Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

cli-anything-notebooklm — Claude Code skill: setup and features

Experimental harness to manage Google NotebookLM through a local CLI. It lets agents list notebooks, query sources, generate artifacts, and download files.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add HKUDS/CLI-Anything --skill cli-anything-notebooklm -a claude-code
Open on GitHub

What cli-anything-notebooklm does

The skill connects your coding agent to an installed notebooklm executable. It covers authentication checks, notebook queries, and source management. Agents can also chat with notebooks and fetch generated artifacts directly.

Workflows rely on explicit notebook IDs with --notebook and machine-readable output via --json where supported. The harness also exposes commands to list and trigger artifact generation, then download finished outputs to disk.

You need an active local NotebookLM session and the upstream notebooklm-py[browser] package with Playwright Chromium. Without an active session or the required browser binary, commands will fail.

What it helps with

  • inspect local NotebookLM authentication status
  • list existing notebooks and retrieve their IDs
  • attach URL sources to a selected notebook
  • ask questions and review conversation history
  • download generated artifacts to local storage

Example prompts for the agent

  • Check authentication state using `cli-anything-notebooklm auth status`.
  • List all notebooks in JSON format with `cli-anything-notebooklm --json notebook list`.
  • Show sources for notebook `nb_123` via `cli-anything-notebooklm --notebook nb_123 source list`.

How to install cli-anything-notebooklm

1Skills CLI (Vercel)

npx skills add HKUDS/CLI-Anything --skill cli-anything-notebooklm -a claude-code

2Manually: put the files in place

~/.claude/skills/cli-anything-notebooklm/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/cli-anything-notebooklm/

From the same set18

The whole set →
cli-hub-meta-skill HKUDS A skill that gives agents a catalog of professional command-line tools built for AI. Search, install, and run CLIs for video, design, AI, and development without leaving your editor. Claude Code CX Codex Cursor +1 5,300installs cli-anything HKUDS Builds a Python harness with Click commands for any GUI application or repository. Generates REPL, tests, and docs following the CLI-Anything methodology. Claude Code CX Codex Cursor +1 2,100installs cli-anything-blender HKUDS A skill that adds a stateful command-line interface for editing Blender 3D scenes. Use it when an agent needs to assemble a scene, assign materials, or render a frame without manual clicking. Claude Code CX Codex Cursor +1 941installs cli-anything-obsidian HKUDS Manage an Obsidian vault from the terminal: read, create, search, and update notes or run editor commands. It suits agents that need to work without the GUI. Claude Code CX Codex Cursor +1 917installs cli-anything-libreoffice HKUDS Skill for creating and editing Writer, Calc, and Impress documents from the CLI without a GUI. Produces real ODF files (ZIP with XML) — useful when an AI agent needs to assemble a report, spreadsheet, or presentation programmatically. Claude Code CX Codex Cursor +1 669installs cli-anything-drawio HKUDS A command-line harness over Draw.io: the skill hands your agent commands to build a diagram step by step and export it to PNG, PDF or SVG. Claude Code CX Codex Cursor +1 666installs cli-anything-freecad HKUDS Turns FreeCAD into a scriptable CLI for your agent: 258 commands for primitives, sketches, PartDesign features and headless export. Claude Code CX Codex Cursor +1 643installs cli-anything-gimp HKUDS Provides a stateful image editing CLI built on Pillow and GIMP for AI agents. It handles layers, drawing, and headless rendering without a GUI. Claude Code CX Codex Cursor +1 609installs

