notebooklm

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

NotebookLM Research Assistant Skill

NotebookLM 研究助手技能

Interact with Google NotebookLM to query documentation with Gemini's source-grounded answers. Each question opens a fresh browser session, retrieves the answer exclusively from your uploaded documents, and closes.

与Google NotebookLM交互，查询文档并获得Gemini提供的有来源支撑的答案。每次提问都会打开一个全新的浏览器会话，仅从你上传的文档中检索答案后关闭会话。

When to Use This Skill

何时使用该技能

Trigger when user:

Mentions NotebookLM explicitly

Shares NotebookLM URL (

https://notebooklm.google.com/notebook/...

)

Asks to query their notebooks/documentation
Wants to add documentation to NotebookLM library
Uses phrases like "ask my NotebookLM", "check my docs", "query my notebook"

当用户出现以下行为时触发：

明确提到NotebookLM

分享NotebookLM链接（

https://notebooklm.google.com/notebook/...

）

要求查询自己的笔记本/文档
想要将文档添加到NotebookLM库中
使用类似“询问我的NotebookLM”、“检查我的文档”、“查询我的笔记本”这类表述

⚠️ CRITICAL: Add Command - Smart Discovery

⚠️ 关键要求：添加命令 - 智能发现

When user wants to add a notebook without providing details:

SMART ADD (Recommended): Query the notebook first to discover its content:

bash

undefined

当用户想要添加笔记本但未提供细节时：

智能添加（推荐）：先查询笔记本内容，自动识别相关信息：

bash

undefined

Step 1: Query the notebook about its content

步骤1：查询笔记本的内容信息

python scripts/run.py ask_question.py --question "What is the content of this notebook? What topics are covered? Provide a complete overview briefly and concisely" --notebook-url "[URL]"

Step 2: Use the discovered information to add it

步骤2：使用识别到的信息添加笔记本

python scripts/run.py notebook_manager.py add --url "[URL]" --name "[Based on content]" --description "[Based on content]" --topics "[Based on content]"


**MANUAL ADD**: If user provides all details:
- `--url` - The NotebookLM URL
- `--name` - A descriptive name
- `--description` - What the notebook contains (REQUIRED!)
- `--topics` - Comma-separated topics (REQUIRED!)

NEVER guess or use generic descriptions! If details missing, use Smart Add to discover them.

python scripts/run.py notebook_manager.py add --url "[URL]" --name "[基于内容生成]" --description "[基于内容生成]" --topics "[基于内容生成]"


**手动添加**：如果用户提供了所有信息：
- `--url` - NotebookLM链接
- `--name` - 描述性名称
- `--description` - 笔记本包含的内容（必填！）
- `--topics` - 英文逗号分隔的主题标签（必填！）

绝对不要猜测或使用通用描述！如果信息缺失，请使用智能添加功能自动识别。

Critical: Always Use run.py Wrapper

关键要求：始终使用run.py封装脚本

NEVER call scripts directly. ALWAYS use
python scripts/run.py [script]
:

bash

undefined

绝对不要直接调用脚本，始终使用
python scripts/run.py [脚本名称]
：

bash

undefined

✅ CORRECT - Always use run.py:

✅ 正确用法 - 始终使用run.py:

python scripts/run.py auth_manager.py status python scripts/run.py notebook_manager.py list python scripts/run.py ask_question.py --question "..."

❌ WRONG - Never call directly:

❌ 错误用法 - 不要直接调用:

python scripts/auth_manager.py status # Fails without venv!


The `run.py` wrapper automatically:
1. Creates `.venv` if needed
2. Installs all dependencies
3. Activates environment
4. Executes script properly

python scripts/auth_manager.py status # 没有虚拟环境会运行失败!


