notebooklm

What This Skill Does

The NotebookLM local file analyzer empowers your OpenClaw agent to leverage Google's NotebookLM for deep, source-grounded document analysis. Rather than relying on generic AI, this skill allows you to upload business-critical files—such as long-form strategy documents, quarterly financial reports, and complex legal proposals—into a dedicated environment. The AI then processes these specific documents to provide highly contextual insights, risk assessments, and actionable intelligence, ensuring every answer is anchored directly to your own provided material.

Installation

To integrate this skill, run the following command in your terminal: clawhub install openclaw/skills/skills/seanphan/notebooklm

Ensure you complete the setup process once installed by running: python scripts/setup_notebooklm.py This initializes the connection to your local file system and prepares the agent to handle document uploads.

Use Cases

• Strategic Planning: Automatically synthesize multiple strategy documents to identify core competitive advantages and internal implementation hurdles.
• Financial Reporting: Parse heavy financial reports to isolate ROI projections, liquidity risks, and growth opportunities without manual skimming.
• Compliance & Risk: Quickly query documentation to identify regulatory gaps, potential liability, or required mitigation strategies based on established organizational policies.
• Market Research: Group related market study files to extract unified takeaways and summary reports suitable for executive briefings.

Example Prompts

1. "Analyze the attached strategy plan and create a list of the 5 most critical risks that could impact our Q3 goals."
2. "Review the provided financial documents and summarize the key ROI projections versus our original budget."
3. "Based on our compliance handbook, identify any potential gaps in our current project workflow and suggest mitigation steps."

Tips & Limitations

• Formatting Matters: Ensure your local files are in text-based formats (like .md or .txt) for the best analysis results. Cleanly formatted files yield more accurate insights.
• Batching: Use the batch_analyzer.py tool to organize large folders before uploading. This helps the AI contextually understand the relationships between multiple files.
• Grounding: Always remember that the AI’s answers are only as good as the source data provided. If an answer seems broad, check your uploaded file content to ensure sufficient detail is present.
• Notebook Limits: Keep in mind that individual notebooks have character limits; for massive datasets, consider breaking files into thematic batches.