notebooklm-patterns
Facilitates interaction with NotebookLM through RPC tools for research and content generation.
Install
mkdir -p .claude/skills/notebooklm-patterns && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18682" && unzip -o skill.zip -d .claude/skills/notebooklm-patterns && rm skill.zipInstalls to .claude/skills/notebooklm-patterns
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
NotebookLM integration patterns aligned to notebooklm-mcp (RPC tool names, auth flow, and troubleshooting). Use when listing/creating/querying notebooks, managing sources, running research, or generating studio artifacts.Key capabilities
- →Authenticate with NotebookLM using cookies
- →List, create, get, rename, and delete notebooks
- →Add URLs, text, or Drive files as sources
- →Start and check research status
- →Generate audio and video overviews
- →Create infographics and slide decks
How it works
The skill provides RPC tool names for NotebookLM operations, handles cookie-based authentication, and outlines workflows for querying and generating artifacts.
Inputs & outputs
When to use notebooklm-patterns
- →Querying notebook sources
- →Generating audio/video overviews
- →Managing research notebook lifecycles
About this skill
NotebookLM Codex Skill (RPC)
Provide a reliable, repeatable workflow to authenticate with NotebookLM and automate queries using notebooklm-mcp.
Tool Reference (RPC)
Authentication
mcp__notebooklm-rpc__save_auth_tokens
Notebooks
mcp__notebooklm-rpc__notebook_listmcp__notebooklm-rpc__notebook_createmcp__notebooklm-rpc__notebook_getmcp__notebooklm-rpc__notebook_describemcp__notebooklm-rpc__notebook_renamemcp__notebooklm-rpc__notebook_deletemcp__notebooklm-rpc__notebook_query
Sources
mcp__notebooklm-rpc__notebook_add_urlmcp__notebooklm-rpc__notebook_add_textmcp__notebooklm-rpc__notebook_add_drivemcp__notebooklm-rpc__source_list_drivemcp__notebooklm-rpc__source_sync_drivemcp__notebooklm-rpc__source_deletemcp__notebooklm-rpc__source_describe
Research
mcp__notebooklm-rpc__research_startmcp__notebooklm-rpc__research_statusmcp__notebooklm-rpc__research_import
Chat Configuration
mcp__notebooklm-rpc__chat_configure
Studio
mcp__notebooklm-rpc__audio_overview_createmcp__notebooklm-rpc__video_overview_createmcp__notebooklm-rpc__infographic_createmcp__notebooklm-rpc__slide_deck_createmcp__notebooklm-rpc__studio_statusmcp__notebooklm-rpc__studio_delete
If tools are missing, ask the user to run pixi run mcp-install-code and ensure cookies are saved via notebooklm-mcp-auth + save_auth_tokens.
Authentication Workflow
NotebookLM has no public API; authentication is cookie-based:
- Run
notebooklm-mcp-authand complete Google login. - Call
save_auth_tokensto persist cookies to~/.notebooklm-mcp/auth.json. - Retry NotebookLM RPC tools.
Core Query Workflow
- List notebooks:
notebook_list. - Ask a question:
notebook_querywithnotebook_id+question. - For follow-ups, pass
session_idfrom the prior response.
Multi-Notebook Query
notebook_listto get IDs.- Query each notebook via
notebook_querywith the same question. - Aggregate responses labeled by notebook name/ID and citations.
Notes:
- Retry a timed-out query once; then record a timeout and continue.
- Avoid shared mutable state; always use
notebook_idexplicitly.
Research-First Behavior
Always query NotebookLM first and cite sources before making code changes. Prefer concise, citation-backed summaries.
Reliability Tips
- If answers drift, retry once with a narrower prompt.
- Re-run
notebooklm-mcp-authwhen cookies expire. - Keep notebooks domain-specific to reduce off-topic answers.
When not to use it
- →When not interacting with NotebookLM
- →When a public API is available for NotebookLM
- →When not using `notebooklm-mcp` for RPC calls
Limitations
- →NotebookLM has no public API; authentication is cookie-based
- →Requires `notebooklm-mcp` for RPC tool execution
- →Queries are subject to NotebookLM's internal processing capabilities
How it compares
This skill provides a structured RPC interface and authentication workflow for NotebookLM, unlike manual interaction with the web interface.
Compared to similar skills
notebooklm-patterns side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| notebooklm-patterns (this skill) | 0 | 6mo | No flags | Intermediate |
| weekend-learning | 0 | 5mo | Review | Intermediate |
| ailey-tools-tag-n-rag | 0 | 5mo | Review | Intermediate |
| literature-review | 559 | 1mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by ray-manaloto
View all by ray-manaloto →You might also like
weekend-learning
IgorGanapolsky
Weekend auto-learning from YouTube transcripts, Phil Town content, trade analysis
ailey-tools-tag-n-rag
armoin2018
Process and index content from files, folders, Git repos, or URLs into tagged RAG (Retrieval Augmented Generation) sets with ChromaDB. Supports text, markdown, video/audio transcription, OCR, intelligent chunking, and metadata tagging. Use when preparing content for AI retrieval, building knowledge
literature-review
K-Dense-AI
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
openalex-database
davila7
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.
market-research-reports
davila7
Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for data gathering, and multi-framework strategic analysis including Porter's Five Forces, PESTLE, SWOT, TAM/SAM/SOM, and BCG Matrix.
scientific-brainstorming
davila7
Research ideation partner. Generate hypotheses, explore interdisciplinary connections, challenge assumptions, develop methodologies, identify research gaps, for creative scientific problem-solving.