Back to Details

notebooklm

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

NotebookLM CLI Wrapper (Python)

NotebookLM CLI Wrapper (Python)

Required parameters

必要参数

  • python3
    available.
  • notebooklm-py
    installed (CLI binary: 
    notebooklm
    ).
  • NotebookLM authenticated (
    login
    ).
  • 需安装
    python3
    。
  • 已安装
    notebooklm-py
    （CLI二进制文件：
    notebooklm
    ）。
  • 已完成NotebookLM身份验证（执行
    login
    命令）。

Quick start

快速开始

  • Wrapper script: 
    scripts/notebooklm.py
    .
  • Command form: 
    python3 {baseDir}/scripts/notebooklm.py <command> [args...]
    .
bash
python3 {baseDir}/scripts/notebooklm.py login
python3 {baseDir}/scripts/notebooklm.py list
python3 {baseDir}/scripts/notebooklm.py use <notebook_id>
python3 {baseDir}/scripts/notebooklm.py status
python3 {baseDir}/scripts/notebooklm.py ask "Summarize the key takeaways" --notebook <notebook_id>
  • 封装脚本路径：
    scripts/notebooklm.py
    。
  • 命令格式：
    python3 {baseDir}/scripts/notebooklm.py <command> [args...]
    。
bash
python3 {baseDir}/scripts/notebooklm.py login
python3 {baseDir}/scripts/notebooklm.py list
python3 {baseDir}/scripts/notebooklm.py use <notebook_id>
python3 {baseDir}/scripts/notebooklm.py status
python3 {baseDir}/scripts/notebooklm.py ask "Summarize the key takeaways" --notebook <notebook_id>

Output guidance

输出指南

  • Prefer 
    --json
    for machine-readable output where supported.
  • Long-running waits are handled by native commands like: 
    • source wait
    • artifact wait
    • research wait
  • 支持的情况下优先使用
    --json
    参数以获得机器可读的输出。
  • 长时间等待操作由原生命令处理，例如： 
    • source wait
    • artifact wait
    • research wait

⚡ Sub-Agent Delegation (Anti-Blocking)

⚡ 子Agent委托（防阻塞）

Problem

问题

NotebookLM operations like 
source wait
, 
artifact wait
, 
research wait
, 
generate slide-deck
, and 
source add-research
can take minutes to complete. Running them in the main session blocks the conversation.
NotebookLM的部分操作，如
source wait
、
artifact wait
、
research wait
、
generate slide-deck
和
source add-research
，可能需要数分钟才能完成。在主会话中运行这些操作会阻塞对话流程。

Strategy

解决策略

For any operation expected to take >30 seconds, delegate to a sub-agent via 
sessions_spawn
:
  1. Main session: Acknowledge the user's request, then spawn a sub-agent with a clear task description.
  2. Sub-agent: Executes the long-running NotebookLM commands, waits for completion, and reports back.
  3. Main session: Remains responsive. The sub-agent auto-announces completion.
对于任何预计耗时超过30秒的操作，通过
sessions_spawn
委托给子Agent处理：
  1. 主会话：确认用户请求，然后生成一个带有明确任务描述的子Agent。
  2. 子Agent：执行耗时的NotebookLM命令，等待操作完成后反馈结果。
  3. 主会话：保持响应状态，子Agent会自动通知任务完成。

