blog-notebooklm

Query Google NotebookLM notebooks for citation-backed answers from uploaded documents.

Updated Jul 10, 2026
One-click install
npx skills add https://github.com/captaindevv/SEO-ajaypipes --skill blog-notebooklm-captaindevv
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: blog-notebooklm
Source: https://github.com/captaindevv/SEO-ajaypipes/tree/main/skills/blog-notebooklm
Command: npx skills add https://github.com/captaindevv/SEO-ajaypipes --skill blog-notebooklm-captaindevv

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires patchright, python-dotenv, and includes scripts (resource) and references (resource) components.

What problem does it solve? Research for blog writing often relies on generic web search results that risk hallucination and lack verifiable sources. This Skill queries Google NotebookLM notebooks directly, returning answers grounded exclusively in your own uploaded documents with source citations, satisfying strict evidence requirements before statistics go public. ## Core Features & Use Cases - Source-Grounded Querying: Ask questions against NotebookLM notebooks via automated browser sessions and receive citation-backed answers from your primary documents. - Notebook Library Management: Add, search, activate, and remove notebooks with metadata (name, description, topics), plus smart discovery that queries a notebook to learn its content before cataloging. - Authentication & Cleanup: One-time interactive Google login with persistent browser state, status checks, re-authentication, and safe data cleanup that preserves the library. - Use Case: While writing a blog post, ask "What are the latest conversion rate benchmarks?" against your marketing research notebook, then use the returned source title as the inline citation and the notebook URL as the bibliography entry. ## Quick Start Run /blog notebooklm setup once to authenticate with Google, then ask a question with /blog notebooklm ask followed by your research question.

Frequently Asked Questions about blog-notebooklm

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I query a NotebookLM notebook from the command line?▼

Run python3 scripts/run.py ask_question.py --question "your question" after completing one-time Google authentication. The run.py wrapper creates the virtual environment, installs dependencies, and launches a headless browser session that returns the answer.

How do I set up Google authentication for NotebookLM automation?▼

Run python3 scripts/run.py auth_manager.py setup, which opens a visible browser for manual Google login. Authentication persists through a hybrid approach combining a persistent browser profile with cookie injection from state.json.

What are the limitations of automating NotebookLM queries?▼

Free Google accounts are limited to roughly 50 queries per day, resetting at midnight PST. Each question opens a new browser session with a few seconds of launch overhead, and documents must be uploaded manually through the NotebookLM web interface.

Why does the NotebookLM query fail with ModuleNotFoundError?▼

Calling scripts directly without the virtual environment causes missing dependency errors. Always invoke scripts through python3 scripts/run.py, which automatically creates the .venv, installs patchright and python-dotenv, and sets up Chrome.

Can NotebookLM queries be used inside other writing workflows?▼

Yes, blog-write and blog-researcher can invoke it internally with a question and notebook ID. If authentication is missing or the query fails, it returns silently with no error so the writing workflow continues with web search research.