ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified productivity Safety 4/5

notebooklm-cli

Search and answer questions over documents already uploaded to NotebookLM using the nlm CLI. Use when users ask to find information, summarize sources, or query a specific NotebookLM notebook.

Why use this skill?

Seamlessly search and query your NotebookLM documents using the OpenClaw NotebookLM CLI skill. Extract grounded answers from your private sources.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/lhquangit/notebooklm-cli-cookies
Or

What This Skill Does

The notebooklm-cli is a powerful OpenClaw AI agent skill designed to integrate directly with your NotebookLM knowledge bases. It allows you to query, search, and extract information from your uploaded documents without ever leaving the agent interface. By utilizing the notebooklm-mcp-cli, the skill bridges the gap between your conversational AI and your private, curated data stored in NotebookLM, ensuring answers are grounded strictly in the sources you have provided.

Installation

To integrate this skill into your environment, run the following command in your terminal: clawhub install openclaw/skills/skills/lhquangit/notebooklm-cli-cookies

Ensure that the NOTEBOOKLM_MCP_CLI_PATH environment variable is correctly configured to point to your authentication storage directory, as the skill requires valid session credentials to access your notebooks securely.

Use Cases

  • Corporate Knowledge Management: Instantly retrieve policies, manuals, or project documentation from private NotebookLM notebooks.
  • Technical Research: Query technical specifications or product guides by using aliases for specific notebooks, such as querying a product catalog by name.
  • Meeting Summarization: Ask the agent to summarize key takeaways from meeting transcripts uploaded to your notebook.
  • Fact Checking: Verify information against specific source documents rather than relying on general web-search or model training data.

Example Prompts

  1. "Chạy lệnh: nlm notebook query tai_lieu_dien "giá của thiết bị A9N61500 là bao nhiêu? Nếu không có thông tin, hãy nói rõ không tìm thấy trong nguồn.""
  2. "Trong NotebookLM notebook alias tai_lieu_dien: trả lời câu hỏi "Quy trình bảo trì định kỳ cho hệ thống điện yêu cầu những bước gì?""
  3. "/nlm notebook list --json"

Tips & Limitations

  • Use Aliases: For notebooks you query frequently, always define an alias. This prevents ambiguity and avoids the need to repeatedly list all notebooks to find a specific UUID.
  • Verify Auth: Always run nlm login --check if you suspect the session has expired before initiating complex queries.
  • No Hallucinations: Because the skill strictly queries the provided sources, it may return empty results if the information is missing. This is a feature, not a bug, ensuring you receive grounded, factual data rather than AI-generated conjecture.
  • Local Execution: The skill operates via direct shell execution; ensure your environment permissions allow the nlm binary to access its auth storage.

Metadata

Author@lhquangit
Stars1656
Views1
Updated2026-02-28
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-lhquangit-notebooklm-cli-cookies": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#notebooklm#knowledge-retrieval#document-analysis#cli-tools
Safety Score: 4/5

Flags: file-read, code-execution, external-api