`run.py` 封装脚本会自动完成以下操作：
1. 必要时自动创建 `.venv` 虚拟环境
2. 安装所有依赖
3. 激活虚拟环境
4. 正确执行脚本

Core Workflow

核心工作流

Step 1: Check Authentication Status

步骤1：检查认证状态

bash

python scripts/run.py auth_manager.py status

If not authenticated, proceed to setup.

bash

python scripts/run.py auth_manager.py status

如果未认证，继续进行认证设置。

Step 2: Authenticate (One-Time Setup)

步骤2：认证（仅需首次设置）

bash

undefined

bash

undefined

Browser MUST be visible for manual Google login

浏览器必须可见，用于手动完成Google登录

python scripts/run.py auth_manager.py setup


**Important:**
- Browser is VISIBLE for authentication
- Browser window opens automatically
- User must manually log in to Google
- Tell user: "A browser window will open for Google login"

python scripts/run.py auth_manager.py setup


**重要说明：**
- 认证过程中浏览器是可见的
- 浏览器窗口会自动打开
- 用户需要手动完成Google账号登录
- 需要告知用户："将打开一个浏览器窗口用于Google登录"

Step 3: Manage Notebook Library

步骤3：管理笔记本库

bash

undefined

bash

undefined

List all notebooks

列出所有笔记本

python scripts/run.py notebook_manager.py list

BEFORE ADDING: Ask user for metadata if unknown!

添加前注意：如果不知道元数据，需要先询问用户!

"What does this notebook contain?"

"这个笔记本包含什么内容？"

"What topics should I tag it with?"

"我应该给它打上什么主题标签？"

Add notebook to library (ALL parameters are REQUIRED!)

添加笔记本到库中（所有参数均为必填项！）

python scripts/run.py notebook_manager.py add
--url "https://notebooklm.google.com/notebook/..."
--name "Descriptive Name"
--description "What this notebook contains" \ # REQUIRED - ASK USER IF UNKNOWN! --topics "topic1,topic2,topic3" # REQUIRED - ASK USER IF UNKNOWN!

python scripts/run.py notebook_manager.py add
--url "https://notebooklm.google.com/notebook/..."
--name "描述性名称"
--description "笔记本包含的内容" \ # 必填 - 未知时请询问用户! --topics "主题1,主题2,主题3" # 必填 - 未知时请询问用户!

Search notebooks by topic

按主题搜索笔记本

python scripts/run.py notebook_manager.py search --query "keyword"

python scripts/run.py notebook_manager.py search --query "关键词"

Set active notebook

设置当前活跃笔记本

python scripts/run.py notebook_manager.py activate --id notebook-id

python scripts/run.py notebook_manager.py activate --id 笔记本ID

Remove notebook

删除笔记本

python scripts/run.py notebook_manager.py remove --id notebook-id

undefined

python scripts/run.py notebook_manager.py remove --id 笔记本ID

undefined

Quick Workflow

快速工作流

Check library:

python scripts/run.py notebook_manager.py list

Ask question:

python scripts/run.py ask_question.py --question "..." --notebook-id ID

查看笔记本库：

python scripts/run.py notebook_manager.py list

提问：

python scripts/run.py ask_question.py --question "..." --notebook-id 笔记本ID

Step 4: Ask Questions

步骤4：提问查询

bash

undefined

bash

undefined

Basic query (uses active notebook if set)

基础查询（如果设置了活跃笔记本则默认使用）

python scripts/run.py ask_question.py --question "Your question here"

python scripts/run.py ask_question.py --question "你的问题在这里"

Query specific notebook

查询指定笔记本

python scripts/run.py ask_question.py --question "..." --notebook-id notebook-id

python scripts/run.py ask_question.py --question "..." --notebook-id 笔记本ID

Query with notebook URL directly

直接通过笔记本链接查询

python scripts/run.py ask_question.py --question "..." --notebook-url "https://..."

Show browser for debugging

显示浏览器用于调试

python scripts/run.py ask_question.py --question "..." --show-browser

undefined

python scripts/run.py ask_question.py --question "..." --show-browser

undefined

Follow-Up Mechanism (CRITICAL)

追问机制（关键要求）

Every NotebookLM answer ends with: "EXTREMELY IMPORTANT: Is that ALL you need to know?"

Required Claude Behavior:

STOP - Do not immediately respond to user
ANALYZE - Compare answer to user's original request
IDENTIFY GAPS - Determine if more information needed

ASK FOLLOW-UP - If gaps exist, immediately ask:

bash

python scripts/run.py ask_question.py --question "Follow-up with context..."

