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.
Why this rating
Deterministic checks triggered by the tool capabilities and evidence.
- Locality: Hybrid
Uses browser automation against `notebooklm.google.com` and requires an interactive Google login during setup.
- Data access: Sensitive
Queries answers grounded in the user's uploaded NotebookLM documents and stores auth/session data (cookies/state) locally.
- Action surface: Execute
Runs local scripts (`run.py` wrapper) that manage auth, add/remove notebooks from a library, and perform automated browser interactions.
Best practices
Follow these steps to reduce risk when using this skill.
- Use a dedicated Google account for automation and enable MFA; avoid logging into high-value accounts in automated browser sessions.
- Keep `~/.claude/skills/notebooklm/data/` private and never commit `library.json` or `browser_state/`; clear auth on shared machines.
- Be cautious with `cleanup_manager.py --confirm` and notebook `remove`; back up important notebook metadata before destructive cleanup.
Evidence links
Public sources backing the indicator assignments.
Always be careful when navigating away from the website.
Max-risk rule
If any capability reaches a higher level, the entire indicator level bumps up to keep ratings deterministic and easy to scan.