← Back to Skills Marketplace
8143
Downloads
15
Stars
60
Active Installs
1
Versions
Install in OpenClaw
/install notebooklm-skill
Description
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.
Usage Guidance
Install only if you are comfortable letting local scripts automate a logged-in Google NotebookLM browser. Prefer a dedicated Google account, avoid sensitive notebooks or public 'anyone with link' sharing, protect or regularly clear the skill data directory, and set limits before allowing automatic follow-up queries.
Capability Analysis
Type: OpenClaw Skill
Name: notebooklm-skill
Version: 0.1.0
The skill is classified as suspicious due to its extensive use of high-risk capabilities, even though the stated intent appears functional. Key indicators include: 1) Browser automation with anti-detection features (e.g., `StealthUtils`, `BROWSER_ARGS` in `scripts/browser_utils.py` and `scripts/config.py`), which, while explained as necessary for reliable interaction with Google, are commonly associated with malicious bots. 2) Local storage of sensitive Google authentication session tokens (`state.json`) in `~/.claude/skills/notebooklm/data/browser_state/` as confirmed by `scripts/auth_manager.py` and `AUTHENTICATION.md`. 3) Significant use of prompt injection against the AI agent in `SKILL.md` and `scripts/ask_question.py` (e.g., 'CRITICAL: Add Command - Smart Discovery', 'EXTREMELY IMPORTANT: Is that ALL you need to know?'), instructing the agent to perform specific actions and decision-making, which is a high-risk technique even if used for benign purposes here. 4) The skill installs a full browser (Google Chrome) via `patchright install chrome` as seen in `scripts/setup_environment.py` and `requirements.txt`, and uses `subprocess.run` for various system commands, granting it powerful execution capabilities.
Capability Assessment
Purpose & Capability
Querying NotebookLM, managing a local notebook library, and using browser automation are coherent with the stated purpose, but anti-detection flags, human-like interaction helpers, account switching for limits, and public link-sharing guidance broaden the risk beyond ordinary document querying.
Instruction Scope
The skill tells the agent to keep asking follow-up questions until it decides the answer is complete and to query notebooks for discovery, which is purpose-aligned but can repeatedly use the authenticated Google session without clear per-query user control.
Install Mechanism
First use can create a virtual environment, install pinned Python packages, upgrade pip, and install a Patchright Chrome/Chromium browser. This is disclosed in docs, but it is automatic and lacks lockfile/hash verification or a separate consent step.
Credentials
The local Claude Code requirement and network/browser access are expected, but the skill also reuses a logged-in Google browser context, supports proxy/environment configuration, and recommends weaker or alternate-account workflows in troubleshooting guidance.
Persistence & Privilege
Authentication cookies, localStorage, auth metadata, and a persistent browser profile are stored under the skill data directory and reloaded later; documentation acknowledges this but also contradicts itself by saying there is no session persistence and does not sufficiently warn that state.json is sensitive session material.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install notebooklm-skill - After installation, invoke the skill by name or use
/notebooklm-skill - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
notebooklm-skill v0.1.0
- Initial release introducing integration with Google NotebookLM for source-grounded, citation-backed research queries.
- Provides persistent authentication, browser automation, and robust notebook/document management via a Python script interface.
- Features Smart Discovery for notebook metadata, minimizing the need for manual data entry.
- Strongly enforces use of a wrapper script (run.py) for consistent environment setup and dependency management.
- Includes critical follow-up and synthesis workflow for comprehensive, accurate responses.
- Stores all data locally with security in mind; configuration options via `.env` supported.
Metadata
Frequently Asked Questions
What is 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. It is an AI Agent Skill for Claude Code / OpenClaw, with 8143 downloads so far.
How do I install Notebooklm?
Run "/install notebooklm-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Notebooklm free?
Yes, Notebooklm is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Notebooklm support?
Notebooklm is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Notebooklm?
It is built and maintained by guccidgi (@guccidgi); the current version is v0.1.0.
More Skills