retry controls, batch/multi-query modes, and export options (JSON/Markdown) with artifact capture on failures.

When to use it

• You want to ask questions of a specific NotebookLM notebook or run multiple questions in batch.
• You need to register, list, or describe NotebookLM notebooks programmatically.
• You need to add, sync, or dedupe local folders and files into a NotebookLM notebook.
• You want to compare answers across multiple notebooks or run bulk audits/exports.
• You require reproducible, scriptable exports of notes and answers for downstream processing.

Best practices

• Create a named persistent profile with auth_manager.py setup and reuse it for all scripts.
• Run destructive or bulk operations with --dry-run first to preview changes before applying them.
• Use --retries N to handle transient browser flakiness and capture screenshots/HTML on failures.
• Store large or frequently-updated sources in a consistent directory layout to maximize hash-based dedupe.
• Use batch questions (q1||q2||q3) and compare-notebook-ids for efficient multi-query workflows.

Example use cases

• Onboard a new NotebookLM notebook with notebook_manager.py add, then bulk-add a docs folder via remote_manager.py add-source.
• Run nightly sync with remote_manager.py sync-sources --recursive --delete-missing --dry-run to validate changes before commit.
• Ask a notebook a series of research questions in batch and export answers to Markdown for inclusion in a report.
• Compare responses from two notebooks on the same question set using --compare-notebook-ids to audit knowledge drift.
• Perform large export of notes and metadata to JSON for archival or downstream analysis.