← 返回 Skills 市场
OpenClaw Expert Brain
作者
Carlos De La Torre
· GitHub ↗
· v1.0.0
· MIT-0
187
总下载
1
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install openclaw-expert-brain
功能描述
Manual interactivo de OpenClaw con 185 fuentes curadas en NotebookLM. Pregunta sobre instalación, configuración, skills, troubleshooting, multi-agent, cron,...
安全使用建议
This skill appears to do what it says: it runs a small Python wrapper that calls your locally installed nlm CLI to query a curated NotebookLM notebook. Before installing/using it: (1) confirm you install notebooklm-mcp-cli from a trusted source and understand nlm will perform Google OAuth and store tokens locally; (2) avoid sending sensitive secrets or private data in queries to NotebookLM; (3) review the notebook ID (default is provided) if you need to ensure the data sources are trustworthy; (4) note requirements.txt lists python-dotenv but the script doesn't use it — benign but odd. If you want extra assurance, inspect the nlm package source or run the script in an isolated environment first.
功能分析
Type: OpenClaw Skill
Name: openclaw-expert-brain
Version: 1.0.0
The skill provides a legitimate interface for querying OpenClaw documentation via the 'nlm' (notebooklm-mcp-cli) tool. The implementation in 'scripts/ask.py' uses safe subprocess execution (list-based) to prevent shell injection, and the bundle lacks any indicators of data exfiltration, unauthorized persistence, or malicious prompt injection. It functions as a standard RAG (Retrieval-Augmented Generation) tool for technical support.
能力评估
Purpose & Capability
Name/description (interactive OpenClaw manual) match the implementation: the script invokes the nlm CLI to query a NotebookLM notebook. Declared required binaries (python3, nlm) are appropriate. The tiny requirements.txt entry (python-dotenv) is unused by the script but is not harmful.
Instruction Scope
SKILL.md instructs the agent to run the bundled script which calls nlm notebook query with an optional OPENCLAW_NOTEBOOK_ID. The instructions do not ask for arbitrary file reads, unrelated env vars, or sending data to unknown endpoints. The claim of "Cero alucinaciones" is a content guarantee that cannot be technically enforced by the skill itself (note).
Install Mechanism
No automated install spec is present (instruction-only), which minimizes risk. The README tells users to install notebooklm-mcp-cli via pip — a normal public package install. There are no downloads from unknown URLs or extract steps in the manifest.
Credentials
The skill does not require secrets or config paths. It expects the user to authenticate nlm with Google (nlm login), which is appropriate for accessing NotebookLM. Optional OPENCLAW_NOTEBOOK_ID is reasonable. Note: nlm will manage OAuth tokens locally — expected but worth awareness.
Persistence & Privilege
Skill does not request always:true, does not modify other skills or system-wide settings, and has no special persistence privileges. It simply invokes a CLI at runtime.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install openclaw-expert-brain - 安装完成后，直接呼叫该 Skill 的名称或使用
/openclaw-expert-brain触发 - 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
v1.0.0
Manual interactivo de OpenClaw con 185 fuentes en NotebookLM. Sin Chromium, via nlm CLI.
元数据
常见问题
OpenClaw Expert Brain 是什么？
Manual interactivo de OpenClaw con 185 fuentes curadas en NotebookLM. Pregunta sobre instalación, configuración, skills, troubleshooting, multi-agent, cron,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 187 次。
如何安装 OpenClaw Expert Brain？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openclaw-expert-brain」即可一键安装，无需额外配置。
OpenClaw Expert Brain 是免费的吗？
是的，OpenClaw Expert Brain 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
OpenClaw Expert Brain 支持哪些平台？
OpenClaw Expert Brain 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 OpenClaw Expert Brain？
由 Carlos De La Torre（@radelqui）开发并维护，当前版本 v1.0.0。
推荐 Skills