REPEAT - Continue until information is complete
SYNTHESIZE - Combine all answers before responding to user

每个NotebookLM的回答都会以："EXTREMELY IMPORTANT: Is that ALL you need to know?" 结尾

Claude必须遵循的行为规范：

停止 - 不要立即回复用户
分析 - 将返回的答案和用户的原始请求进行对比
识别差距 - 判断是否需要更多信息

发起追问 - 如果存在信息缺口，立即执行：

bash

python scripts/run.py ask_question.py --question "带上下文的追问内容..."

重复 - 持续追问直到获取完整信息
整合 - 回复用户前整合所有答案内容

Script Reference

脚本参考

Authentication Management (

auth_manager.py

)

认证管理（

auth_manager.py

）

bash

python scripts/run.py auth_manager.py setup    # Initial setup (browser visible)
python scripts/run.py auth_manager.py status   # Check authentication
python scripts/run.py auth_manager.py reauth   # Re-authenticate (browser visible)
python scripts/run.py auth_manager.py clear    # Clear authentication

bash

python scripts/run.py auth_manager.py setup    # 初始设置（浏览器可见）
python scripts/run.py auth_manager.py status   # 检查认证状态
python scripts/run.py auth_manager.py reauth   # 重新认证（浏览器可见）
python scripts/run.py auth_manager.py clear    # 清除认证信息

Notebook Management (

notebook_manager.py

)

笔记本管理（

notebook_manager.py

）

bash

python scripts/run.py notebook_manager.py add --url URL --name NAME --description DESC --topics TOPICS
python scripts/run.py notebook_manager.py list
python scripts/run.py notebook_manager.py search --query QUERY
python scripts/run.py notebook_manager.py activate --id ID
python scripts/run.py notebook_manager.py remove --id ID
python scripts/run.py notebook_manager.py stats

bash

python scripts/run.py notebook_manager.py add --url URL --name NAME --description DESC --topics TOPICS
python scripts/run.py notebook_manager.py list
python scripts/run.py notebook_manager.py search --query QUERY
python scripts/run.py notebook_manager.py activate --id ID
python scripts/run.py notebook_manager.py remove --id ID
python scripts/run.py notebook_manager.py stats

Question Interface (

ask_question.py

)

提问接口（

ask_question.py

）

bash

python scripts/run.py ask_question.py --question "..." [--notebook-id ID] [--notebook-url URL] [--show-browser]

bash

python scripts/run.py ask_question.py --question "..." [--notebook-id ID] [--notebook-url URL] [--show-browser]

Data Cleanup (

cleanup_manager.py

)

数据清理（

cleanup_manager.py

）

bash

python scripts/run.py cleanup_manager.py                    # Preview cleanup
python scripts/run.py cleanup_manager.py --confirm          # Execute cleanup
python scripts/run.py cleanup_manager.py --preserve-library # Keep notebooks

bash

python scripts/run.py cleanup_manager.py                    # 预览清理内容
python scripts/run.py cleanup_manager.py --confirm          # 执行清理
python scripts/run.py cleanup_manager.py --preserve-library # 保留笔记本库

Environment Management

环境管理

The virtual environment is automatically managed:

First run creates
```
.venv
```
automatically
Dependencies install automatically
Chromium browser installs automatically
Everything isolated in skill directory

Manual setup (only if automatic fails):

bash

python -m venv .venv
source .venv/bin/activate  # Linux/Mac
pip install -r requirements.txt
python -m patchright install chromium

虚拟环境会自动管理：

首次运行会自动创建
```
.venv
```
自动安装所有依赖
自动安装Chromium浏览器
所有内容都隔离在技能目录下

手动设置（仅自动安装失败时使用）：

bash

python -m venv .venv
source .venv/bin/activate  # Linux/Mac系统
pip install -r requirements.txt
python -m patchright install chromium

Data Storage

数据存储

All data stored in

~/.claude/skills/notebooklm/data/

```
library.json
```
- Notebook metadata
```
auth_info.json
```
- Authentication status
```
browser_state/
```
- Browser cookies and session

Security: Protected by

.gitignore

, never commit to git.

