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.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "notebooklm" with this command: npx skills add jmagar/claude-homelab/jmagar-claude-homelab-notebooklm

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:

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

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

Quick Reference

TaskCommand
Authenticatenotebooklm login
Diagnose authnotebooklm auth check --test
List notebooksnotebooklm list
Create notebooknotebooklm create "Title"
Set contextnotebooklm use <notebook_id>
Show contextnotebooklm status
Add URL sourcenotebooklm source add "https://..."
Add filenotebooklm source add ./file.pdf
Add YouTubenotebooklm source add "https://youtube.com/..."
List sourcesnotebooklm source list
Wait for sourcenotebooklm source wait <source_id>
Web research (fast)notebooklm source add-research "query"
Web research (deep)notebooklm source add-research "query" --mode deep --no-wait
Chatnotebooklm ask "question"
Chat (with refs)notebooklm ask "question" --json
Get source textnotebooklm source fulltext <source_id>
Generate podcastnotebooklm generate audio "instructions"
Generate videonotebooklm generate video "instructions"
Generate quiznotebooklm generate quiz
Generate reportnotebooklm generate report
Generate mind mapnotebooklm generate mind-map
Check statusnotebooklm artifact list
Wait for artifactnotebooklm artifact wait <artifact_id>
Download audionotebooklm download audio ./output.mp3
Download videonotebooklm download video ./output.mp4
Download reportnotebooklm download report ./report.md
Download mind mapnotebooklm download mind-map ./map.json
Download data tablenotebooklm download data-table ./data.csv
Download quiznotebooklm download quiz quiz.json
Download flashcardsnotebooklm download flashcards cards.json
Delete notebooknotebooklm notebook delete <id>
Set languagenotebooklm 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

TypeCommandOptionsDownload
Podcastgenerate audio--format [deep-dive|brief|critique|debate], --length [short|default|long].mp3
Videogenerate video--format [explainer|brief], --style [auto|classic|whiteboard|kawaii|anime|watercolor|retro-print|heritage|paper-craft].mp4
Slide Deckgenerate slide-deck--format [detailed|presenter], --length [default|short].pdf
Infographicgenerate infographic--orientation [landscape|portrait|square], --detail [concise|standard|detailed].png
Reportgenerate report--format [briefing-doc|study-guide|blog-post|custom].md
Mind Mapgenerate mind-map(sync, instant).json
Data Tablegenerate data-tabledescription required.csv
Quizgenerate quiz--difficulty [easy|medium|hard], --quantity [fewer|standard|more].json/.md/.html
Flashcardsgenerate 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

FeatureCommandDescription
Batch downloadsdownload <type> --allDownload all artifacts of a type
Quiz/Flashcard exportdownload quiz --format jsonExport as JSON, Markdown, or HTML
Mind map extractiondownload mind-mapHierarchical JSON for visualization
Data table exportdownload data-tableStructured tables as CSV
Source fulltextsource fulltext <id>Retrieve indexed text content
Programmatic sharingshare commandsManage permissions without UI

Common Workflows

Research to Podcast

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

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

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

Processing Times

OperationTypical TimeSuggested Timeout
Source processing30s - 10 min600s
Research (fast)30s - 2 min180s
Research (deep)15 - 30+ min1800s
Mind-mapinstant (sync)n/a
Quiz, flashcards5 - 15 min900s
Report, data-table5 - 15 min900s
Audio generation10 - 20 min1200s
Video generation15 - 45 min2700s

Error Handling

ErrorCauseAction
Auth/cookie errorSession expirednotebooklm auth check then notebooklm login
"No notebook context"Context not setUse -n <id> or --notebook <id> flag
"No result found for RPC ID"Rate limitingWait 5-10 min, retry
GENERATION_FAILEDGoogle rate limitWait and retry later
Download failsGeneration incompleteCheck 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.

Reference

Agent Tool Usage Requirements

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

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

memos

No summary provided by upstream source.

Repository SourceNeeds Review
General

unraid

No summary provided by upstream source.

Repository SourceNeeds Review
General

tailscale

No summary provided by upstream source.

Repository SourceNeeds Review
General

zfs

No summary provided by upstream source.

Repository SourceNeeds Review