Nlm Skill
Expert guide for NotebookLM CLI and MCP server automation
What You Can Do
You can interact with NotebookLM programmatically to automate research workflows, content generation, and knowledge management tasks. This skill guides you through creating and managing notebooks, adding diverse source types (URLs, YouTube videos, PDFs, Google Drive files, text), generating multiple content formats (podcasts, reports, quizzes, flashcards, mind maps, slides, infographics), and conducting intelligent research through source-aware chat interactions.
Features
create, list, delete, and organize NotebookLM projects via CLI or MCP
add URLs, YouTube videos, PDFs, Google Drive files, and text snippets to notebooks
produce podcasts (Audio Overviews), reports, quizzes, flashcards, mind maps, slides, infographics, and videos
query and analyze your notebook sources with context-aware responses
streamline research workflows by automating source collection and content synthesis
chain commands to automate complex NotebookLM tasks programmatically
use either nlm CLI or MCP tools based on your environment and preferences
Example Output
Creating a research notebook and generating a podcast:
User: "Create a notebook about AI safety, add these three sources, and generate a podcast"
Skill output:
- Notebook created: "AI Safety Research" (ID: abc123)
- Sources added: 3 URLs processed
- Podcast generation initiated: Audio Overview ready for playback
Generating multiple content formats from a notebook:
User: "Generate a quiz, mind map, and infographic from my marketing research notebook"
Skill output:
- Quiz created: 10 questions with answer key
- Mind map generated: Visual hierarchy of key concepts
- Infographic created: Data visualization ready for export
What's Included
- SKILL.md: comprehensive guide for nlm CLI commands and MCP tool integration
- CLI Command Reference: complete syntax for notebook, source, and content generation operations
- MCP Tool Documentation: parameter guides and integration examples
- Workflow Automation Templates: ready-to-use command sequences for common research and content tasks
- Troubleshooting Guide: solutions for tool availability detection and authentication issues
Who It's For
- Research analysts automating literature reviews and source analysis
- Content creators generating multi-format educational materials and podcasts
- Knowledge workers building automated research and synthesis workflows
- Developers building NotebookLM integrations into larger applications
- Academic and corporate teams scaling knowledge management processes
Best For
- Automating notebook creation and source management workflows
- Batch generating content (podcasts, reports, quizzes) from source collections
- Building research pipelines that ingest and synthesize diverse information sources
- Integrating NotebookLM capabilities into CLI tools or applications
- Orchestrating complex multi-step content generation and knowledge extraction tasks
You might also like
When a user uploads a file to Claude, you can intelligently detect its type and read it using the appropriate method. Instead of blindly running cat on binary files or loading massive CSVs into context, this skill routes each file type to the right tool, reading only what's needed to answer the user's question. You'll extract text from PDFs, parse structured data from CSVs and JSON, process images, and decompress archives—all without wasting context or producing garbage output.
by seifbenayed
This skill transforms your press story into a compelling media pitch tailored to specific journalists and publications. You input your newsworthy angle, target beat, and key message, and receive a personalized pitch email with multiple subject line variants, a narratively structured body that leads with the news hook, and customized talking points that resonate with beat journalists. The skill also generates follow-up strategies and objection-handling language to maximize your pitch's impact.
You can rapidly analyze subsidiary rights contracts to uncover licensing gaps, overlooked revenue opportunities, and negotiation vulnerabilities. The skill generates detailed insights on international editions, film adaptations, audio rights, translation licenses, and merchandising clauses, plus actionable negotiation strategies tailored to your specific deal.
You can draft contextually appropriate Zendesk ticket responses, automatically categorize incoming tickets by type and urgency, and analyze response quality to boost resolution rates and CSAT scores. Claude learns your team's communication style and knowledge base, delivering responses that sound authentic while maintaining consistency across your support team.
You can compose polished, empathetic customer support responses directly within Intercom by analyzing customer sentiment to adjust your tone appropriately. The skill evaluates draft responses for clarity, professionalism, and problem-solving effectiveness, helping you maintain consistent voice while accelerating response time through intelligent templating.
Systematically evaluate speaker proposals using customizable weighted criteria, automatically identifying imbalanced content tracks and recommending selections. Generate personalized, professional acceptance and rejection feedback that provides constructive guidance to speakers, helping your conference committee make consistent, data-driven decisions while reducing manual review time.
Map complete attendee journeys from arrival to departure, identifying emotional peaks and operational touchpoints. Coordinate multi-vendor timelines to ensure seamless transitions and eliminate bottlenecks. Create detailed moment-to-moment experience scripts that balance emotional resonance with practical logistics.
Query your local Screenpipe instance to retrieve screen recordings, audio transcriptions, UI element accessibility trees, keyboard/mouse input logs, and productivity analytics. You can search by keywords, filter by content type (audio, OCR, accessibility, input), set time ranges, and extract structured data about your applications, meetings, and work sessions without sending data to external servers.
by az9713