Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This skill connects Claude Code to Google NotebookLM so that every query returns answers drawn exclusively from your uploaded documents. It handles browser automation, library management, and persistent authentication, letting researchers, knowledge teams, and AI agent users ask natural-language questions and receive citation-backed responses without leaving the agent workflow.
WHO IT'S FOR
Research Scientists
query personal document libraries for grounded answers
Knowledge Management Teams
manage and query organizational documentation libraries
AI-Assisted Research Users
ask follow-up questions to synthesize comprehensive answers
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Retrieve three specifications from an uploaded manual
Uses notebooklm
A local Claude Code installation with the notebooklm skill installed
One-time Google authentication completed when prompted in the visible browser window
A NotebookLM notebook containing the workshop manual
Replace `[NotebookLM URL or active notebook name]` with the notebook's shared URL or its configured library name
Use the notebooklm skill to check my uploaded workshop-manual notebook for the specified brake-fluid type, engine-oil specification, and rear-axle torque. Return a concise, source-grounded answer with citations. Notebook: [NotebookLM URL or active notebook name].
Claude
Codex
Cursor
Gemini CLI