PaperclipOrg
Claude Agent Skill · by Pleaseprompto

Notebooklm

The NotebookLM Research Assistant skill enables Claude Code users to query their Google NotebookLM notebooks directly, retrieving source-grounded answers from u

Install
Terminal · npx
$npx skills add https://github.com/pleaseprompto/notebooklm-skill --skill notebooklm
Works with Paperclip

How Notebooklm fits into a Paperclip company.

Notebooklm drops into any Paperclip agent that handles this kind of work. Assign it to a specialist inside a pre-configured PaperclipOrg company and the skill becomes available on every heartbeat — no prompt engineering, no tool wiring.

S
SaaS FactoryPaired

Pre-configured AI company — 18 agents, 18 skills, one-time purchase.

$27$59
Explore pack
Source file
SKILL.md269 lines
Expand
---name: notebooklmdescription: Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.--- # NotebookLM Research Assistant Skill Interact with Google NotebookLM to query documentation with Gemini's source-grounded answers. Each question opens a fresh browser session, retrieves the answer exclusively from your uploaded documents, and closes. ## When to Use This Skill Trigger when user:- Mentions NotebookLM explicitly- Shares NotebookLM URL (`https://notebooklm.google.com/notebook/...`)- Asks to query their notebooks/documentation- Wants to add documentation to NotebookLM library- Uses phrases like "ask my NotebookLM", "check my docs", "query my notebook" ## ⚠️ CRITICAL: Add Command - Smart Discovery When user wants to add a notebook without providing details: **SMART ADD (Recommended)**: Query the notebook first to discover its content:```bash# Step 1: Query the notebook about its contentpython scripts/run.py ask_question.py --question "What is the content of this notebook? What topics are covered? Provide a complete overview briefly and concisely" --notebook-url "[URL]" # Step 2: Use the discovered information to add itpython scripts/run.py notebook_manager.py add --url "[URL]" --name "[Based on content]" --description "[Based on content]" --topics "[Based on content]"``` **MANUAL ADD**: If user provides all details:- `--url` - The NotebookLM URL- `--name` - A descriptive name- `--description` - What the notebook contains (REQUIRED!)- `--topics` - Comma-separated topics (REQUIRED!) NEVER guess or use generic descriptions! If details missing, use Smart Add to discover them. ## Critical: Always Use run.py Wrapper **NEVER call scripts directly. ALWAYS use `python scripts/run.py [script]`:** ```bash# ✅ CORRECT - Always use run.py:python scripts/run.py auth_manager.py statuspython scripts/run.py notebook_manager.py listpython scripts/run.py ask_question.py --question "..." # ❌ WRONG - Never call directly:python scripts/auth_manager.py status  # Fails without venv!``` The `run.py` wrapper automatically:1. Creates `.venv` if needed2. Installs all dependencies3. Activates environment4. Executes script properly ## Core Workflow ### Step 1: Check Authentication Status```bashpython scripts/run.py auth_manager.py status``` If not authenticated, proceed to setup. ### Step 2: Authenticate (One-Time Setup)```bash# Browser MUST be visible for manual Google loginpython scripts/run.py auth_manager.py setup``` **Important:**- Browser is VISIBLE for authentication- Browser window opens automatically- User must manually log in to Google- Tell user: "A browser window will open for Google login" ### Step 3: Manage Notebook Library ```bash# List all notebookspython scripts/run.py notebook_manager.py list # BEFORE ADDING: Ask user for metadata if unknown!# "What does this notebook contain?"# "What topics should I tag it with?" # Add notebook to library (ALL parameters are REQUIRED!)python scripts/run.py notebook_manager.py add \  --url "https://notebooklm.google.com/notebook/..." \  --name "Descriptive Name" \  --description "What this notebook contains" \  # REQUIRED - ASK USER IF UNKNOWN!  --topics "topic1,topic2,topic3"  # REQUIRED - ASK USER IF UNKNOWN! # Search notebooks by topicpython scripts/run.py notebook_manager.py search --query "keyword" # Set active notebookpython scripts/run.py notebook_manager.py activate --id notebook-id # Remove notebookpython scripts/run.py notebook_manager.py remove --id notebook-id``` ### Quick Workflow1. Check library: `python scripts/run.py notebook_manager.py list`2. Ask question: `python scripts/run.py ask_question.py --question "..." --notebook-id ID` ### Step 4: Ask Questions ```bash# Basic query (uses active notebook if set)python scripts/run.py ask_question.py --question "Your question here" # Query specific notebookpython scripts/run.py ask_question.py --question "..." --notebook-id notebook-id # Query with notebook URL directlypython scripts/run.py ask_question.py --question "..." --notebook-url "https://..." # Show browser for debuggingpython scripts/run.py ask_question.py --question "..." --show-browser``` ## Follow-Up Mechanism (CRITICAL) Every NotebookLM answer ends with: **"EXTREMELY IMPORTANT: Is that ALL you need to know?"