# Jacob Bd Notebooklm CLI Nlm CLI Skill > NotebookLM CLI Expert - Skill: `tomevault-io/jacob-bd-notebooklm-cli-nlm-cli-skill` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/jacob-bd-notebooklm-cli-nlm-cli-skill` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/jacob-bd-notebooklm-cli-nlm-cli-skill/raw - Safety review: pending (external: skill-scanner PASS, skillspector PASS) - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Coding & Dev Tools - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/jacob-bd-notebooklm-cli-nlm-cli-skill --- # NotebookLM CLI Expert This skill provides comprehensive guidance for using the `nlm` CLI to automate Google NotebookLM workflows. ## Quick Reference ```bash nlm --help # List all commands nlm --help # Help for specific command nlm --ai # Full AI-optimized documentation nlm --version # Check installed version ``` ## Critical Rules (Read First!) 1. **Always authenticate first**: Run `nlm login` before any operations 2. **Sessions expire in ~20 minutes**: Re-run `nlm login` if commands start failing 3. **`--confirm` is REQUIRED**: All generation and delete commands need `--confirm` or `-y` 4. **Research requires `--notebook-id`**: The flag is mandatory, not positional 5. **Capture IDs from output**: Create/start commands return IDs needed for subsequent operations 6. **Use aliases**: Simplify long UUIDs with `nlm alias set ` 7. **⚠️ ALWAYS ASK USER BEFORE DELETE**: Before executing ANY delete command, ask the user for explicit confirmation. Deletions are **irreversible**. Show what will be deleted and warn about permanent data loss. 8. **Check aliases before creating**: Run `nlm alias list` before creating a new alias to avoid conflicts with existing names. 9. **DO NOT launch REPL**: Never use `nlm chat start` - it opens an interactive REPL that AI tools cannot control. Use `nlm notebook query` for one-shot Q&A instead. 10. **Choose output format wisely**: Default output (no flags) is compact and token-efficient—use it for status checks. Use `--quiet` to capture IDs for piping. Only use `--json` when you need to parse specific fields programmatically. ## Workflow Decision Tree Use this to determine the right sequence of commands: ``` User wants to... │ ├─► Work with NotebookLM for the first time │ └─► nlm login → nlm notebook create "Title" │ ├─► Add content to a notebook │ ├─► From a URL/webpage → nlm source add --url "https://..." │ ├─► From YouTube → nlm source add --url "https://youtube.com/..." │ ├─► From pasted text → nlm source add --text "content" --title "Title" │ ├─► From Google Drive → nlm source add --drive --type doc │ └─► Discover new sources → nlm research start "query" --notebook-id │ ├─► Generate content from sources │ ├─► Podcast/Audio → nlm audio create --confirm │ ├─► Written summary → nlm report create --confirm │ ├─► Study materials → nlm quiz/flashcards create --confirm │ ├─► Visual content → nlm mindmap/slides/infographic create --confirm │ ├─► Video → nlm video create --confirm │ └─► Extract data → nlm data-table create "description" --confirm │ ├─► Ask questions about sources │ └─► nlm notebook query "question" │ (Use --conversation-id for follow-ups) │ ⚠️ Do NOT use `nlm chat start` - it's a REPL for humans only │ ├─► Check generation status │ └─► nlm studio status │ └─► Manage/cleanup ├─► List notebooks → nlm notebook list ├─► List sources → nlm source list ├─► Delete source → nlm source delete --confirm └─► Delete notebook → nlm notebook delete --confirm ``` ## Command Categories ### 1. Authentication ```bash nlm login # Launch Chrome, extract cookies (primary method) nlm login --check # Validate current session nlm login --profile work # Use named profile for multiple accounts nlm auth status # Check if authenticated nlm auth list # List all profiles ``` **Session lifetime**: ~20 minutes. Re-authenticate when commands fail with auth errors. ### 2. Notebook Management ```bash nlm notebook list # List all notebooks nlm notebook list --json # JSON output for parsing nlm