b-open-io/notebooklm
skills/notebooklm/SKILL.md
This skill should be used when the user wants to query Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Provides browser automation, library management, and persistent auth. Drastically reduced hallucinations through document-only responses.
$ install --global
skillsauthnpx skillsauth add b-open-io/prompts notebooklmInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 29, 2026, 3:22 AM94.1s18 files scanned
SKILL.md
- name:
- notebooklm
- version:
- 1.0.0
- description:
- This skill should be used when the user wants to query Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Provides browser automation, library management, and persistent auth. Drastically reduced hallucinations through document-only responses.
- disable-model-invocation:
- true
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
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: Always Use run.py Wrapper
NEVER call scripts directly. ALWAYS use python scripts/run.py [script]:
# CORRECT - Always use run.py:
python scripts/run.py auth_manager.py status
python scripts/run.py notebook_manager.py list
python 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 handles environment setup.
Core Workflow
Step 1: Check Authentication
python scripts/run.py auth_manager.py status
If not authenticated, proceed to setup.
Step 2: Authenticate (One-Time Setup)
python scripts/run.py auth_manager.py setup
Important: Browser is VISIBLE for authentication. User must manually log in to Google.
Step 3: Manage Notebook Library
# List all notebooks
python scripts/run.py notebook_manager.py list
# Add notebook to library (ALL parameters REQUIRED)
python scripts/run.py notebook_manager.py add \
--url "https://notebooklm.google.com/notebook/..." \
--name "Descriptive Name" \
--description "What this notebook contains" \
--topics "topic1,topic2,topic3"
# Smart Add (discover content first)
python scripts/run.py ask_question.py \
--question "What is the content of this notebook?" \
--notebook-url "[URL]"
# Then use discovered info to add
# Set active notebook
python scripts/run.py notebook_manager.py activate --id notebook-id
Step 4: Ask Questions
# Basic query (uses active notebook if set)
python scripts/run.py ask_question.py --question "Your question here"
# Query specific notebook
python scripts/run.py ask_question.py --question "..." --notebook-id notebook-id
# Query with notebook URL directly
python scripts/run.py ask_question.py --question "..." --notebook-url "https://..."
Follow-Up Mechanism (CRITICAL)
Every NotebookLM answer ends with: "EXTREMELY IMPORTANT: Is that ALL you need to know?"
Required Behavior:
- STOP - Do not immediately respond to user
- ANALYZE - Compare answer to user's original request
- IDENTIFY GAPS - Determine if more information needed
- ASK FOLLOW-UP - If gaps exist, immediately ask follow-up question
- REPEAT - Continue until information is complete
- SYNTHESIZE - Combine all answers before responding to user
Script Reference
| Script | Purpose |
|--------|---------|
| auth_manager.py | Authentication setup and status |
| notebook_manager.py | Library management (add, list, search, activate, remove) |
| ask_question.py | Query interface |
| cleanup_manager.py | Data cleanup and maintenance |
Data Storage
All data stored in ~/.claude/skills/notebooklm/data/:
library.json- Notebook metadataauth_info.json- Authentication statusbrowser_state/- Browser cookies and session
Security: Protected by .gitignore, never commit to git.
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)
Additional Resources
For detailed guidance, see the references directory:
references/api-reference.md- Complete API documentation for all scripts with parameters, response formats, and exit codesreferences/troubleshooting.md- Common errors and solutions including authentication issues, rate limits, browser crashes, and recovery proceduresreferences/best-practices.md- Workflow patterns, question strategies, library organization, and rate limit management
Quick Reference
# Check auth
python scripts/run.py auth_manager.py status
# Add notebook
python scripts/run.py notebook_manager.py add --url URL --name NAME --description DESC --topics TOPICS
# List notebooks
python scripts/run.py notebook_manager.py list
# Ask question
python scripts/run.py ask_question.py --question "..."
# Cleanup
python scripts/run.py cleanup_manager.py --preserve-library
Related Skills
b-open-io/html-to-pdf
development
VerifiedTrustedCommunity
This skill should be used when the user asks to "design a business card", "make a printable PDF", "render HTML to PDF", "generate a postcard", "build print collateral", "set up an HTML print pipeline", or needs help with bleed, safe areas, font embedding, or QR generation for print. Provides a Playwright-based pipeline with multiple bundled templates and theme variants for business cards (minimal, watercolor light, watercolor dark) and instructions for adding new templates.
12SKILL.mdUpdated May 29, 2026
b-open-io/x-user-timeline
tools
VerifiedTrustedCommunity
Get recent tweets from an X/Twitter user. Use when user asks "what has @username posted", "recent tweets from", "user's X posts", "show timeline for", "what is @user saying". Requires X_BEARER_TOKEN.
12SKILL.mdUpdated Apr 3, 2026
b-open-io/x-user-lookup
data-ai
VerifiedTrustedCommunity
Get X/Twitter user profile by username. Use when user asks "who is @username", "get X profile", "lookup Twitter user", "find X account", "user details", "follower count for". Requires X_BEARER_TOKEN.
12SKILL.mdUpdated Apr 3, 2026
b-open-io/x-tweet-search
data-ai
VerifiedTrustedCommunity
Search recent X/Twitter posts by query. Returns RAW TWEETS (last 7 days). Use when user asks "search X for", "find tweets about", "what are people saying about", "Twitter search", "raw tweets about". For AI summaries/sentiment, use x-research instead. Requires X_BEARER_TOKEN.
12SKILL.mdUpdated Apr 3, 2026