Notebooklm
Wire Google NotebookLM into your agent so you can query curated docs, add sources, and pull synthesized answers or studio outputs via the `nlm` CLI.
Overview
notebooklm is an agent skill most often used in Build (also Idea research and Validate scope) that connects agents to Google NotebookLM via `nlm` for RAG queries and notebook management.
Install
npx skills add https://github.com/giuseppe-trisciuoglio/developer-kit --skill notebooklmWhat is this skill?
- Integrates notebooklm-mcp-cli (`nlm`) for programmatic NotebookLM access
- Manage notebooks: create, list, rename, delete
- Add sources: URLs, text, files, YouTube, Google Drive
- Contextual queries and AI-synthesized retrieval from curated knowledge bases
- Studio outputs: audio podcasts, video explainers, reports, quizzes
- Five source types called out: URLs, text, files, YouTube, Google Drive
Adoption & trust: 933 installs on skills.sh; 271 GitHub stars; 1/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your project knowledge is scattered across docs and URLs, and your coding agent cannot ground answers in a curated NotebookLM corpus.
Who is it for?
Solo builders who maintain NotebookLM notebooks of specs, docs, or competitive research and want agent queries without manual copy-paste.
Skip if: Builders who need only one-off web search with no maintained notebook or who cannot install or auth the notebooklm-mcp-cli tool.
When should I use this skill?
User mentions notebooklm, nlm, notebook query, research notebook, or querying documentation in NotebookLM.
What do I get? / Deliverables
The agent runs `nlm` workflows to query notebooks, refresh sources, and return synthesized answers or studio artifacts grounded in your uploaded material.
- Notebook queries with grounded answers
- Updated notebooks and sources
- Studio artifacts (audio, reports, quizzes) when requested
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
NotebookLM is primarily agent-side RAG tooling—notebooks, sources, and CLI queries—so Build → Agent tooling is the primary shelf. The skill centers on notebooklm-mcp-cli integration (Bash/Read/Write), not shipping UI or backend product code.
Where it fits
Load competitor URLs into a notebook and ask contextual questions before picking a product angle.
Query a PRD notebook to confirm feature boundaries before prototyping.
Pull implementation details from an internal API notebook while coding integrations.
Generate a report or audio explainer from a marketing research notebook.
How it compares
Notebook-backed RAG via CLI—not the same as embedding files locally with a generic vector DB skill.
Common Questions / FAQ
Who is notebooklm for?
Indie developers using Claude Code, Cursor, or similar agents who already use or want Google NotebookLM as a documentation hub.
When should I use notebooklm?
While building agent tooling to query stored docs; during Idea/Validate research notebooks; when generating podcasts or reports from curated sources.
Is notebooklm safe to install?
It uses Bash and Google account-backed NotebookLM access—check the Security Audits panel on this page and scope notebook content to non-secret material.
SKILL.md
READMESKILL.md - Notebooklm
# NotebookLM Integration Interact with Google NotebookLM for advanced RAG capabilities — query project documentation, manage research sources, and retrieve AI-synthesized information from notebooks. ## Overview This skill integrates with the [notebooklm-mcp-cli](https://github.com/jacob-bd/notebooklm-mcp-cli) tool (`nlm` CLI) to provide programmatic access to Google NotebookLM. It enables agents to manage notebooks, add sources, perform contextual queries, and retrieve generated artifacts like audio podcasts or reports. ## When to Use Use this skill when: - Querying project documentation stored in Google NotebookLM - Retrieving AI-synthesized information from notebooks (e.g., summaries, Q&A) - Managing notebooks: creating, listing, renaming, or deleting - Adding sources to notebooks: URLs, text, files, YouTube, Google Drive - Generating studio content: audio podcasts, video explainers, reports, quizzes - Downloading generated artifacts (audio, video, reports, mind maps) - Performing research queries across web or Google Drive - Checking freshness and syncing Google Drive sources - An agent is tasked with using documentation stored in NotebookLM for implementation **Trigger phrases:** "query notebooklm", "search notebook", "add source to notebook", "create podcast from notebook", "generate report from notebook", "nlm query" ## Prerequisites ### Installation ```bash # Install via uv (recommended) uv tool install notebooklm-mcp-cli # Or via pip pip install notebooklm-mcp-cli # Verify installation nlm --version ``` ### Authentication ```bash # Login — opens Chrome for cookie extraction nlm login # Verify authentication nlm login --check # Use named profiles for multiple Google accounts nlm login --profile work nlm login --profile personal nlm login switch work ``` ### Diagnostics ```bash # Run diagnostics if issues occur nlm doctor nlm doctor --verbose ``` > **⚠️ Important:** This tool uses internal Google APIs. Cookies expire every ~2-4 weeks — run `nlm login` again when operations fail. Free tier has ~50 queries/day rate limit. ## Instructions ### Step 1: Verify Tool Availability Before performing any NotebookLM operation, verify the CLI is installed and authenticated: ```bash nlm --version && nlm login --check ``` If authentication has expired, inform the user they need to run `nlm login`. ### Step 2: Identify the Target Notebook List available notebooks or resolve an alias: ```bash # List all notebooks nlm notebook list # Use an alias if configured nlm alias get <alias-name> # Get notebook details nlm notebook get <notebook-id> ``` If the user references a notebook by name, use `nlm notebook list` to find the matching ID. If an alias exists, prefer using the alias. ### Step 3: Perform the Requested Operation #### Querying a Notebook Use this to retrieve information from notebook sources: ```bash # Ask a question against notebook sources nlm notebook query <notebook-id-or-alias> "What are the login requirements?" # The response contains AI-generated answers grounded in the notebook's sources ``` **Best practices for queries:** - Be specific and detailed in your questions - Reference particular topics or sections when possible - Use follow-up queries to drill deeper into specific areas #### Managing Sources ```bash # List current sources nlm source list <notebook-id> # Add a URL source (wait for processing) — only use UR