notebook list --quiet # IDs only (for scripting) nlm notebook create "Title" # Create notebook, returns ID nlm notebook get # Get notebook details nlm notebook describe # AI-generated summary + suggested topics nlm notebook query "question" # One-shot Q&A with sources nlm notebook rename "New Title" # Rename notebook nlm notebook delete --confirm # PERMANENT deletion ``` ### 3. Source Management ```bash # Adding sources nlm source add --url "https://..." # Web page nlm source add --url "https://youtube.com/..." # YouTube video nlm source add --text "content" --title "X" # Pasted text nlm source add --drive # Drive doc (auto-detect type) nlm source add --drive --type slides # Explicit type # Listing and viewing nlm source list # Table of sources nlm source list --drive # Show Drive sources with freshness nlm source list --drive -S # Skip freshness checks (faster) nlm source get # Source metadata nlm source describe # AI summary + keywords nlm source content # Raw text content nlm source content -o file.txt # Export to file # Drive sync (for stale sources) nlm source stale # List outdated Drive sources nlm source sync --confirm # Sync all stale sources nlm source sync --source-ids --confirm # Sync specific # Deletion nlm source delete --confirm ``` **Drive types**: `doc`, `slides`, `sheets`, `pdf` ### 4. Research (Source Discovery) Research finds NEW sources from the web or Google Drive: ```bash # Start research (--notebook-id is REQUIRED) nlm research start "query" --notebook-id # Fast web (~30s) nlm research start "query" --notebook-id --mode deep # Deep web (~5min) nlm research start "query" --notebook-id --source drive # Drive search # Check progress nlm research status # Poll until done (5min max) nlm research status --max-wait 0 # Single check, no waiting nlm research status --task-id # Check specific task nlm research status --full # Full details # Import discovered sources nlm research import # Import all nlm research import --indices 0,2,5 # Import specific ``` **Modes**: `fast` (~30s, ~10 sources) | `deep` (~5min, ~40+ sources, web only) ### 5. Content Generation (Studio) All generation commands share these flags: - `--confirm` or `-y`: **REQUIRED** to execute - `--source-ids `: Limit to specific sources - `--language `: BCP-47 code (en, es, fr, de, ja) ```bash # Audio (Podcast) nlm audio create --confirm nlm audio create --format deep_dive --length default --confirm nlm audio create --format brief --focus "key topic" --confirm # Formats: deep_dive, brief, critique, debate # Lengths: short, default, long # Report nlm report create --confirm nlm report create --format "Study Guide" --confirm nlm report create --format "Create Your Own" --prompt "Custom..." --confirm # Formats: "Briefing Doc", "Study Guide", "Blog Post", "Create Your Own" # Quiz nlm quiz create --confirm nlm quiz create --count 5 --difficulty 3 --confirm # Count: number of questions (default: 2) # Difficulty: 1-5 (1=easy, 5=hard) # Flashcards nlm flashcards create --confirm nlm flashcards create --difficulty hard --confirm # Difficulty: easy, medium, hard # Mind Map nlm mindmap create --confirm nlm mindmap create --title "Topic Overview" --confirm nlm mindmap list # List existing mind maps # Slides nlm slides create --confirm nlm slides create --format presenter --length short --confirm # Formats: detailed, presenter | Lengths: short, default # Infographic nlm infographic create --confirm nlm infographic create --orientation portrait --detail detailed --confirm # Orientations: landscape, portrait, square # Detail: concise, standard, detailed # Video nlm video create --confirm nlm video create --format brief --style whiteboard --confirm # Formats: explainer, brief # Styles: auto_select, classic, whiteboard, kawaii, anime, watercolor, retro_print, heritage, paper_craft # Data Table nlm data-table create "Extract all dates and events" --confirm # DESCRIPTION is required as second argument ``` ### 6. Studio (Artifact Management) Check and manage generated content: ```bash nlm