相关职业SOC
基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/thirdlf03/ccpeek --skill notebooklm-query命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | notebooklm-query |
| description | Access NotebookLM to ask questions and retrieve information. Specify a NotebookLM URL and query. |
| argument-hint | <NotebookLM URL> <question or research topic> |
| allowed-tools | ["mcp__claude-in-chrome__tabs_context_mcp","mcp__claude-in-chrome__tabs_create_mcp","mcp__claude-in-chrome__navigate","mcp__claude-in-chrome__computer","mcp__claude-in-chrome__read_page","mcp__claude-in-chrome__find","mcp__claude-in-chrome__form_input","mcp__claude-in-chrome__javascript_tool","mcp__claude-in-chrome__get_page_text","Read","Glob","Grep","AskUserQuestion"] |
Access a NotebookLM notebook, ask questions via chat, and retrieve information.
The user provides:
https://notebooklm.google.com/notebook/xxxx)If arguments are missing, use AskUserQuestion to clarify.
tabs_context_mcp to get tab infotabs_create_mcp to create a new tab and navigate to the URLscreenshot to check the page stateCraft an effective question from the user's research topic and send it to NotebookLM.
find to locate the chat input fieldform_input to type the question textfind to locate the "Send" button and click the one near the chat input
screenshot to confirm the response is displayedjavascript_tool to extract the response text:
const chatArea = document.querySelector('[role="log"], [class*="chat"], [class*="conversation"]');
if (chatArea) {
const text = chatArea.innerText;
const lastQ = text.lastIndexOf('<partial question text>');
if (lastQ >= 0) text.substring(lastQ, lastQ + 5000);
}
Present the retrieved information in this format:
## NotebookLM Research Results
### Source
- Notebook: [Title](URL)
- Sources: N items
### Q1: <question>
<response summary>
### Q2: <question>
<response summary>
### Key Takeaways
- Point 1
- Point 2
- ...
javascript_tool with varying offsets for multiple retrieval passestabs_context_mcp and re-access in a new tabread_page to list interactive elements and identify the buttonPerform a comprehensive code quality review
TypeScript and Next.js coding standards. Auto-triggered when writing, reviewing, or refactoring TypeScript/React code. Covers type patterns, component patterns, Biome rules, and import conventions.
React and Next.js frontend design patterns. Auto-triggered when creating React components, implementing data fetching, managing state, or optimizing performance. Covers Server Components, Suspense, streaming, and rendering.