nlm-skill

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

NotebookLM CLI & MCP Expert

NotebookLM CLI & MCP 专家指南

This skill provides comprehensive guidance for using NotebookLM via both the

nlm

CLI and MCP tools.

本技能提供通过

nlm

CLI和MCP工具使用NotebookLM的全面指导。

Tool Detection (CRITICAL - Read First!)

工具检测（关键内容 - 请先阅读！）

ALWAYS check which tools are available before proceeding:

Check for MCP tools: Look for tools starting with
```
mcp__notebooklm-mcp__*
```
or
```
mcp_notebooklm_*
```
If BOTH MCP tools AND CLI are available: ASK the user which they prefer to use before proceeding
If only MCP tools are available: Use them directly (refer to tool docstrings for parameters)
If only CLI is available: Use
```
nlm
```
CLI commands via Bash

Decision Logic:

has_mcp_tools = check_available_tools()  # Look for mcp__notebooklm-mcp__* or mcp_notebooklm_*
has_cli = check_bash_available()  # Can run nlm commands

if has_mcp_tools and has_cli:
    # ASK USER: "I can use either MCP tools or the nlm CLI. Which do you prefer?"
    user_preference = ask_user()
else if has_mcp_tools:
    # Use MCP tools directly
    mcp__notebooklm-mcp__notebook_list()
else:
    # Use CLI via Bash
    bash("nlm notebook list")

This skill documents BOTH approaches. Choose the appropriate one based on tool availability and user preference.

操作前请务必先检查可用的工具：

检查MCP工具：查找以
```
mcp__notebooklm-mcp__*
```
或
```
mcp_notebooklm_*
```
开头的工具
如果同时有MCP工具和CLI可用：操作前询问用户偏好使用哪种方式
如果只有MCP工具可用：直接使用（参数参考工具文档字符串）
如果只有CLI可用：通过Bash执行
```
nlm
```
CLI命令

决策逻辑：

has_mcp_tools = check_available_tools()  # Look for mcp__notebooklm-mcp__* or mcp_notebooklm_*
has_cli = check_bash_available()  # Can run nlm commands

if has_mcp_tools and has_cli:
    # ASK USER: "I can use either MCP tools or the nlm CLI. Which do you prefer?"
    user_preference = ask_user()
else if has_mcp_tools:
    # Use MCP tools directly
    mcp__notebooklm-mcp__notebook_list()
else:
    # Use CLI via Bash
    bash("nlm notebook list")

本技能同时记录了两种使用方式，请根据工具可用性和用户偏好选择合适的方案。

Quick Reference

快速参考

Run
nlm --ai
to get comprehensive AI-optimized documentation - this provides a complete view of all CLI capabilities.

bash

nlm --help              # List all commands
nlm <command> --help    # Help for specific command
nlm --ai                # Full AI-optimized documentation (RECOMMENDED)
nlm --version           # Check installed version

执行
nlm --ai
获取AI优化的完整文档 - 可以查看所有CLI能力的完整说明。

bash

nlm --help              # 列出所有命令
nlm <command> --help    # 查看特定命令的帮助信息
nlm --ai                # AI优化的完整文档（推荐）
nlm --version           # 检查安装版本

Critical Rules (Read First!)

核心规则（请先阅读！）

Always authenticate first: Run
```
nlm login
```
before any operations
Sessions expire in ~20 minutes: Re-run
```
nlm login
```
if commands start failing
⚠️ ALWAYS ASK USER BEFORE DELETE: Before executing ANY delete command, ask the user for explicit confirmation. Deletions are irreversible. Show what will be deleted and warn about permanent data loss.
--confirm
is REQUIRED: All generation and delete commands need
```
--confirm
```
or
```
-y
```
(CLI) or
```
confirm=True
```
(MCP)
Research requires
--notebook-id
: The flag is mandatory, not positional
Capture IDs from output: Create/start commands return IDs needed for subsequent operations
Use aliases: Simplify long UUIDs with
```
nlm alias set <name> <uuid>
```
Check aliases before creating: Run
```
nlm alias list
```
before creating a new alias to avoid conflicts with existing names.
DO NOT launch REPL: Never use
```
nlm chat start
```
- it opens an interactive REPL that AI tools cannot control. Use
```
nlm notebook query
```
for one-shot Q&A instead.
Choose output format wisely: Default output (no flags) is compact and token-efficient—use it for status checks. Use
```
--quiet
```
to capture IDs for piping. Only use
```
--json
```
when you need to parse specific fields programmatically.
Use
--help
when unsure: Run
```
nlm <command> --help
```
to see available options and flags for any command.

始终先完成身份认证：执行任何操作前先运行
```
nlm login
```
会话有效期约20分钟：如果命令执行失败，请重新运行
```
nlm login
```
⚠️ 删除操作前必须询问用户：执行任何删除命令前，必须获得用户的明确确认。删除操作不可撤销，请告知用户将删除的内容并警告永久数据丢失风险。
--confirm
为必填参数：所有生成和删除命令都需要添加
```
--confirm
```
或
```
-y
```
（CLI）或
```
confirm=True
```
（MCP）
调研功能需要
--notebook-id
参数：该标志是必填项，不是位置参数
从输出中捕获ID：创建/启动命令会返回后续操作需要的ID
使用别名：通过
```
nlm alias set <name> <uuid>
```
简化过长的UUID
创建别名前先检查：创建新别名前运行
```
nlm alias list
```
避免与现有名称冲突
不要启动REPL：禁止使用
```
nlm chat start
```
，它会打开AI工具无法控制的交互式REPL，请使用
```
nlm notebook query
```
进行单轮问答
合理选择输出格式：默认输出（无标志）紧凑且节省token，适用于状态检查。使用
```
--quiet
```
捕获ID用于管道操作。仅当你需要程序化解析特定字段时才使用
```
--json
```
不确定时使用
--help
：运行
```
nlm <command> --help
```
查看任意命令的可用选项和标志