Similar

huggingface-gradio huggingface This skill helps you build and modify Python Gradio interfaces for machine learning demos. It provides patterns for layouts, UI components, and chatbot workflows. Claude Code CX Codex Cursor +1 2,300installs skill-creator tldraw A guide the agent follows while building a skill: what belongs in SKILL.md, what goes into scripts/, references/ and assets/, and how to keep the whole thing short. Claude Code CX Codex Cursor +1 431installs statistical-power K-Dense-AI Calculates how many observations your study needs to reliably detect a meaningful effect. Supports protocol planning, grant submissions, and pre-registration — from basic t-tests to complex mixed models and survival analysis. Claude Code CX Codex Cursor +1 1,300installs phoenix-tracing official [email protected] This skill guides OpenInference tracing for LLM apps with Phoenix. Use it to set up instrumentation, define custom spans, or prepare tracing for production. GitHub Copilot 1,000installs phoenix-evals official [email protected] Build and run evaluators for AI and LLM applications with Phoenix. Use it to investigate failures, evaluate RAG systems, and check model output. GitHub Copilot 1,000installs phoenix-cli official arize-ai A GitHub Copilot skill that drives the Phoenix CLI to pull traces, spans and sessions, then turns what it finds into a failure taxonomy for your LLM app. GitHub Copilot 1,000installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. Claude Code 466,719installs

Questions about cli-anything-notebooklm

How to install cli-anything-notebooklm in Claude Code?

Run npx skills add HKUDS/CLI-Anything --skill cli-anything-notebooklm -a claude-code in your terminal.

What does cli-anything-notebooklm do?

It provides a CLI harness for Google NotebookLM. The tool lets coding agents manage notebooks, ask questions, handle source URLs, and fetch generated artifacts.

What prerequisites are required before using this skill?

You need a local notebooklm CLI installation, Playwright Chromium via python3 -m playwright install chromium, and an active local login session.

Source text

SKILL.md · Apache-2.0 
---
name: "cli-anything-notebooklm"
description: Experimental NotebookLM harness for listing notebooks, managing sources, asking questions, generating artifacts, and downloading outputs through an installed notebooklm CLI.
---

# cli-anything-notebooklm

Experimental NotebookLM harness for CLI-Anything.

## Installation

This package is intended to be installed from the harness directory:

```bash
cd notebooklm/agent-harness
python3 -m pip install -e .
```

Install the upstream NotebookLM CLI if needed:

```bash
python3 -m pip install --user 'notebooklm-py[browser]'
python3 -m playwright install chromium
```

## Requirements

- `notebooklm` command installed locally
- Valid local NotebookLM login session

## Usage

### Basic Commands

```bash
# Show help
cli-anything-notebooklm --help

# Start with a notebook context
cli-anything-notebooklm --notebook nb_123 source list

# Prefer JSON for agent use
cli-anything-notebooklm --json notebook list
```

## Command Groups

| Group | Purpose |
| --- | --- |
| `auth` | login and auth validation |
| `notebook` | notebook list, create, summary |
| `source` | source listing and URL add |
| `chat` | ask questions and inspect history |
| `artifact` | list and generate artifacts |
| `download` | fetch generated outputs |
| `share` | inspect sharing state |

## Agent Workflow

1. Check auth with `cli-anything-notebooklm auth status`
2. Discover notebook IDs with `cli-anything-notebooklm --json notebook list`
3. Use explicit `--notebook` for follow-up commands
4. Prefer `--json` only where the upstream `notebooklm` command supports it

## Agent Guidance

- Prefer explicit notebook IDs with `--notebook`.
- Use `--json` for machine-readable output only on commands that support it upstream.
- Treat this harness as experimental and unofficial.
- Do not expose auth files or cookies in logs.
- NotebookLM is a Google product; this harness is unofficial and not affiliated with Google.

## References

- CLI-Anything: https://github.com/HKUDS/CLI-Anything
- CLI-Anything HARNESS.md: https://github.com/HKUDS/CLI-Anything/blob/main/cli-anything-plugin/HARNESS.md
- notebooklm-py: https://github.com/teng-lin/notebooklm-py
- Google NotebookLM help: https://support.google.com/notebooklm/answer/16206563

© HKUDS · Apache-2.0 · HKUDS/CLI-Anything

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor