An advanced AI agent skill enabling complete automation and command-line management of Google NotebookLM workspaces, sources, and queries.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install notebooklm-py-skill
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install notebooklm-py-skill using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is NotebookLM Python Skill?
The NotebookLM Python Skill empowers Openclaw Skills agents to interact directly with Google NotebookLM via a powerful local CLI. By interfacing with notebooks, sources, chats, and artifacts programmatically, this skill enables seamless management of research workflows, source material ingestion, and multi-document synthesis.
Designed with safety and scalability in mind, it provides robust capabilities for technical professionals, researchers, and developers who want to hook their AI coding agents into Google's powerful notebook environment. The skill optimizes parallel agent workflows by bypassing shared contexts and executing precise, targeted API/CLI actions.
NotebookLM Python Skill Use Cases
- Automating the upload of local documents, PDFs, and web URLs directly into specific Google NotebookLM instances.
- Querying complex, multi-source research notebooks programmatically and capturing the structured responses for downstream tasks.
- Orchestrating automated knowledge synthesis where local files are injected as text sources, indexed, and immediately queried.
- Managing notebook artifacts, exports, and metadata across multiple workspaces without manual browser interaction.
How NotebookLM Python Skill Works
- Authentication Verification: The skill first executes an explicit auth test command to ensure secure, active session access to the account.
- Target Identification: It lists or targets specific workspaces using explicit notebook IDs to prevent collision in parallel automated environments.
- Source Aggregation & Syncing: Local attachments, text inputs, or remote URLs are passed to the CLI, uploading them directly into the designated notebook.
- Indexing Wait States: For multi-step automations, the skill monitors and polls specific source IDs to guarantee materials are indexed before proceeding.
- Structured Query & Synthesis: Queries are issued with structured output flags, allowing the AI agent to parse, reference, and synthesize the generated response.
NotebookLM Python Skill Setup
To deploy this skill with your Openclaw Skills agent, ensure the notebooklm CLI is installed and authenticated on your local host system.
Verify your authentication status and list available notebooks using the following commands:
# Check authentication state and output configuration
notebooklm auth check --test --json
# List all active notebooks available to the agent
notebooklm list --json
NotebookLM Python Skill Data Schema & Taxonomy
The skill interacts with local temporary files and organizes structured remote assets according to the following taxonomy:
| Data Component | Format / Location | Description |
|---|---|---|
| Temporary Attachments | /tmp/openclaw-attachments/ |
Temporary staging directory for one-off prompts, PDFs, and source text inputs. |
| CLI Command Responses | JSON | All core data queries use the --json flag to ensure parseable, machine-readable responses. |
| Resource Identification | Unique String IDs | Notebooks, sources, and artifacts are systematically tracked and modified via explicit unique IDs (-n NOTEBOOK_ID). |
NotebookLM Python Skill Advanced Features
- Parallel Workflow Isolation: Rejects global context switches in favor of strict, ID-driven targeting to support multi-agent parallel operations.
- Asynchronous Source Syncing: Includes automated wait hooks (
source wait) to pause execution pipelines until complex documents finish processing. - Destructive Action Guardrails: Built-in interactive blocks that prompt for user confirmation prior to long-running generations or resource deletions.
- Automated Cleanup Pipelines: Self-cleaning workspace handling that purges temporary prompt files and attachment exports post-execution.
SKILL.md
Loading
Related Openclaw Skills
Video Metadata Analyzer
An automated multi-stage video analysis pipeline that processes parallel visual frames and audio transcriptions to synthesize optimized, publish-ready metadata for Bilibili.
Autoresearch Loop
A highly structured, metric-driven modify-verify-decide optimization loop with strict safety gates and approval contracts for AI coding agents.
AI Agent Usage Stats
A zero-dependency, local Python CLI tool to monitor token usage and statistics for popular AI coding agents like Hermes, Claude Code, CodeX, and OpenClaw.
OPC Playbook (One-Person Company)
The OPC Playbook is a dual-mode strategic framework designed to help solo founders rigorously evaluate startup viability and systematically execute an AI-native business model.
Hashmob Integration
An Openclaw skill that enables AI agents to query hashlists, run automated hashcat attacks, and manage Hashmob resources.
Asphalt & Driveway Sealing Marketing Kit
A specialized marketing generation toolkit designed to craft compliant, conversion-driven campaigns for asphalt and driveway sealing contractors.
Featured*
