Use when analyzing sources with NotebookLM, creating research notebooks, or generating audio overviews and study materials. Triggers on NotebookLM, create notebook, add sources to notebook, ask NotebookLM, notebook question, synthesize sources, audio overview, podcast summary, generate infographic, mind map, study guide, FAQ generation, briefing document, NotebookLM MCP, research notebook, source analysis, multi-source synthesis, notebook deliverable.
From george-setupnpx claudepluginhub george11642/george-plugins --plugin george-setupThis skill uses the workspace's default tool permissions.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Deep research and analysis via NotebookLM MCP (lazy-loaded via ToolSearch).
ToolSearch: +notebooklm
| Task | Tool |
|---|---|
| Create notebook | mcp__notebooklm__add_notebook |
| Select notebook | mcp__notebooklm__select_notebook |
| Get details | mcp__notebooklm__get_notebook |
| Ask question | mcp__notebooklm__ask_question |
| List notebooks | mcp__notebooklm__list_notebooks |
| Search notebooks | mcp__notebooklm__search_notebooks |
| Update sources | mcp__notebooklm__update_notebook |
| Remove notebook | mcp__notebooklm__remove_notebook |
| Cleanup data | mcp__notebooklm__cleanup_data |
| Health check | mcp__notebooklm__get_health |
| Session mgmt | list_sessions, close_session, reset_session |
| Auth | mcp__notebooklm__setup_auth, mcp__notebooklm__re_auth |
list_notebooks -> check for existing match
add_notebook(title="Topic Name", sources=[url1, url2, ...])
Sources: YouTube URLs (https://youtube.com/watch?v=...), web URLs, or raw text. Up to 50 per notebook.
Ask specific, focused questions:
ask_question("What are the key themes across these sources?")
ask_question("What topics get the most engagement and why?")
ask_question("What content gaps exist that aren't covered?")
ask_question("What are the main takeaways for someone new to this?")
Use ask_question with clear requests:
Visual deliverables (infographic, mind map) can take 5-15 minutes.
Summarize analysis clearly. Include any links or content NotebookLM returned.
cleanup_data to remove stale notebooks periodicallyIf NotebookLM returns auth errors:
mcp__notebooklm__re_auth firstmcp__notebooklm__setup_auth for fresh setupmcp__notebooklm__get_health for service status