所有数据存储在

~/.claude/skills/notebooklm/data/

路径下：

```
library.json
```
- 笔记本元数据
```
auth_info.json
```
- 认证状态
```
browser_state/
```
- 浏览器Cookie和会话信息

安全说明： 已通过

.gitignore

保护，永远不会提交到git。

Configuration

配置

Optional

.env

file in skill directory:

env

HEADLESS=false           # Browser visibility
SHOW_BROWSER=false       # Default browser display
STEALTH_ENABLED=true     # Human-like behavior
TYPING_WPM_MIN=160       # Typing speed
TYPING_WPM_MAX=240
DEFAULT_NOTEBOOK_ID=     # Default notebook

可在技能目录下添加可选的

.env

文件：

env

HEADLESS=false           # 浏览器可见性设置
SHOW_BROWSER=false       # 默认浏览器显示设置
STEALTH_ENABLED=true     # 模拟人类行为
TYPING_WPM_MIN=160       # 打字速度下限
TYPING_WPM_MAX=240
DEFAULT_NOTEBOOK_ID=     # 默认笔记本ID

Decision Flow

决策流程

User mentions NotebookLM
    ↓
Check auth → python scripts/run.py auth_manager.py status
    ↓
If not authenticated → python scripts/run.py auth_manager.py setup
    ↓
Check/Add notebook → python scripts/run.py notebook_manager.py list/add (with --description)
    ↓
Activate notebook → python scripts/run.py notebook_manager.py activate --id ID
    ↓
Ask question → python scripts/run.py ask_question.py --question "..."
    ↓
See "Is that ALL you need?" → Ask follow-ups until complete
    ↓
Synthesize and respond to user

用户提到NotebookLM
    ↓
检查认证 → python scripts/run.py auth_manager.py status
    ↓
未认证 → python scripts/run.py auth_manager.py setup
    ↓
检查/添加笔记本 → python scripts/run.py notebook_manager.py list/add（带--description参数）
    ↓
激活笔记本 → python scripts/run.py notebook_manager.py activate --id ID
    ↓
提问 → python scripts/run.py ask_question.py --question "..."
    ↓
看到"Is that ALL you need?"提示 → 持续追问直到信息完整
    ↓
整合答案后回复用户

Troubleshooting

故障排查

Problem	Solution
ModuleNotFoundError	Use `run.py` wrapper
Authentication fails	Browser must be visible for setup! --show-browser
Rate limit (50/day)	Wait or switch Google account
Browser crashes	`python scripts/run.py cleanup_manager.py --preserve-library`
Notebook not found	Check with `notebook_manager.py list`

问题	解决方案
ModuleNotFoundError	使用 `run.py` 封装脚本
认证失败	认证设置过程中浏览器必须可见！添加--show-browser参数
速率限制（每天50次）	等待后重试或切换Google账号
浏览器崩溃	执行 `python scripts/run.py cleanup_manager.py --preserve-library`
找不到笔记本	使用 `notebook_manager.py list` 命令检查

Best Practices

最佳实践

Always use run.py - Handles environment automatically
Check auth first - Before any operations
Follow-up questions - Don't stop at first answer
Browser visible for auth - Required for manual login
Include context - Each question is independent
Synthesize answers - Combine multiple responses

始终使用run.py - 自动处理环境配置
优先检查认证状态 - 执行任何操作前先确认认证
及时追问 - 不要停留在第一个答案
认证时保持浏览器可见 - 手动登录需要可见窗口
携带上下文 - 每个提问都是独立会话
整合答案 - 合并多轮返回结果再回复用户

Limitations

限制说明

No session persistence (each question = new browser)
Rate limits on free Google accounts (50 queries/day)
Manual upload required (user must add docs to NotebookLM)
Browser overhead (few seconds per question)

无会话持久化（每次提问都是全新浏览器会话）
免费Google账号有速率限制（每天最多50次查询）
需要用户手动上传文档到NotebookLM
浏览器有启动开销（每次提问需要几秒加载时间）

Resources (Skill Structure)

