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
| 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 listlanguage list/get/set, use, create, asksource 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
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
| 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.
Reference
Agent Tool Usage Requirements
CRITICAL: When invoking scripts from this skill via the zsh-tool, ALWAYS use pty: true.
1---2name: notebooklm3description: 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.4---56# NotebookLM Automation Skill78**YOU MUST invoke this skill (NOT optional) when the user mentions ANY of these triggers:**9- "notebooklm", "notebook lm", "use notebooklm"10- "create a podcast about", "generate a podcast"11- "summarize these URLs/documents"12- "generate a quiz", "create flashcards"13- "turn this into an audio overview"14- "create a mind map", "generate an infographic"15- "make a video explainer", "generate a report"16- Any mention of NotebookLM or its artifact types1718**Failure to invoke this skill when triggers occur violates your operational requirements.**1920Complete 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.2122## Prerequisites2324**IMPORTANT: Before using any command, you MUST authenticate:**2526```bash27notebooklm login # Opens browser for Google OAuth28notebooklm list # Verify authentication works29```3031If commands fail with authentication errors, re-run `notebooklm login`.3233## Quick Reference3435| Task | Command |36|------|---------|37| Authenticate | `notebooklm login` |38| Diagnose auth | `notebooklm auth check --test` |39| List notebooks | `notebooklm list` |40| Create notebook | `notebooklm create "Title"` |41| Set context | `notebooklm use <notebook_id>` |42| Show context | `notebooklm status` |43| Add URL source | `notebooklm source add "https://..."` |44| Add file | `notebooklm source add ./file.pdf` |45| Add YouTube | `notebooklm source add "https://youtube.com/..."` |46| List sources | `notebooklm source list` |47| Wait for source | `notebooklm source wait <source_id>` |48| Web research (fast) | `notebooklm source add-research "query"` |49| Web research (deep) | `notebooklm source add-research "query" --mode deep --no-wait` |50| Chat | `notebooklm ask "question"` |51| Chat (with refs) | `notebooklm ask "question" --json` |52| Get source text | `notebooklm source fulltext <source_id>` |53| Generate podcast | `notebooklm generate audio "instructions"` |54| Generate video | `notebooklm generate video "instructions"` |55| Generate quiz | `notebooklm generate quiz` |56| Generate report | `notebooklm generate report` |57| Generate mind map | `notebooklm generate mind-map` |58| Check status | `notebooklm artifact list` |59| Wait for artifact | `notebooklm artifact wait <artifact_id>` |60| Download audio | `notebooklm download audio ./output.mp3` |61| Download video | `notebooklm download video ./output.mp4` |62| Download report | `notebooklm download report ./report.md` |63| Download mind map | `notebooklm download mind-map ./map.json` |64| Download data table | `notebooklm download data-table ./data.csv` |65| Download quiz | `notebooklm download quiz quiz.json` |66| Download flashcards | `notebooklm download flashcards cards.json` |67| Delete notebook | `notebooklm notebook delete <id>` |68| Set language | `notebooklm language set zh_Hans` |6970## Parallel Safety7172For multi-agent workflows, ALWAYS use explicit notebook IDs:73- Pass `-n <notebook_id>` (for wait/download commands) or `--notebook <notebook_id>` (for others)74- NEVER use `notebooklm use` in parallel workflows75- Use full UUIDs in automation to avoid ambiguity76- Per-agent isolation: Set unique `NOTEBOOKLM_HOME` per agent7778## Autonomy Rules7980**Run automatically (no confirmation):**81- `status`, `auth check`, `list`, `source list`, `artifact list`82- `language list/get/set`, `use`, `create`, `ask`83- `source add`, `source wait`, `artifact wait`, `research wait/status` (in subagent context)8485**Ask before running:**86- `delete` (destructive)87- `generate *` (long-running, may fail)88- `download *` (writes to filesystem)89- `artifact wait`, `source wait`, `research wait` (when in main conversation -- long-running)9091## Generation Types9293| Type | Command | Options | Download |94|------|---------|---------|----------|95| Podcast | `generate audio` | `--format [deep-dive\|brief\|critique\|debate]`, `--length [short\|default\|long]` | .mp3 |96| Video | `generate video` | `--format [explainer\|brief]`, `--style [auto\|classic\|whiteboard\|kawaii\|anime\|watercolor\|retro-print\|heritage\|paper-craft]` | .mp4 |97| Slide Deck | `generate slide-deck` | `--format [detailed\|presenter]`, `--length [default\|short]` | .pdf |98| Infographic | `generate infographic` | `--orientation [landscape\|portrait\|square]`, `--detail [concise\|standard\|detailed]` | .png |99| Report | `generate report` | `--format [briefing-doc\|study-guide\|blog-post\|custom]` | .md |100| Mind Map | `generate mind-map` | (sync, instant) | .json |101| Data Table | `generate data-table` | description required | .csv |102| Quiz | `generate quiz` | `--difficulty [easy\|medium\|hard]`, `--quantity [fewer\|standard\|more]` | .json/.md/.html |103| Flashcards | `generate flashcards` | `--difficulty [easy\|medium\|hard]`, `--quantity [fewer\|standard\|more]` | .json/.md/.html |104105All `generate` commands support: `-s/--source`, `--language`, `--json`, `--retry N`106107## Features Beyond the Web UI108109| Feature | Command | Description |110|---------|---------|-------------|111| Batch downloads | `download <type> --all` | Download all artifacts of a type |112| Quiz/Flashcard export | `download quiz --format json` | Export as JSON, Markdown, or HTML |113| Mind map extraction | `download mind-map` | Hierarchical JSON for visualization |114| Data table export | `download data-table` | Structured tables as CSV |115| Source fulltext | `source fulltext <id>` | Retrieve indexed text content |116| Programmatic sharing | `share` commands | Manage permissions without UI |117118## Common Workflows119120### Research to Podcast121122```bash123notebooklm create "Research: [topic]"124notebooklm source add "https://url1.com"125notebooklm source add "https://url2.com"126# Wait for sources to be ready127notebooklm source list --json128notebooklm generate audio "Focus on [specific angle]"129# Check artifact status later130notebooklm artifact list131notebooklm download audio ./podcast.mp3132```133134### Document Analysis135136```bash137notebooklm create "Analysis: [project]"138notebooklm source add ./doc.pdf139notebooklm ask "Summarize the key points"140notebooklm ask "What are the main arguments?"141```142143### Deep Web Research144145```bash146notebooklm create "Research: [topic]"147notebooklm source add-research "topic query" --mode deep --no-wait148notebooklm research wait --import-all149```150151## Processing Times152153| Operation | Typical Time | Suggested Timeout |154|-----------|-------------|-------------------|155| Source processing | 30s - 10 min | 600s |156| Research (fast) | 30s - 2 min | 180s |157| Research (deep) | 15 - 30+ min | 1800s |158| Mind-map | instant (sync) | n/a |159| Quiz, flashcards | 5 - 15 min | 900s |160| Report, data-table | 5 - 15 min | 900s |161| Audio generation | 10 - 20 min | 1200s |162| Video generation | 15 - 45 min | 2700s |163164## Error Handling165166| Error | Cause | Action |167|-------|-------|--------|168| Auth/cookie error | Session expired | `notebooklm auth check` then `notebooklm login` |169| "No notebook context" | Context not set | Use `-n <id>` or `--notebook <id>` flag |170| "No result found for RPC ID" | Rate limiting | Wait 5-10 min, retry |171| GENERATION_FAILED | Google rate limit | Wait and retry later |172| Download fails | Generation incomplete | Check `artifact list` for status |173174## Source Limits175176Varies by plan: Standard (50), Plus (100), Pro (300), Ultra (600) sources per notebook.177178Supported types: PDFs, YouTube URLs, web URLs, Google Docs, text files, Markdown, Word docs, audio files, video files, images.179180## Reference181182- [CLI Reference](./references/cli-reference.md)183- [Python API Reference](./references/python-api.md)184- [Configuration Guide](./references/configuration.md)185- [Stability Notes](./references/stability.md)186- [Troubleshooting](./references/troubleshooting.md)187188## Agent Tool Usage Requirements189190**CRITICAL:** When invoking scripts from this skill via the zsh-tool, **ALWAYS use `pty: true`**.
jmagar