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 automates source-grounded research by integrating with Google NotebookLM. It allows users to build notebooks from URLs, text, or local files and perform cited source analysis through fast or deep web research.
Content creators can use these capabilities to bridge the gap between synthesis and publishing, converting research into articles, social drafts, reports, or study guides.
WHO IT'S FOR
Content creators
automate research-to-content pipelines for articles
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.
Follow the documented setup, then try a first task.
Source install for Claude Code
Installs: Complete notebooklm-skill installation, including the notebooklm-research skill at Claude Code user scope · Claude Code
Before you start
Python 3.10 or newer
A Google account with access to NotebookLM
In a terminal, clone the repository, enter its directory, and run the isolated installer. The installer installs Chromium and installs or updates the Claude Code skill automatically; forced skill updates create a timestamped backup of a changed target.
git clone https://github.com/claude-world/notebooklm-skill.git
cd notebooklm-skill
./install.sh
If necessary, add the linked command directory to PATH. By default it is ~/.local/bin, and XDG_BIN_HOME can override it.
In a terminal, authenticate the installed package and verify the NotebookLM session.
Installs: Complete notebooklm-skill installation with the notebooklm-research skill at Claude Code user scope (~/.claude/skills/notebooklm-research/SKILL.md) · Claude Code
Before you start
Python 3.10 or newer
A Google account with access to NotebookLM
In a terminal, create and activate a virtual environment, install notebooklm-skill from PyPI, and install Chromium for browser login. Keep this virtual environment active for the following terminal steps.
In the same terminal environment, authenticate and verify the NotebookLM session.
notebooklm-auth setup
notebooklm-auth verify
In the same terminal environment, install the notebooklm-research skill for the Claude Code user. A changed target is not overwritten without --force; forced updates create a timestamped backup.
Installs: Complete notebooklm-skill installation with the notebooklm-research skill at Claude Code project scope (.claude/skills/notebooklm-research/SKILL.md) · Claude Code
Before you start
Python 3.10 or newer
A Google account with access to NotebookLM
Run from: Claude Code project directory
In a terminal in the project directory, create and activate a virtual environment, install notebooklm-skill from PyPI, and install Chromium for browser login. Keep this virtual environment active for the following terminal steps.
In the same terminal environment, authenticate and verify the NotebookLM session.
notebooklm-auth setup
notebooklm-auth verify
In the same terminal environment and project directory, install the notebooklm-research skill at project scope. A changed target is not overwritten without --force; forced updates create a timestamped backup.
Create a source-grounded notebook and ask one evidence question
Uses notebooklm-research
An authenticated NotebookLM profile
Notebook title
One or more source inputs, each supplied as a URL, local file path, or raw text
Use the notebooklm-research skill to create a NotebookLM notebook titled [NOTEBOOK TITLE] using [ONE OR MORE SOURCE INPUTS]. Each source input may be a URL, a local file path, or raw text; at least one source input is required. Then ask: “Which conclusions have the strongest evidence?” Return the grounded answer with its citation metadata and identify any sources that were not successfully ingested. Do not generate additional artifacts yet.
Claude
Cursor