Notebooklm

Community

jmagar

notebooklm

Programmatic access to Google NotebookLM for creating notebooks, adding sources (URLs, YouTube, PDFs, audio, video, images), chatting with content, generating artifacts (podcasts, videos, reports, quizzes, mind maps, flashcards, infographics), and downloading results. Includes capabilities beyond the web UI.

Overview

Publisher	jmagar
Repository	`claude-homelab`
Skill name	`notebooklm`
Stars	87
Forks	11
Bundled files	17
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
17 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by jmagar on GitHub. Read the source before you install it.

Installation

Install the Notebooklm AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/jmagar/claude-homelab/tree/main/skills/notebooklm
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/jmagar/claude-homelab.git /tmp/claude-homelab
mkdir -p .claude/skills
cp -r /tmp/claude-homelab/skills/notebooklm .claude/skills/notebooklm

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Notebooklm in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Notebooklm on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Notebooklm is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

NotebookLM Automation Skill

YOU MUST invoke this skill (NOT optional) when the user mentions ANY of these triggers:

"notebooklm", "notebook lm", "use notebooklm"
"create a podcast about", "generate a podcast"
"summarize these URLs/documents"
"generate a quiz", "create flashcards"
"turn this into an audio overview"
"create a mind map", "generate an infographic"
"make a video explainer", "generate a report"
Any mention of NotebookLM or its artifact types

Failure to invoke this skill when triggers occur violates your operational requirements.

Complete programmatic access to Google NotebookLM -- including capabilities not exposed in the web UI. Create notebooks, add sources (URLs, YouTube, PDFs, audio, video, images), chat with content, generate all artifact types, and download results in multiple formats.

Prerequisites

IMPORTANT: Before using any command, you MUST authenticate:

bash
notebooklm login          # Opens browser for Google OAuth
notebooklm list           # Verify authentication works

If commands fail with authentication errors, re-run notebooklm login.

Quick Reference

Task	Command
Authenticate	`notebooklm login`
Diagnose auth	`notebooklm auth check --test`
List notebooks	`notebooklm list`
Create notebook	`notebooklm create "Title"`
Set context	`notebooklm use <notebook_id>`
Show context	`notebooklm status`
Add URL source	`notebooklm source add "https://..."`
Add file	`notebooklm source add ./file.pdf`
Add YouTube	`notebooklm source add "https://youtube.com/..."`
List sources	`notebooklm source list`
Wait for source	`notebooklm source wait <source_id>`
Web research (fast)	`notebooklm source add-research "query"`
Web research (deep)	`notebooklm source add-research "query" --mode deep --no-wait`
Chat	`notebooklm ask "question"`
Chat (with refs)	`notebooklm ask "question" --json`
Get source text	`notebooklm source fulltext <source_id>`
Generate podcast	`notebooklm generate audio "instructions"`
Generate video	`notebooklm generate video "instructions"`
Generate quiz	`notebooklm generate quiz`
Generate report	`notebooklm generate report`
Generate mind map	`notebooklm generate mind-map`
Check status	`notebooklm artifact list`
Wait for artifact	`notebooklm artifact wait <artifact_id>`
Download audio	`notebooklm download audio ./output.mp3`
Download video	`notebooklm download video ./output.mp4`
Download report	`notebooklm download report ./report.md`
Download mind map	`notebooklm download mind-map ./map.json`
Download data table	`notebooklm download data-table ./data.csv`
Download quiz	`notebooklm download quiz quiz.json`
Download flashcards	`notebooklm download flashcards cards.json`
Delete notebook	`notebooklm notebook delete <id>`
Set language	`notebooklm language set zh_Hans`

Parallel Safety

For multi-agent workflows, ALWAYS use explicit notebook IDs:

Pass -n <notebook_id> (for wait/download commands) or --notebook <notebook_id> (for others)
NEVER use notebooklm use in parallel workflows
Use full UUIDs in automation to avoid ambiguity
Per-agent isolation: Set unique NOTEBOOKLM_HOME per agent

Autonomy Rules

Run automatically (no confirmation):

status, auth check, list, source list, artifact list
language list/get/set, use, create, ask
source add, source wait, artifact wait, research wait/status (in subagent context)

Ask before running:

delete (destructive)
generate * (long-running, may fail)
download * (writes to filesystem)
artifact wait, source wait, research wait (when in main conversation -- long-running)