Workflow Decision Tree

工作流决策树

Use this to determine the right sequence of commands:

User wants to...
│
├─► Work with NotebookLM for the first time
│   └─► nlm login → nlm notebook create "Title"
│
├─► Add content to a notebook
│   ├─► From a URL/webpage → nlm source add <nb-id> --url "https://..."
│   ├─► From YouTube → nlm source add <nb-id> --url "https://youtube.com/..."
│   ├─► From pasted text → nlm source add <nb-id> --text "content" --title "Title"
│   ├─► From Google Drive → nlm source add <nb-id> --drive <doc-id> --type doc
│   └─► Discover new sources → nlm research start "query" --notebook-id <nb-id>
│
├─► Generate content from sources
│   ├─► Podcast/Audio → nlm audio create <nb-id> --confirm
│   ├─► Written summary → nlm report create <nb-id> --confirm
│   ├─► Study materials → nlm quiz/flashcards create <nb-id> --confirm
│   ├─► Visual content → nlm mindmap/slides/infographic create <nb-id> --confirm
│   ├─► Video → nlm video create <nb-id> --confirm
│   └─► Extract data → nlm data-table create <nb-id> "description" --confirm
│
├─► Ask questions about sources
│   └─► nlm notebook query <nb-id> "question"
│       (Use --conversation-id for follow-ups)
│       ⚠️ Do NOT use `nlm chat start` - it's a REPL for humans only
│
├─► Check generation status
│   └─► nlm studio status <nb-id>
│
└─► Manage/cleanup
    ├─► List notebooks → nlm notebook list
    ├─► List sources → nlm source list <nb-id>
    ├─► Delete source → nlm source delete <source-id> --confirm
    └─► Delete notebook → nlm notebook delete <nb-id> --confirm

使用以下决策树确定正确的命令序列：

User wants to...
│
├─► 首次使用NotebookLM
│   └─► nlm login → nlm notebook create "Title"
│
├─► 向笔记本添加内容
│   ├─► 从URL/网页添加 → nlm source add <nb-id> --url "https://..."
│   ├─► 从YouTube添加 → nlm source add <nb-id> --url "https://youtube.com/..."
│   ├─► 从粘贴文本添加 → nlm source add <nb-id> --text "content" --title "Title"
│   ├─► 从Google Drive添加 → nlm source add <nb-id> --drive <doc-id> --type doc
│   └─► 发现新素材源 → nlm research start "query" --notebook-id <nb-id>
│
├─► 从素材源生成内容
│   ├─► 播客/音频 → nlm audio create <nb-id> --confirm
│   ├─► 文字摘要 → nlm report create <nb-id> --confirm
│   ├─► 学习资料 → nlm quiz/flashcards create <nb-id> --confirm
│   ├─► 可视化内容 → nlm mindmap/slides/infographic create <nb-id> --confirm
│   ├─► 视频 → nlm video create <nb-id> --confirm
│   └─► 提取数据 → nlm data-table create <nb-id> "description" --confirm
│
├─► 针对素材源提问
│   └─► nlm notebook query <nb-id> "question"
│       (追问使用--conversation-id参数)
│       ⚠️ 不要使用`nlm chat start` - 它是仅面向人类的REPL
│
├─► 检查生成状态
│   └─► nlm studio status <nb-id>
│
└─► 管理/清理资源
    ├─► 列出笔记本 → nlm notebook list
    ├─► 列出素材源 → nlm source list <nb-id>
    ├─► 删除素材源 → nlm source delete <source-id> --confirm
    └─► 删除笔记本 → nlm notebook delete <nb-id> --confirm

Command Categories

命令分类

1. Authentication

1. 身份认证

MCP Authentication

MCP身份认证

If using MCP tools and encountering authentication errors:

bash

undefined

如果使用MCP工具时遇到认证错误：

bash

undefined

Run the CLI authentication (works for both CLI and MCP)

运行CLI身份认证（同时适用于CLI和MCP）

nlm login

Then reload tokens in MCP

然后在MCP中重新加载令牌

mcp__notebooklm-mcp__refresh_auth()


Or manually save cookies via MCP (fallback):
```python

mcp__notebooklm-mcp__refresh_auth()


或通过MCP手动保存cookie（ fallback方案）：
```python

Extract cookies from Chrome DevTools and save

从Chrome开发者工具提取cookie并保存

mcp__notebooklm-mcp__save_auth_tokens(cookies="<cookie_header>")

undefined

mcp__notebooklm-mcp__save_auth_tokens(cookies="<cookie_header>")

undefined

CLI Authentication

CLI身份认证

bash

nlm login                           # Launch browser, extract cookies (primary method)
nlm login --check                   # Validate current session
nlm login --profile work            # Use named profile for multiple accounts
nlm login --provider openclaw --cdp-url http://127.0.0.1:18800  # External CDP provider
nlm login switch <profile>          # Switch the default profile
nlm login profile list              # List all profiles with email addresses
nlm login profile delete <name>     # Delete a profile
nlm login profile rename <old> <new> # Rename a profile

Multi-Profile Support: Each profile gets its own isolated browser session (supports Chrome, Arc, Brave, Edge, Chromium, and more), so you can be logged into multiple Google accounts simultaneously.

Session lifetime: ~20 minutes. Re-authenticate when commands fail with auth errors.

Switching MCP Accounts: The MCP server always uses the active default profile. If you need to switch which Google account the MCP server is communicating with, you MUST use the CLI: run

nlm login switch <name>

. Your next MCP tool call will instantly use the new account.

Note: Both MCP and CLI share the same authentication backend, so authenticating with one works for both.

bash

nlm login                           # 启动浏览器，提取cookie（主要方式）
nlm login --check                   # 验证当前会话
nlm login --profile work            # 使用命名配置文件支持多账户
nlm login --provider openclaw --cdp-url http://127.0.0.1:18800  # 外部CDP提供商
nlm login switch <profile>          # 切换默认配置文件
nlm login profile list              # 列出所有配置文件及关联邮箱
nlm login profile delete <name>     # 删除配置文件
nlm login profile rename <old> <new> # 重命名配置文件

多配置文件支持：每个配置文件都有独立的浏览器会话（支持Chrome、Arc、Brave、Edge、Chromium等），因此你可以同时登录多个Google账户。

会话有效期：约20分钟。如果命令返回认证错误，请重新认证。

切换MCP账户：MCP服务器始终使用当前活跃的默认配置文件。如果你需要切换MCP服务器使用的Google账户，必须通过CLI执行

nlm login switch <name>

，下次MCP工具调用会立即使用新账户。

注意：MCP和CLI共享同一套身份认证后端，因此对其中一个完成认证后两者都可以使用。

2. Notebook Management

2. 笔记本管理

MCP Tools

MCP工具

Use tools:

notebook_list

notebook_create

notebook_get

notebook_describe

notebook_query

notebook_rename

notebook_delete

. All accept

notebook_id

parameter. Delete requires

confirm=True

使用工具：

notebook_list

、

notebook_create

、

notebook_get

、

notebook_describe

、

notebook_query

、

notebook_rename

、

notebook_delete

。所有工具都接受

notebook_id

参数，删除操作需要

confirm=True

。

CLI Commands

CLI命令

bash

nlm notebook list                      # List all notebooks
nlm notebook list --json               # JSON output for parsing
nlm notebook list --quiet              # IDs only (for scripting)
nlm notebook create "Title"            # Create notebook, returns ID
nlm notebook get <id>                  # Get notebook details
nlm notebook describe <id>             # AI-generated summary + suggested topics
nlm notebook query <id> "question"     # One-shot Q&A with sources
nlm notebook rename <id> "New Title"   # Rename notebook
nlm notebook delete <id> --confirm     # PERMANENT deletion

bash

nlm notebook list                      # 列出所有笔记本
nlm notebook list --json               # JSON格式输出用于解析
nlm notebook list --quiet              # 仅输出ID（用于脚本）
nlm notebook create "Title"            # 创建笔记本，返回ID
nlm notebook get <id>                  # 获取笔记本详情
nlm notebook describe <id>             # AI生成的摘要+建议主题
nlm notebook query <id> "question"     # 针对素材源的单轮问答
nlm notebook rename <id> "New Title"   # 重命名笔记本
nlm notebook delete <id> --confirm     # 永久删除

3. Source Management

3. 素材源管理

MCP Tools

MCP工具

Use

source_add

with these

source_type

values:

```
url
```
- Web page or YouTube URL (
```
url
```
param)
```
text
```
- Pasted content (
```
text
```
+
```
title
```
params)
```
file
```
- Local file upload (
```
file_path
```
param)
```
drive
```
- Google Drive doc (
```
document_id
```
+
```
doc_type
```
params)

Other tools:

source_list_drive

source_describe

source_get_content

source_rename

source_sync_drive

(requires

confirm=True

source_delete

(requires

confirm=True

使用

source_add

工具，支持以下

source_type

值：

```
url
```
- 网页或YouTube URL（
```
url
```
参数）
```
text
```
- 粘贴的内容（
```
text
```
+
```
title
```
参数）
```
file
```
- 本地文件上传（
```
file_path
```
参数）
```
drive
```
- Google Drive文档（
```
document_id
```
+
```
doc_type
```
参数）

其他工具：

source_list_drive

、

source_describe

、

source_get_content

、

source_rename

、

source_sync_drive

（需要

confirm=True

）、

source_delete

（需要

confirm=True

）。

CLI Commands

CLI命令

bash

undefined

bash

undefined

Adding sources

添加素材源

nlm source add <nb-id> --url "https://..." # Web page nlm source add <nb-id> --url "https://youtube.com/..." # YouTube video nlm source add <nb-id> --text "content" --title "X" # Pasted text nlm source add <nb-id> --drive <doc-id> # Drive doc (auto-detect type) nlm source add <nb-id> --drive <doc-id> --type slides # Explicit type

nlm source add <nb-id> --url "https://..." # 网页 nlm source add <nb-id> --url "https://youtube.com/..." # YouTube视频 nlm source add <nb-id> --text "content" --title "X" # 粘贴文本 nlm source add <nb-id> --drive <doc-id> # Drive文档（自动检测类型） nlm source add <nb-id> --drive <doc-id> --type slides # 显式指定类型

Listing and viewing

列出和查看素材源

nlm source list <nb-id> # Table of sources nlm source list <nb-id> --drive # Show Drive sources with freshness nlm source list <nb-id> --drive -S # Skip freshness checks (faster) nlm source get <source-id> # Source metadata nlm source describe <source-id> # AI summary + keywords nlm source content <source-id> # Raw text content nlm source content <source-id> -o file.txt # Export to file

nlm source list <nb-id> # 素材源表格 nlm source list <nb-id> --drive # 展示Drive素材源及新鲜度 nlm source list <nb-id> --drive -S # 跳过新鲜度检查（更快） nlm source get <source-id> # 素材源元数据 nlm source describe <source-id> # AI摘要+关键词 nlm source content <source-id> # 原始文本内容 nlm source content <source-id> -o file.txt # 导出到文件

Drive sync (for stale sources)

Drive同步（用于过时素材源）

nlm source stale <nb-id> # List outdated Drive sources nlm source sync <nb-id> --confirm # Sync all stale sources nlm source sync <nb-id> --source-ids <ids> --confirm # Sync specific

nlm source stale <nb-id> # 列出过时的Drive素材源 nlm source sync <nb-id> --confirm # 同步所有过时素材源 nlm source sync <nb-id> --source-ids <ids> --confirm # 同步指定素材源

Rename

重命名

nlm source rename <source-id> "New Title" --notebook <nb-id> nlm rename source <source-id> "New Title" --notebook <nb-id> # verb-first

nlm source rename <source-id> "New Title" --notebook <nb-id> nlm rename source <source-id> "New Title" --notebook <nb-id> # 动词优先写法

Deletion

删除

nlm source delete <source-id> --confirm


**Drive types**: `doc`, `slides`, `sheets`, `pdf`

nlm source delete <source-id> --confirm


**Drive类型**：`doc`、`slides`、`sheets`、`pdf`

4. Research (Source Discovery)

4. 调研（素材源发现）

Research finds NEW sources from the web or Google Drive.

调研功能可以从网页或Google Drive查找新的素材源。

MCP Tools

MCP工具

Use

research_start

with:

```
source
```
:
```
web
```
or
```
drive
```
```
mode
```
:
```
fast
```
(~30s) or
```
deep
```
(~5min, web only)

Workflow:

research_start

→ poll

research_status

→

research_import

使用

research_start

工具，参数包括：

```
source
```
：
```
web
```
或
```
drive
```
```
mode
```
：
```
fast
```
（约30秒）或
```
deep
```
（约5分钟，仅网页支持）

工作流：

research_start

→ 轮询

research_status

→

research_import

CLI Commands

CLI命令

bash

undefined

bash

undefined

Start research (--notebook-id is REQUIRED)

启动调研（--notebook-id为必填项）

nlm research start "query" --notebook-id <id> # Fast web (~30s) nlm research start "query" --notebook-id <id> --mode deep # Deep web (~5min) nlm research start "query" --notebook-id <id> --source drive # Drive search

nlm research start "query" --notebook-id <id> # 快速网页调研（约30秒） nlm research start "query" --notebook-id <id> --mode deep # 深度网页调研（约5分钟） nlm research start "query" --notebook-id <id> --source drive # Drive搜索

Check progress

检查进度

nlm research status <nb-id> # Poll until done (5min max) nlm research status <nb-id> --max-wait 0 # Single check, no waiting nlm research status <nb-id> --task-id <tid> # Check specific task nlm research status <nb-id> --full # Full details

nlm research status <nb-id> # 轮询直到完成（最多5分钟） nlm research status <nb-id> --max-wait 0 # 单次检查，不等待 nlm research status <nb-id> --task-id <tid> # 检查指定任务 nlm research status <nb-id> --full # 完整详情

Import discovered sources

导入发现的素材源

nlm research import <nb-id> <task-id> # Import all nlm research import <nb-id> <task-id> --indices 0,2,5 # Import specific


**Modes**: `fast` (~30s, ~10 sources) | `deep` (~5min, ~40+ sources, web only)

nlm research import <nb-id> <task-id> # 导入全部 nlm research import <nb-id> <task-id> --indices 0,2,5 # 导入指定索引的素材源


**模式**：`fast`（约30秒，约10个素材源） | `deep`（约5分钟，约40+个素材源，仅网页支持）

5. Content Generation (Studio)

5. 内容生成（工作室）

MCP Tools (Unified Creation)

MCP工具（统一创建接口）

Use

studio_create

with

artifact_type

and type-specific options. All require

confirm=True

artifact_type	Key Options
`audio`	`audio_format` : deep_dive/brief/critique/debate, `audio_length` : short/default/long
`video`	`video_format` : explainer/brief, `visual_style` : auto_select/classic/whiteboard/kawaii/anime/watercolor/retro_print/heritage/paper_craft
`report`	`report_format` : Briefing Doc/Study Guide/Blog Post/Create Your Own, `custom_prompt`
`quiz`	`question_count` , `difficulty` : easy/medium/hard
`flashcards`	`difficulty` : easy/medium/hard
`mind_map`	`title`
`slide_deck`	`slide_format` : detailed_deck/presenter_slides, `slide_length` : short/default
`infographic`	`orientation` : landscape/portrait/square, `detail_level` : concise/standard/detailed, `infographic_style` : auto_select/sketch_note/professional/bento_grid/editorial/instructional/bricks/clay/anime/kawaii/scientific
`data_table`	`description` (REQUIRED)

Common options:

source_ids

language

(BCP-47 code),

focus_prompt

Revise Slides: Use

studio_revise

to revise individual slides in an existing slide deck.

Requires

artifact_id

(from

studio_status

) and

slide_instructions

Creates a NEW artifact — the original is not modified
Slide numbers are 1-based (slide 1 = first slide)
Poll
```
studio_status
```
after calling to check when the new deck is ready

使用

studio_create

工具，指定

artifact_type

和类型特定选项，所有调用都需要

confirm=True

。

产物类型	核心选项
`audio`	`audio_format` : deep_dive/brief/critique/debate, `audio_length` : short/default/long
`video`	`video_format` : explainer/brief, `visual_style` : auto_select/classic/whiteboard/kawaii/anime/watercolor/retro_print/heritage/paper_craft
`report`	`report_format` : Briefing Doc/Study Guide/Blog Post/Create Your Own, `custom_prompt`
`quiz`	`question_count` , `difficulty` : easy/medium/hard
`flashcards`	`difficulty` : easy/medium/hard
`mind_map`	`title`
`slide_deck`	`slide_format` : detailed_deck/presenter_slides, `slide_length` : short/default
`infographic`	`orientation` : landscape/portrait/square, `detail_level` : concise/standard/detailed, `infographic_style` : auto_select/sketch_note/professional/bento_grid/editorial/instructional/bricks/clay/anime/kawaii/scientific
`data_table`	`description` （必填）

通用选项：

source_ids

、

language

（BCP-47编码）、

focus_prompt

修改幻灯片：使用

studio_revise

修改现有幻灯片中的单页幻灯片。

需要

artifact_id

（从

studio_status

获取）和

slide_instructions

参数

会生成新的产物，原始产物不会被修改
幻灯片编号从1开始（slide 1 = 第一页）
调用后轮询
```
studio_status
```
检查新幻灯片的生成进度

CLI Commands

CLI命令

All generation commands share these flags:

```
--confirm
```
or
```
-y
```
: REQUIRED to execute
```
--source-ids <id1,id2>
```
: Limit to specific sources
```
--language <code>
```
: BCP-47 code (en, es, fr, de, ja)

bash

undefined

所有生成命令都支持以下标志：

```
--confirm
```
或
```
-y
```
：执行必填
```
--source-ids <id1,id2>
```
：仅使用指定素材源
```
--language <code>
```
：BCP-47编码（en、es、fr、de、ja）

bash

undefined

Audio (Podcast)

音频（播客）

nlm audio create <id> --confirm nlm audio create <id> --format deep_dive --length default --confirm nlm audio create <id> --format brief --focus "key topic" --confirm

Formats: deep_dive, brief, critique, debate

格式：deep_dive, brief, critique, debate

Lengths: short, default, long

时长：short, default, long

Report

报告

nlm report create <id> --confirm nlm report create <id> --format "Study Guide" --confirm nlm report create <id> --format "Create Your Own" --prompt "Custom..." --confirm

Formats: "Briefing Doc", "Study Guide", "Blog Post", "Create Your Own"

格式："Briefing Doc", "Study Guide", "Blog Post", "Create Your Own"

Quiz

测验

nlm quiz create <id> --confirm nlm quiz create <id> --count 5 --difficulty 3 --confirm nlm quiz create <id> --count 10 --difficulty 3 --focus "Focus on key concepts" --confirm

Count: number of questions (default: 2)

数量：题目数量（默认：2）

Difficulty: 1-5 (1=easy, 5=hard)

难度：1-5（1=简单，5=困难）

Focus: optional text to guide quiz generation

焦点：可选文本，指导测验生成方向

Flashcards

抽认卡

nlm flashcards create <id> --confirm nlm flashcards create <id> --difficulty hard --confirm nlm flashcards create <id> --difficulty medium --focus "Focus on definitions" --confirm

Difficulty: easy, medium, hard

难度：easy, medium, hard

Focus: optional text to guide flashcard generation

焦点：可选文本，指导抽认卡生成方向

Mind Map

思维导图

nlm mindmap create <id> --confirm nlm mindmap create <id> --title "Topic Overview" --confirm nlm mindmap list <id> # List existing mind maps

nlm mindmap create <id> --confirm nlm mindmap create <id> --title "Topic Overview" --confirm nlm mindmap list <id> # 列出现有思维导图

Slides

幻灯片

nlm slides create <id> --confirm nlm slides create <id> --format presenter --length short --confirm

Formats: detailed, presenter | Lengths: short, default

格式：detailed, presenter | 长度：short, default

nlm slides revise <artifact-id> --slide '1 Make the title larger' --confirm

Creates a NEW deck with revisions. Original unchanged.

生成包含修改内容的新幻灯片，原幻灯片保持不变

Infographic

信息图

nlm infographic create <id> --confirm nlm infographic create <id> --orientation portrait --detail detailed --style professional --confirm

Orientations: landscape, portrait, square

方向：landscape, portrait, square

Detail: concise, standard, detailed

详情度：concise, standard, detailed

Styles: auto_select, sketch_note, professional, bento_grid, editorial, instructional, bricks, clay, anime, kawaii, scientific

风格：auto_select, sketch_note, professional, bento_grid, editorial, instructional, bricks, clay, anime, kawaii, scientific

Video

视频

nlm video create <id> --confirm nlm video create <id> --format brief --style whiteboard --confirm

Formats: explainer, brief

格式：explainer, brief

Styles: auto_select, classic, whiteboard, kawaii, anime, watercolor, retro_print, heritage, paper_craft

风格：auto_select, classic, whiteboard, kawaii, anime, watercolor, retro_print, heritage, paper_craft

Data Table

数据表

nlm data-table create <id> "Extract all dates and events" --confirm

DESCRIPTION is required as second argument

描述为必填的第二个参数

undefined

undefined

6. Studio (Artifact Management)

6. 工作室（产物管理）

MCP Tools

MCP工具

Use

studio_status

to check progress (or rename with

action="rename"

). Use

download_artifact

with

artifact_type

and

output_path

. Use

export_artifact

with

export_type

: docs/sheets. Delete with

studio_delete

(requires

confirm=True

使用

studio_status

检查进度（或使用

action="rename"

重命名）。使用

download_artifact

并指定

artifact_type

和

output_path

下载产物。使用

export_artifact

并指定

export_type

：docs/sheets导出到Google文档/表格。使用

studio_delete

删除产物（需要

confirm=True

）。

CLI Commands

CLI命令

bash

undefined

bash

undefined

Check status

检查状态

nlm studio status <nb-id> # List all artifacts nlm studio status <nb-id> --full # Show full details (including custom prompts) nlm studio status <nb-id> --json # JSON output

nlm studio status <nb-id> # 列出所有产物 nlm studio status <nb-id> --full # 展示完整详情（包括自定义提示词） nlm studio status <nb-id> --json # JSON输出

Download artifacts

下载产物

nlm download audio <nb-id> --output podcast.mp3 nlm download video <nb-id> --output video.mp4 nlm download report <nb-id> --output report.md nlm download slide-deck <nb-id> --output slides.pdf # PDF (default) nlm download slide-deck <nb-id> --output slides.pptx --format pptx # PPTX nlm download quiz <nb-id> --output quiz.json --format json

nlm download audio <nb-id> --output podcast.mp3 nlm download video <nb-id> --output video.mp4 nlm download report <nb-id> --output report.md nlm download slide-deck <nb-id> --output slides.pdf # PDF（默认） nlm download slide-deck <nb-id> --output slides.pptx --format pptx # PPTX nlm download quiz <nb-id> --output quiz.json --format json

Export to Google Docs/Sheets

导出到Google Docs/Sheets

nlm export sheets <nb-id> <artifact-id> --title "My Data Table" nlm export docs <nb-id> <artifact-id> --title "My Report"

Delete artifact

删除产物

nlm studio delete <nb-id> <artifact-id> --confirm


**Status values**: `completed` (✓), `in_progress` (●), `failed` (✗)

**Prompt Extraction**: The `studio_status` tool returns a `custom_instructions` field for each artifact. This contains the original focus prompt or custom instructions used to generate that artifact (e.g., the prompt for a "Create Your Own" report, or the focus topic for an Audio Overview). This is useful for retrieving the exact prompt that generated a successful artifact.

nlm studio delete <nb-id> <artifact-id> --confirm


**状态值**：`completed`（✓）、`in_progress`（●）、`failed`（✗）

**提示词提取**：`studio_status`工具会返回每个产物的`custom_instructions`字段，包含生成该产物时使用的原始焦点提示词或自定义指令（例如“自定义”报告的提示词，或音频概览的焦点主题）。该字段可用于检索生成成功产物的精确提示词。

Renaming Resources

重命名资源

Rename a Source

重命名素材源

MCP Tool:

source_rename(notebook_id, source_id, new_title)

CLI:

bash

nlm source rename <source-id> "New Title" --notebook <notebook-id>
nlm rename source <source-id> "New Title" --notebook <notebook-id>  # verb-first

MCP工具：

source_rename(notebook_id, source_id, new_title)

CLI：

bash

nlm source rename <source-id> "New Title" --notebook <notebook-id>
nlm rename source <source-id> "New Title" --notebook <notebook-id>  # 动词优先写法

Rename a Studio Artifact

重命名工作室产物

MCP Tools

MCP工具

Use

studio_status

with

action="rename"

artifact_id

, and

new_title

使用

studio_status

并指定

action="rename"

、

artifact_id

和

new_title

。

CLI Commands

CLI命令

bash

nlm studio rename <artifact-id> "New Title"
nlm rename studio <artifact-id> "New Title"  # verb-first alternative

bash

nlm studio rename <artifact-id> "New Title"
nlm rename studio <artifact-id> "New Title"  # 动词优先替代写法

Server Info (Version Check)

服务器信息（版本检查）

MCP Tools

MCP工具

Use

server_info

to get version and check for updates:

python

mcp__notebooklm-mcp__server_info()

使用

server_info

获取版本并检查更新：

python

mcp__notebooklm-mcp__server_info()

Returns: version, latest_version, update_available, update_command

返回：version, latest_version, update_available, update_command

undefined

undefined

CLI Commands

CLI命令

bash

nlm --version  # Shows version and update availability

bash

nlm --version  # 展示版本和更新可用性

7. Chat Configuration and Notes

7. 聊天配置和笔记

MCP Tools

MCP工具

Use

chat_configure

with

goal

: default/learning_guide/custom. Use

note

with

action

: create/list/update/delete. Delete requires

confirm=True

使用

chat_configure

并指定

goal

：default/learning_guide/custom。使用

note

并指定

action

：create/list/update/delete，删除操作需要

confirm=True

。

CLI Commands

CLI命令

⚠️ AI TOOLS: DO NOT USE
nlm chat start
- It launches an interactive REPL that cannot be controlled programmatically. Use
nlm notebook query
for one-shot Q&A instead.

For human users at a terminal:

bash

nlm chat start <nb-id>  # Launch interactive REPL

REPL Commands:

```
/sources
```
- List available sources
```
/clear
```
- Reset conversation context
```
/help
```
- Show commands
```
/exit
```
- Exit REPL

Configure chat behavior (works for both REPL and query):

bash

nlm chat configure <id> --goal default
nlm chat configure <id> --goal learning_guide
nlm chat configure <id> --goal custom --prompt "Act as a tutor..."
nlm chat configure <id> --response-length longer  # longer, default, shorter

Notes management:

bash

nlm note create <nb-id> "Content" --title "Title"
nlm note list <nb-id>
nlm note update <nb-id> <note-id> --content "New content"
nlm note delete <nb-id> <note-id> --confirm

⚠️ AI工具请勿使用
nlm chat start
- 它会启动无法被程序化控制的交互式REPL，请使用
nlm notebook query
进行单轮问答。

面向终端人类用户的命令：

bash

nlm chat start <nb-id>  # 启动交互式REPL

REPL命令：

```
/sources
```
- 列出可用素材源
```
/clear
```
- 重置会话上下文
```
/help
```
- 展示命令
```
/exit
```
- 退出REPL

配置聊天行为（同时适用于REPL和query命令）：

bash

nlm chat configure <id> --goal default
nlm chat configure <id> --goal learning_guide
nlm chat configure <id> --goal custom --prompt "Act as a tutor..."
nlm chat configure <id> --response-length longer  # longer, default, shorter

笔记管理：

bash

nlm note create <nb-id> "Content" --title "Title"
nlm note list <nb-id>
nlm note update <nb-id> <note-id> --content "New content"
nlm note delete <nb-id> <note-id> --confirm

8. Notebook Sharing

8. 笔记本共享

MCP Tools

MCP工具

Use

notebook_share_status

to check,

notebook_share_public

to enable/disable public link,

notebook_share_invite

with

email

and

role

: viewer/editor.

使用

notebook_share_status

检查共享状态，

notebook_share_public

启用/禁用公开链接，

notebook_share_invite

邀请协作者，指定

email

和

role

：viewer/editor。

CLI Commands

CLI命令

bash

undefined

bash

undefined

Check sharing status

检查共享状态

nlm share status <nb-id>

Enable/disable public link

启用/禁用公开链接

nlm share public <nb-id> # Enable nlm share public <nb-id> --off # Disable

nlm share public <nb-id> # 启用 nlm share public <nb-id> --off # 禁用

Invite collaborator

邀请协作者

nlm share invite <nb-id> user@example.com nlm share invite <nb-id> user@example.com --role editor

undefined

nlm share invite <nb-id> user@example.com nlm share invite <nb-id> user@example.com --role editor

undefined

9. Aliases (UUID Shortcuts)

9. 别名（UUID快捷方式）

Simplify long UUIDs:

bash

nlm alias set myproject abc123-def456...  # Create alias (auto-detects type)
nlm alias get myproject                    # Resolve to UUID
nlm alias list                             # List all aliases
nlm alias delete myproject                 # Remove alias

简化过长的UUID：

bash

nlm alias set myproject abc123-def456...  # 创建别名（自动检测类型）
nlm alias get myproject                    # 解析为UUID
nlm alias list                             # 列出所有别名
nlm alias delete myproject                 # 删除别名

Use aliases anywhere

任意位置都可以使用别名

nlm notebook get myproject nlm source list myproject nlm audio create myproject --confirm

undefined

nlm notebook get myproject nlm source list myproject nlm audio create myproject --confirm

undefined

10. Configuration

10. 配置

CLI-only commands for managing settings:

bash

nlm config show                              # Show current config
nlm config get <key>                         # Get specific setting
nlm config set <key> <value>                 # Update setting
nlm config set output.format json            # Change default output

仅CLI支持的设置管理命令：

bash

nlm config show                              # 展示当前配置
nlm config get <key>                         # 获取指定设置
nlm config set <key> <value>                 # 更新设置
nlm config set output.format json            # 修改默认输出格式

For switching profiles, prefer the simpler command:

切换配置文件推荐使用更简单的命令：

nlm login switch work # Switch default profile


**Available Settings:**

| Key | Default | Description |
|-----|---------|-------------|
| `output.format` | `table` | Default output format (table, json) |
| `output.color` | `true` | Enable colored output |
| `output.short_ids` | `true` | Show shortened IDs |
| `auth.browser` | `auto` | Preferred browser for login (auto, chrome, arc, brave, edge, chromium, vivaldi, opera) |
| `auth.default_profile` | `default` | Profile to use when `--profile` not specified |

nlm login switch work # 切换默认配置文件


**可用设置**：

| 键 | 默认值 | 描述 |
|-----|---------|-------------|
| `output.format` | `table` | 默认输出格式（table、json） |
| `output.color` | `true` | 启用彩色输出 |
| `output.short_ids` | `true` | 展示缩短的ID |
| `auth.browser` | `auto` | 登录首选浏览器（auto、chrome、arc、brave、edge、chromium、vivaldi、opera） |
| `auth.default_profile` | `default` | 未指定`--profile`时使用的配置文件 |

