← 返回 Skills 市场
prantikmedhi

notebooklm-lore

作者 Prantik Medhi · GitHub ↗ · v0.1.1 · MIT-0
cross-platform ⚠ suspicious
35
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install notebooklm-lore
功能描述
OpenClaw skill wrapper for installing and operating Lore (NotebookLM automation toolkit) via CLI + MCP.
使用说明 (SKILL.md)

notebooklm-lore

This skill is a wrapper for agents (especially OpenClaw) to install and use the Lore project safely.

Repo: https://github.com/prantikmedhi/lore

What the agent should do

1) Install Lore locally

  • Clone or update the repo.
  • Install dependencies:
pip install -e .
python3 -m playwright install chromium

2) Authentication (user must do this)

NotebookLM auth is interactive. The agent must ask the user to run:

python3 -m notebooklm login

Rules:

  • Do not attempt to automate login.
  • Do not print, copy, or commit any auth/session state.

3) Verify

After the user confirms login is complete:

python scripts/auth_helper.py
lore list

4) MCP setup

Use the repo’s .mcp.json (preferred) or add an equivalent MCP server entry:

{
  "mcpServers": {
    "lore": {
      "command": "uvx",
      "args": ["--from", "notebooklm-skill", "notebooklm-mcp"],
      "env": {
        "NOTEBOOKLM_DEFAULT_LANGUAGE": "en",
        "NOTEBOOKLM_DEFAULT_FORMAT": "json",
        "NOTEBOOKLM_POWERED_MODE": "1"
      }
    }
  }
}

Security

Do not commit:

  • ~/.notebooklm/
  • ~/.notebooklm/storage_state.json
  • cookies, browser profiles, or private source materials
安全使用建议
Only install this if you are comfortable reviewing and trusting the external Lore repo and notebooklm-mcp package. Prefer a dedicated NotebookLM account/profile, pin reviewed versions, avoid sensitive materials at first, and revoke or delete the local session state when you no longer need it.
功能分析
Type: OpenClaw Skill Name: notebooklm-lore Version: 0.1.1 The skill bundle provides a standard wrapper for installing and configuring the 'Lore' NotebookLM automation toolkit. The instructions in SKILL.md explicitly direct the agent to avoid automating sensitive login processes and warn against exfiltrating or committing session data (e.g., storage_state.json). The installation steps using pip, Playwright, and uvx are consistent with the tool's documented purpose, and no malicious patterns or harmful prompt injections were detected.
能力评估
Purpose & Capability
The stated purpose matches the instructions: it is an OpenClaw wrapper for installing and using Lore with NotebookLM via CLI and MCP. The sensitive capability is disclosed, but it involves an authenticated NotebookLM session.
Instruction Scope
The skill tells the agent to clone/update an external repo, install it, run a helper script, and configure an MCP server, but it does not pin versions or define clear limits on what the MCP tools may do once connected.
Install Mechanism
There is no reviewed code or install spec in the skill; installation depends on external, unpinned repo/package commands such as pip install and uvx.
Credentials
The NotebookLM login/session use is purpose-aligned, and the skill includes warnings not to copy or commit session state, but the credential/session handling is not declared in metadata and relies on external code not included for review.
Persistence & Privilege
The skill references persistent NotebookLM auth/session state and MCP configuration. It warns not to commit that state, but users should understand that the installed tooling may continue to use the local session until removed or revoked.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install notebooklm-lore
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /notebooklm-lore 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v0.1.1
Publish as docs-only OpenClaw skill wrapper (remove executable code to clear security flags)
v0.1.0
Docs refresh: OpenClaw ready-made setup prompt + architecture/flows
元数据
Slug notebooklm-lore
版本 0.1.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

notebooklm-lore 是什么?

OpenClaw skill wrapper for installing and operating Lore (NotebookLM automation toolkit) via CLI + MCP. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 35 次。

如何安装 notebooklm-lore?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install notebooklm-lore」即可一键安装,无需额外配置。

notebooklm-lore 是免费的吗?

是的,notebooklm-lore 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

notebooklm-lore 支持哪些平台?

notebooklm-lore 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 notebooklm-lore?

由 Prantik Medhi(@prantikmedhi)开发并维护,当前版本 v0.1.1。

💬 留言讨论