Which operations to delegate

哪些操作需要委托

OperationDelegate?Reason
login
, 
status
, 
list
, 
use
, 
clear
❌ NoFast (<5s)
ask
(chat)		❌ NoUsually fast (~10s)
source list
, 
source get
, 
note list
❌ NoFast reads
source add
(URL/text)		⚠️ MaybeFast to submit, but 
source wait
after is slow
source add-research
✅ YesDeep research can take 2-5 min
source wait
✅ YesPolling wait, unpredictable duration
generate slide-deck
+ 
artifact wait
✅ YesGeneration takes 1-5 min
research wait
✅ YesCan take several minutes
download slide-deck
⚠️ MaybeUsually fast, but can be slow for large files
Multi-step workflows (add sources → wait → generate → wait → download)✅ YesCompound long tasks
操作是否委托原因
login
, 
status
, 
list
, 
use
, 
clear
❌ 不需要速度快（<5秒）
ask
（对话）		❌ 不需要通常速度快（约10秒）
source list
, 
source get
, 
note list
❌ 不需要快速读取操作
source add
（URL/文本）		⚠️ 视情况而定提交速度快，但后续的
source wait
操作较慢
source add-research
✅ 需要深度研究可能耗时2-5分钟
source wait
✅ 需要轮询等待，时长不可预测
generate slide-deck
+ 
artifact wait
✅ 需要生成过程耗时1-5分钟
research wait
✅ 需要可能耗时数分钟
download slide-deck
⚠️ 视情况而定通常速度快，但大文件可能较慢
多步骤工作流（添加源→等待→生成→等待→下载）✅ 需要复合式长耗时任务

How to spawn

如何生成子Agent

sessions_spawn:
  task: |
    You are a NotebookLM task runner. Execute the following NotebookLM operations
    and report results when done.

    Notebook ID: <notebook_id>
    Commands to run (in order):
    1. <command 1>
    2. <command 2>
    ...

    Use the CLI wrapper: python3 ~/.openclaw/skills/notebooklm-Invoke/scripts/notebooklm.py
    Prefer --json output where supported.
    If any step fails, report the error and stop.
    When complete, summarize what was accomplished and any output files created.
  mode: run
  label: notebooklm-<short-description>
sessions_spawn:
  task: |
    You are a NotebookLM task runner. Execute the following NotebookLM operations
    and report results when done.

    Notebook ID: <notebook_id>
    Commands to run (in order):
    1. <command 1>
    2. <command 2>
    ...

    Use the CLI wrapper: python3 ~/.openclaw/skills/notebooklm-Invoke/scripts/notebooklm.py
    Prefer --json output where supported.
    If any step fails, report the error and stop.
    When complete, summarize what was accomplished and any output files created.
  mode: run
  label: notebooklm-<short-description>

Example: Generate slide deck

示例：生成幻灯片

User: "帮我用 notebook X 生成一个 PPT"
Main session response:
好的，我派了一个后台任务去生成 PPT，完成后会通知你 ✧
Spawn:
sessions_spawn:
  task: |
    NotebookLM task: Generate a slide deck from notebook.

    Steps:
    1. python3 ~/.openclaw/skills/notebooklm-Invoke/scripts/notebooklm.py generate slide-deck "Create a comprehensive slide deck" --notebook <id>
    2. python3 ~/.openclaw/skills/notebooklm-Invoke/scripts/notebooklm.py artifact wait <artifact_id> --notebook <id> --timeout 600 --json
    3. python3 ~/.openclaw/skills/notebooklm-Invoke/scripts/notebooklm.py download slide-deck ./output.pptx --notebook <id> --latest --format pptx

    Report: artifact details, file path, any errors.
  mode: run
  label: notebooklm-slide-deck
用户："帮我用 notebook X 生成一个 PPT"
主会话回复:
好的，我派了一个后台任务去生成 PPT，完成后会通知你 ✧
生成子Agent:
sessions_spawn:
  task: |
    NotebookLM task: Generate a slide deck from notebook.

    Steps:
    1. python3 ~/.openclaw/skills/notebooklm-Invoke/scripts/notebooklm.py generate slide-deck "Create a comprehensive slide deck" --notebook <id>
    2. python3 ~/.openclaw/skills/notebooklm-Invoke/scripts/notebooklm.py artifact wait <artifact_id> --notebook <id> --timeout 600 --json
    3. python3 ~/.openclaw/skills/notebooklm-Invoke/scripts/notebooklm.py download slide-deck ./output.pptx --notebook <id> --latest --format pptx

    Report: artifact details, file path, any errors.
  mode: run
  label: notebooklm-slide-deck

Example: Add research source

示例：添加研究源

User: "在 notebook Y 里加一个关于碳足迹的深度研究"
Spawn:
sessions_spawn:
  task: |
    NotebookLM task: Add deep research source.

    Steps:
    1. python3 ~/.openclaw/skills/notebooklm-Invoke/scripts/notebooklm.py source add-research "碳足迹最新研究进展" --mode deep --notebook <id>
    2. python3 ~/.openclaw/skills/notebooklm-Invoke/scripts/notebooklm.py research wait --notebook <id> --timeout 600
    3. python3 ~/.openclaw/skills/notebooklm-Invoke/scripts/notebooklm.py source list --notebook <id> --json

    Report: research status, new sources added, any errors.
  mode: run
  label: notebooklm-research
用户："在 notebook Y 里加一个关于碳足迹的深度研究"
生成子Agent:
sessions_spawn:
  task: |
    NotebookLM task: Add deep research source.

    Steps:
    1. python3 ~/.openclaw/skills/notebooklm-Invoke/scripts/notebooklm.py source add-research "碳足迹最新研究进展" --mode deep --notebook <id>
    2. python3 ~/.openclaw/skills/notebooklm-Invoke/scripts/notebooklm.py research wait --notebook <id> --timeout 600
    3. python3 ~/.openclaw/skills/notebooklm-Invoke/scripts/notebooklm.py source list --notebook <id> --json

    Report: research status, new sources added, any errors.
  mode: run
  label: notebooklm-research

Guidelines

注意事项

  • Always tell the user you're delegating to a background task before spawning.
  • Use 
    mode: run
     (one-shot) — no need for persistent sessions.
  • Use descriptive labels like 
    notebooklm-slide-deck
    , 
    notebooklm-research-carbon
    for easy tracking.
  • Include all context in the task — the sub-agent has no conversation history.
  • Error handling: Instruct the sub-agent to report errors clearly so you can relay them.
  • File paths: Use absolute paths for output files so the main session can find them.
  • Compound workflows: Bundle related steps (add → wait → generate → wait → download) into a single sub-agent task rather than spawning multiple.
  • 务必告知用户在生成子Agent前，你将把任务委托给后台处理。
  • 使用
    mode: run
    （一次性任务）——无需持久会话。
  • 使用描述性标签，如
    notebooklm-slide-deck
    、
    notebooklm-research-carbon
    ，以便追踪。
  • 在任务中包含所有上下文信息——子Agent无对话历史。
  • 错误处理：指示子Agent清晰报告错误，以便你转达给用户。
  • 文件路径：使用绝对路径保存输出文件，以便主会话能找到。
  • 复合工作流：将相关步骤（添加→等待→生成→等待→下载）打包为单个子Agent任务，而非生成多个子Agent。

PPT generation policy

PPT生成规则

  • A single generated slide deck should target at most 15 pages.
  • If user requirements exceed 15 pages, split into multiple decks (e.g., Part 1/2/3) and generate separately.
  • After generation, provide downloadable 
    .pptx
     output when possible: 
    • download slide-deck ... --format pptx
  • 单次生成的幻灯片最多不超过15页。
  • 如果用户需求超过15页，需拆分为多个幻灯片（如第1/2/3部分）分别生成。
  • 生成完成后，尽可能提供可下载的
    .pptx
    格式文件：
    • 使用命令
      download slide-deck ... --format pptx

References

参考文档

  • README.md
    (installation, requirements, troubleshooting)
  • QUICKSTART_CN.md
    （中文快速上手）
  • references/cli-commands.md
  • README.md
    （安装、需求、故障排查）
  • QUICKSTART_CN.md
    （中文快速上手）
  • references/cli-commands.md

Assets

资源

  • None.
  • 无。