Generation Types

Type	Command	Options	Download
Podcast	`generate audio`	`--format [deep-dive\|brief\|critique\|debate]`, `--length [short\|default\|long]`	.mp3
Video	`generate video`	`--format [explainer\|brief]`, `--style [auto\|classic\|whiteboard\|kawaii\|anime\|watercolor\|retro-print\|heritage\|paper-craft]`	.mp4
Slide Deck	`generate slide-deck`	`--format [detailed\|presenter]`, `--length [default\|short]`	.pdf
Infographic	`generate infographic`	`--orientation [landscape\|portrait\|square]`, `--detail [concise\|standard\|detailed]`	.png
Report	`generate report`	`--format [briefing-doc\|study-guide\|blog-post\|custom]`	.md
Mind Map	`generate mind-map`	(sync, instant)	.json
Data Table	`generate data-table`	description required	.csv
Quiz	`generate quiz`	`--difficulty [easy\|medium\|hard]`, `--quantity [fewer\|standard\|more]`	.json/.md/.html
Flashcards	`generate flashcards`	`--difficulty [easy\|medium\|hard]`, `--quantity [fewer\|standard\|more]`	.json/.md/.html

All generate commands support: -s/--source, --language, --json, --retry N

Features Beyond the Web UI

Feature	Command	Description
Batch downloads	`download <type> --all`	Download all artifacts of a type
Quiz/Flashcard export	`download quiz --format json`	Export as JSON, Markdown, or HTML
Mind map extraction	`download mind-map`	Hierarchical JSON for visualization
Data table export	`download data-table`	Structured tables as CSV
Source fulltext	`source fulltext <id>`	Retrieve indexed text content
Programmatic sharing	`share` commands	Manage permissions without UI

Common Workflows

Research to Podcast

bash
notebooklm create "Research: [topic]"
notebooklm source add "https://url1.com"
notebooklm source add "https://url2.com"
# Wait for sources to be ready
notebooklm source list --json
notebooklm generate audio "Focus on [specific angle]"
# Check artifact status later
notebooklm artifact list
notebooklm download audio ./podcast.mp3

Document Analysis

bash
notebooklm create "Analysis: [project]"
notebooklm source add ./doc.pdf
notebooklm ask "Summarize the key points"
notebooklm ask "What are the main arguments?"

Deep Web Research

bash
notebooklm create "Research: [topic]"
notebooklm source add-research "topic query" --mode deep --no-wait
notebooklm research wait --import-all

Processing Times

Operation	Typical Time	Suggested Timeout
Source processing	30s - 10 min	600s
Research (fast)	30s - 2 min	180s
Research (deep)	15 - 30+ min	1800s
Mind-map	instant (sync)	n/a
Quiz, flashcards	5 - 15 min	900s
Report, data-table	5 - 15 min	900s
Audio generation	10 - 20 min	1200s
Video generation	15 - 45 min	2700s

Error Handling

Error	Cause	Action
Auth/cookie error	Session expired	`notebooklm auth check` then `notebooklm login`
"No notebook context"	Context not set	Use `-n <id>` or `--notebook <id>` flag
"No result found for RPC ID"	Rate limiting	Wait 5-10 min, retry
GENERATION_FAILED	Google rate limit	Wait and retry later
Download fails	Generation incomplete	Check `artifact list` for status

Source Limits

Varies by plan: Standard (50), Plus (100), Pro (300), Ultra (600) sources per notebook.

Supported types: PDFs, YouTube URLs, web URLs, Google Docs, text files, Markdown, Word docs, audio files, video files, images.

Agent Tool Usage Requirements

CRITICAL: When invoking scripts from this skill via the zsh-tool, ALWAYS use pty: true.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Notebooklm AI skill do?

Why use Notebooklm on TypingMind?

Because you install it once and use it with any model. Notebooklm is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Notebooklm in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jmagar/claude-homelab/tree/main/skills/notebooklm. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Notebooklm?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Notebooklm?

As many as you like. As long as a model supports skills, you can use Notebooklm with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Notebooklm AI skill free?

Yes. It is published on GitHub by jmagar under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Proof Video

openclaw

OrganizationPopular

Add subtitles, captions, narration cues, or zoom to a proof video or PR recording using repo-local capture helpers and a system ffmpeg renderer.

Facetime

Inspect FaceTime internal stages, place an approved call to a configured owner handle, and request hangup through facetime_call.

Camsnap

Capture frames or clips from RTSP/ONVIF cameras and local webcams, including USB pan/tilt/zoom control.

Content Engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

NotebookLM Automation Skill

Prerequisites

Quick Reference

Parallel Safety

Autonomy Rules

Generation Types

Features Beyond the Web UI

Common Workflows

Research to Podcast

Document Analysis

Deep Web Research

Processing Times

Error Handling

Source Limits

Reference

Agent Tool Usage Requirements

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now