资源（技能结构）

Important directories and files:

```
scripts/
```
- All automation scripts (ask_question.py, notebook_manager.py, etc.)
```
data/
```
- Local storage for authentication and notebook library
```
references/
```
- Extended documentation:
- ```
api_reference.md
```
  - Detailed API documentation for all scripts
- ```
troubleshooting.md
```
  - Common issues and solutions
- ```
usage_patterns.md
```
  - Best practices and workflow examples
```
.venv/
```
- Isolated Python environment (auto-created on first run)
```
.gitignore
```
- Protects sensitive data from being committed

重要目录和文件：

```
scripts/
```
- 所有自动化脚本（ask_question.py、notebook_manager.py等）
```
data/
```
- 认证信息和笔记本库的本地存储
```
references/
```
- 扩展文档：
- ```
api_reference.md
```
  - 所有脚本的详细API文档
- ```
troubleshooting.md
```
  - 常见问题和解决方案
- ```
usage_patterns.md
```
  - 最佳实践和工作流示例
```
.venv/
```
- 隔离Python虚拟环境（首次运行自动创建）
```
.gitignore
```
- 防止敏感数据被提交到git

notebooklm

Original

Translation

NotebookLM Research Assistant Skill

NotebookLM 研究助手技能

When to Use This Skill

何时使用该技能

⚠️ CRITICAL: Add Command - Smart Discovery

⚠️ 关键要求：添加命令 - 智能发现

Step 1: Query the notebook about its content

步骤1：查询笔记本的内容信息

Step 2: Use the discovered information to add it

步骤2：使用识别到的信息添加笔记本

Critical: Always Use run.py Wrapper

关键要求：始终使用run.py封装脚本

✅ CORRECT - Always use run.py:

✅ 正确用法 - 始终使用run.py:

❌ WRONG - Never call directly:

❌ 错误用法 - 不要直接调用:

Core Workflow

核心工作流

Step 1: Check Authentication Status

步骤1：检查认证状态

Step 2: Authenticate (One-Time Setup)

步骤2：认证（仅需首次设置）

Browser MUST be visible for manual Google login

浏览器必须可见，用于手动完成Google登录

Step 3: Manage Notebook Library

步骤3：管理笔记本库

List all notebooks

列出所有笔记本

BEFORE ADDING: Ask user for metadata if unknown!

添加前注意：如果不知道元数据，需要先询问用户!

"What does this notebook contain?"

"这个笔记本包含什么内容？"

"What topics should I tag it with?"

"我应该给它打上什么主题标签？"

Add notebook to library (ALL parameters are REQUIRED!)

添加笔记本到库中（所有参数均为必填项！）

Search notebooks by topic

按主题搜索笔记本

Set active notebook

设置当前活跃笔记本

Remove notebook

删除笔记本

Quick Workflow

快速工作流

Step 4: Ask Questions

步骤4：提问查询

Basic query (uses active notebook if set)

基础查询（如果设置了活跃笔记本则默认使用）

Query specific notebook

查询指定笔记本

Query with notebook URL directly

直接通过笔记本链接查询

Show browser for debugging

显示浏览器用于调试

Follow-Up Mechanism (CRITICAL)

追问机制（关键要求）

Script Reference

脚本参考

Authentication Management (auth_manager.py)

认证管理（auth_manager.py）

Notebook Management (notebook_manager.py)

笔记本管理（notebook_manager.py）

Question Interface (ask_question.py)

提问接口（ask_question.py）

Data Cleanup (cleanup_manager.py)

数据清理（cleanup_manager.py）

Environment Management

环境管理

Data Storage

数据存储

Configuration

配置

Decision Flow

决策流程

Troubleshooting

故障排查

Best Practices

Authentication Management (
`auth_manager.py`
)

认证管理（
`auth_manager.py`
）

Notebook Management (
`notebook_manager.py`
)

笔记本管理（
`notebook_manager.py`
）

Question Interface (
`ask_question.py`
)

提问接口（
`ask_question.py`
）

Data Cleanup (
`cleanup_manager.py`
)

数据清理（
`cleanup_manager.py`
）