11. Skill Management

11. 技能管理

Manage the NotebookLM skill installation for various AI assistants:

bash

nlm skill list                              # Show installation status
nlm skill update                            # Update all outdated skills
nlm skill update <tool>                     # Update specific skill (e.g., claude-code)
nlm skill install <tool>                    # Install skill
nlm skill uninstall <tool>                  # Uninstall skill

Verb-first aliases:

nlm update skill

nlm list skills

nlm install skill

管理各类AI助手的NotebookLM技能安装：

bash

nlm skill list                              # 展示安装状态
nlm skill update                            # 更新所有过时技能
nlm skill update <tool>                     # 更新指定技能（例如claude-code）
nlm skill install <tool>                    # 安装技能
nlm skill uninstall <tool>                  # 卸载技能

动词优先别名：

nlm update skill

、

nlm list skills

、

nlm install skill

Output Formats

输出格式

Most list commands support multiple formats:

Flag	Description
(none)	Rich table (human-readable)
`--json`	JSON output (for parsing)
`--quiet`	IDs only (for piping)
`--title`	"ID: Title" format
`--url`	"ID: URL" format (sources only)
`--full`	All columns/details

大多数列表命令支持多种格式：

标志	描述
（无）	富表格（人类可读）
`--json`	JSON输出（用于解析）
`--quiet`	仅输出ID（用于管道）
`--title`	"ID: 标题"格式
`--url`	"ID: URL"格式（仅素材源）
`--full`	所有列/完整详情

Common Patterns

常用模式

Pattern 1: Research → Podcast Pipeline

模式1：调研→播客流水线

bash

nlm notebook create "AI Research 2026"   # Capture ID
nlm alias set ai <notebook-id>
nlm research start "agentic AI trends" --notebook-id ai --mode deep
nlm research status ai --max-wait 300    # Wait up to 5 min
nlm research import ai <task-id>         # Import all sources
nlm audio create ai --format deep_dive --confirm
nlm studio status ai                     # Check generation progress

bash

nlm notebook create "AI Research 2026"   # 捕获返回的ID
nlm alias set ai <notebook-id>
nlm research start "agentic AI trends" --notebook-id ai --mode deep
nlm research status ai --max-wait 300    # 最多等待5分钟
nlm research import ai <task-id>         # 导入所有素材源
nlm audio create ai --format deep_dive --confirm
nlm studio status ai                     # 检查生成进度

Pattern 2: Quick Content Ingestion

模式2：快速内容摄入

bash

nlm source add <id> --url "https://example1.com"
nlm source add <id> --url "https://example2.com"
nlm source add <id> --text "My notes..." --title "Notes"
nlm source list <id>

bash

nlm source add <id> --url "https://example1.com"
nlm source add <id> --url "https://example2.com"
nlm source add <id> --text "My notes..." --title "Notes"
nlm source list <id>

Pattern 3: Study Materials Generation

模式3：学习资料生成

bash

nlm report create <id> --format "Study Guide" --confirm
nlm quiz create <id> --count 10 --difficulty 3 --focus "Exam prep" --confirm
nlm flashcards create <id> --difficulty medium --focus "Core terms" --confirm

bash

nlm report create <id> --format "Study Guide" --confirm
nlm quiz create <id> --count 10 --difficulty 3 --focus "Exam prep" --confirm
nlm flashcards create <id> --difficulty medium --focus "Core terms" --confirm

Pattern 4: Drive Document Workflow

模式4：Drive文档工作流

bash

nlm source add <id> --drive 1KQH3eW0hMBp7WK... --type slides

bash

nlm source add <id> --drive 1KQH3eW0hMBp7WK... --type slides

... time passes, document is edited ...

... 时间流逝，文档被编辑 ...

nlm source stale <id> # Check freshness nlm source sync <id> --confirm # Sync if stale

undefined

nlm source stale <id> # 检查新鲜度 nlm source sync <id> --confirm # 如果过时则同步

undefined

Error Recovery

错误恢复

Error	Cause	Solution
"Cookies have expired"	Session timeout	`nlm login`
"authentication may have expired"	Session timeout	`nlm login`
"Notebook not found"	Invalid ID	`nlm notebook list`
"Source not found"	Invalid ID	`nlm source list <nb-id>`
"Rate limit exceeded"	Too many calls	Wait 30s, retry
"Research already in progress"	Pending research	Use `--force` or import first
Browser doesn't launch	Port conflict	Close browser, retry

错误信息	原因	解决方案
"Cookies have expired"	会话超时	`nlm login`
"authentication may have expired"	会话超时	`nlm login`
"Notebook not found"	无效ID	`nlm notebook list`
"Source not found"	无效ID	`nlm source list <nb-id>`
"Rate limit exceeded"	调用次数过多	等待30秒后重试
"Research already in progress"	已有进行中的调研任务	使用 `--force` 参数或先导入现有调研结果
浏览器未启动	端口冲突	关闭浏览器后重试

Rate Limiting

速率限制

Wait between operations to avoid rate limits:

Source operations: 2 seconds
Content generation: 5 seconds
Research operations: 2 seconds
Query operations: 2 seconds

操作之间请等待一定时间避免触发速率限制：

素材源操作：2秒
内容生成：5秒
调研操作：2秒
查询操作：2秒

Advanced Reference

高级参考

For detailed information, see:

references/command_reference.md: Complete command signatures
references/troubleshooting.md: Detailed error handling
references/workflows.md: End-to-end task sequences

详细信息请查看：

references/command_reference.md：完整命令签名
references/troubleshooting.md：详细错误处理说明
references/workflows.md：端到端任务序列