studio status # List all artifacts nlm studio status --json # JSON output nlm studio delete --confirm # Delete artifact ``` **Status values**: `completed` (✓), `in_progress` (●), `failed` (✗) ### 7. Interactive Chat (Human Users Only) > ⚠️ **AI TOOLS: DO NOT USE `nlm chat start`** - It launches an interactive REPL that cannot be controlled programmatically. Use `nlm notebook query` for one-shot Q&A instead. For human users at a terminal: ```bash nlm chat start # Launch interactive REPL ``` **REPL Commands**: - `/sources` - List available sources - `/clear` - Reset conversation context - `/help` - Show commands - `/exit` - Exit REPL **Configure chat behavior** (works for both REPL and query): ```bash nlm chat configure --goal default nlm chat configure --goal learning_guide nlm chat configure --goal custom --prompt "Act as a tutor..." nlm chat configure --response-length longer # longer, default, shorter ``` ### 8. Aliases (UUID Shortcuts) Simplify long UUIDs: ```bash nlm alias set myproject abc123-def456... # Create alias (auto-detects type) nlm alias get myproject # Resolve to UUID nlm alias list # List all aliases nlm alias delete myproject # Remove alias # Use aliases anywhere nlm notebook get myproject nlm source list myproject nlm audio create myproject --confirm ``` ### 9. Configuration ```bash nlm config show # Show current config nlm config get # Get specific setting nlm config set # Update setting ``` ## Output Formats Most list commands support multiple formats: | Flag | Description | |------|-------------| | (none) | Rich table (human-readable) | | `--json` | JSON output (for parsing) | | `--quiet` | IDs only (for piping) | | `--title` | "ID: Title" format | | `--url` | "ID: URL" format (sources only) | | `--full` | All columns/details | ## Common Patterns ### Pattern 1: Research → Podcast Pipeline ```bash nlm notebook create "AI Research 2026" # Capture ID nlm alias set ai nlm research start "agentic AI trends" --notebook-id ai --mode deep nlm research status ai --max-wait 300 # Wait up to 5 min nlm research import ai # Import all sources nlm audio create ai --format deep_dive --confirm nlm studio status ai # Check generation progress ``` ### Pattern 2: Quick Content Ingestion ```bash nlm source add --url "https://example1.com" nlm source add --url "https://example2.com" nlm source add --text "My notes..." --title "Notes" nlm source list ``` ### Pattern 3: Study Materials Generation ```bash nlm report create --format "Study Guide" --confirm nlm quiz create --count 10 --difficulty 3 --confirm nlm flashcards create --difficulty medium --confirm ``` ### Pattern 4: Drive Document Workflow ```bash nlm source add --drive 1KQH3eW0hMBp7WK... --type slides # ... time passes, document is edited ... nlm source stale # Check freshness nlm source sync --confirm # Sync if stale ``` ## Error Recovery | Error | Cause | Solution | |-------|-------|----------| | "Cookies have expired" | Session timeout | `nlm login` | | "authentication may have expired" | Session timeout | `nlm login` | | "Notebook not found" | Invalid ID | `nlm notebook list` | | "Source not found" | Invalid ID | `nlm source list ` | | "Rate limit exceeded" | Too many calls | Wait 30s, retry | | "Research already in progress" | Pending research | Use `--force` or import first | | Chrome doesn't launch | Port conflict | Close Chrome, retry | ## Rate Limiting Wait between operations to avoid rate limits: - Source operations: 2 seconds - Content generation: 5 seconds - Research operations: 2 seconds - Query operations: 2 seconds ## Advanced Reference For detailed information, see: - **[references/command_reference.md](references/command_reference.md)**: Complete command signatures - **[references/troubleshooting.md](references/troubleshooting.md)**: Detailed error handling - **[references/workflows.md](references/workflows.md)**: End-to-end task sequences --- > Converted and distributed by [TomeVault](https://tomevault.io/claim/jacob-bd) — claim your Tome and manage your conversions.