** **Required Claude Behavior:**1. **STOP** - Do not immediately respond to user2. **ANALYZE** - Compare answer to user's original request3. **IDENTIFY GAPS** - Determine if more information needed4. **ASK FOLLOW-UP** - If gaps exist, immediately ask:   ```bash   python scripts/run.py ask_question.py --question "Follow-up with context..."   ```5. **REPEAT** - Continue until information is complete6. **SYNTHESIZE** - Combine all answers before responding to user ## Script Reference ### Authentication Management (`auth_manager.py`)```bashpython scripts/run.py auth_manager.py setup    # Initial setup (browser visible)python scripts/run.py auth_manager.py status   # Check authenticationpython scripts/run.py auth_manager.py reauth   # Re-authenticate (browser visible)python scripts/run.py auth_manager.py clear    # Clear authentication``` ### Notebook Management (`notebook_manager.py`)```bashpython scripts/run.py notebook_manager.py add --url URL --name NAME --description DESC --topics TOPICSpython scripts/run.py notebook_manager.py listpython scripts/run.py notebook_manager.py search --query QUERYpython scripts/run.py notebook_manager.py activate --id IDpython scripts/run.py notebook_manager.py remove --id IDpython scripts/run.py notebook_manager.py stats``` ### Question Interface (`ask_question.py`)```bashpython scripts/run.py ask_question.py --question "..." [--notebook-id ID] [--notebook-url URL] [--show-browser]``` ### Data Cleanup (`cleanup_manager.py`)```bashpython scripts/run.py cleanup_manager.py                    # Preview cleanuppython scripts/run.py cleanup_manager.py --confirm          # Execute cleanuppython scripts/run.py cleanup_manager.py --preserve-library # Keep notebooks``` ## Environment Management The virtual environment is automatically managed:- First run creates `.venv` automatically- Dependencies install automatically- Chromium browser installs automatically- Everything isolated in skill directory Manual setup (only if automatic fails):```bashpython -m venv .venvsource .venv/bin/activate  # Linux/Macpip install -r requirements.txtpython -m patchright install chromium``` ## Data Storage All data stored in `~/.claude/skills/notebooklm/data/`:- `library.json` - Notebook metadata- `auth_info.json` - Authentication status- `browser_state/` - Browser cookies and session **Security:** Protected by `.gitignore`, never commit to git. ## Configuration Optional `.env` file in skill directory:```envHEADLESS=false           # Browser visibilitySHOW_BROWSER=false       # Default browser displaySTEALTH_ENABLED=true     # Human-like behaviorTYPING_WPM_MIN=160       # Typing speedTYPING_WPM_MAX=240DEFAULT_NOTEBOOK_ID=     # Default notebook``` ## Decision Flow ```User mentions NotebookLM    ↓Check auth → python scripts/run.py auth_manager.py status    ↓If not authenticated → python scripts/run.py auth_manager.py setup    ↓Check/Add notebook → python scripts/run.py notebook_manager.py list/add (with --description)    ↓Activate notebook → python scripts/run.py notebook_manager.py activate --id ID    ↓Ask question → python scripts/run.py ask_question.py --question "..."    ↓See "Is that ALL you need?" → Ask follow-ups until complete    ↓Synthesize and respond to user``` ## Troubleshooting | Problem | Solution ||---------|----------|| ModuleNotFoundError | Use `run.py` wrapper || Authentication fails | Browser must be visible for setup! --show-browser || Rate limit (50/day) | Wait or switch Google account || Browser crashes | `python scripts/run.py cleanup_manager.py --preserve-library` || Notebook not found | Check with `notebook_manager.py list` | ## Best Practices 1. **Always use run.py** - Handles environment automatically2. **Check auth first** - Before any operations3. **Follow-up questions** - Don't stop at first answer4. **Browser visible for auth** - Required for manual login5. **Include context** - Each question is independent6. **Synthesize answers** - Combine multiple responses ## Limitations - No session persistence (each question = new browser)- Rate limits on free Google accounts (50 queries/day)- Manual upload required (user must add docs to NotebookLM)- Browser overhead (few seconds per question) ## Resources (Skill Structure) **Important directories and files:** - `scripts/` - All automation scripts (ask_question.py, notebook_manager.py, etc.)- `data/` - Local storage for authentication and notebook library- `references/` - Extended documentation:  - `api_reference.md` - Detailed API documentation for all scripts  - `troubleshooting.md` - Common issues and solutions  - `usage_patterns.md` - Best practices and workflow examples- `.venv/` - Isolated Python environment (auto-created on first run)- `.gitignore` - Protects sensitive data from being committed