← ClaudeAtlas

notebooklm-managerlisted

This skill should be used when the user wants to interact with NotebookLM notebooks via Claude Code's Chrome integration. Trigger phrases: "Query my NotebookLM", "Ask my notebook about X", "query [id] about X", "list my notebooks", "add notebook URL", "show notebook details", "search notebooks for X", "Check my docs", "what does my [topic] notebook say about", "remove notebook", "delete notebook", "disable notebook", "enable notebook". Also triggers when user: (1) mentions NotebookLM explicitly, (2) shares NotebookLM URL (https://notebooklm.google.com/notebook/...). Do NOT use for: general web searches, local file reading, or non-NotebookLM documentation queries. Requires: claude --chrome with claude-in-chrome MCP.
aiskillstore/marketplace · ★ 329 · Data & Documents · score 82
Install: claude install-skill aiskillstore/marketplace
# NotebookLM Manager Query orchestration and notebook registry management. ## Instructions ### CRITICAL CONSTRAINT This skill MUST NOT call any `mcp__claude-in-chrome__*` tools. These tools DO NOT EXIST in this skill's allowed tool set. All Chrome interaction is delegated to the agent via Task. After receiving an agent error, do NOT attempt to use Chrome tools yourself. ### 1. Query Detection Extract from user message: - `notebook_id`: Which notebook (e.g., "claude-docs") - `question`: What to ask ### 2. Notebook Lookup Read `${SKILL_ROOT}/data/library.json` to find notebook URL. - **File not found → Create `data/` folder and files with `[]`** - Not found → Show "Did you mean?" with similar IDs ### 3. Chat History Confirmation (First Query Only) **Before the first query to a notebook**, ask user about chat history: ``` AskUserQuestion({ questions: [{ question: "Clear NotebookLM chat history before querying?", header: "History", options: [ { label: "No (Recommended)", description: "Keep previous context, faster response" }, { label: "Yes", description: "Start fresh, may involve UI modal interaction" } ], multiSelect: false }] }) ``` Pass result to agent as `clearHistory: true/false` in the prompt. **Note**: Clearing history may trigger a confirmation modal in NotebookLM, which can slow down automation. Default "No" is recommended. Track per-notebook first-query status within the current conversation. After asking once for a give