PlaygroundCatalog › NotebookLM Connector
NC

NotebookLM Connector

🟡 Experimental🕐 updated 2026-06-08 🔷 SkillSpec L3 pm-cross

Automates NotebookLM from Claude Code using browser automation via the Claude Chrome extension — creating notebooks, adding sources, and triggering outputs without manual clicking. Use when you want to create a NotebookLM notebook, add URLs or documents as sources, or generate mindmaps, audio overviews, or briefing docs programmatically. Produces a confirmed checklist of completed actions and a direct link to the notebook.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

🗣 Say this to your agent

“Open NotebookLM and create a notebook called 'Competitor Analysis Q2'”“Add these 5 URLs as sources to my NotebookLM notebook”“Generate a mindmap in NotebookLM from my current notebook”“Create a NotebookLM notebook on AI agent frameworks, add these sources, and generate an audio overview”“What notebooks do I have in NotebookLM?”

What to give it

Action(s) to perform — What you want done — see Supported Actions below
Notebook name — Required for create; optional for add/generate if a notebook is already open
Sources — Required for add sources action — URLs, file paths, or pasted text
Output type — Required for generate action — mindmap, audio overview, or briefing doc

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

User's full request was parsed into discrete steps before any browser action was taken
Ambiguous source references were clarified before proceeding
Each action was confirmed complete before the next one started
Direct notebook URL is included in the output
If audio overview was triggered, user was informed of the render delay
Any failed steps are explicitly reported with the specific failure reason
Manual workaround was offered for any step that failed
Output checklist accurately reflects what was completed vs. what failed

⚠️ What it refuses to do

Do not proceed with any browser action before the full request has been parsed into discrete steps — ambiguous source references must be clarified before navigating
Do not guess at source URLs if the user says "add my research sources" without specifying them — ask for the explicit list before starting
Do not batch actions speculatively — each action must be confirmed complete before the next one begins to avoid compounding failures
Do not wait for audio overview rendering to complete — audio overviews take 5–15 minutes server-side; report the trigger and move on rather than blocking the session
Do not attempt this skill if the Claude Chrome extension is not active — report the missing prerequisite immediately rather than attempting browser steps that will fail

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Start with

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="notebooklm-connector"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

NotebookLM Connector is one of 1174 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog