skills/notebooklm-connector/SKILL.md
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.
npx skillsauth add mohitagw15856/pm-claude-skills notebooklm-connectorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
NotebookLM is one of the best AI research tools — but it doesn't connect to your other tools. Every notebook requires manual setup inside the NotebookLM UI: open browser, name the notebook, paste URLs one by one, click generate. For researchers, builders, or anyone who works with a high volume of sources, this friction compounds fast.
This skill automates NotebookLM from Claude Code using browser automation via the Claude Chrome extension.
| Requirement | Details | |-------------|---------| | Claude Chrome extension | Must be installed and active in your Chrome browser | | NotebookLM account | Active account at notebooklm.google.com | | Chrome browser | Open and signed into NotebookLM |
If the Chrome extension is not installed, this skill cannot function. There is no fallback — you will need to perform actions manually.
| Input | Required | Notes | |-------|----------|-------| | Action(s) to perform | Yes | What you want done — see Supported Actions below | | Notebook name | Conditional | Required for create; optional for add/generate if a notebook is already open | | Sources | Conditional | Required for add sources action — URLs, file paths, or pasted text | | Output type | Conditional | Required for generate action — mindmap, audio overview, or briefing doc |
| Action | What It Does | |--------|-------------| | Create notebook | Opens NotebookLM, creates a new notebook with the specified title | | Add sources | Adds one or more URLs, files, or text blocks as sources to a notebook | | Generate mindmap | Triggers mindmap generation from the notebook's sources | | Generate audio overview | Requests an audio overview (note: takes several minutes to render) | | Generate briefing doc | Requests a briefing document or slide deck from sources | | List notebooks | Lists your existing notebooks and their source counts | | Open notebook | Navigates to a specific existing notebook by name |
Actions can be chained in a single request: "Create a notebook called 'AI Trends Q2', add these 3 URLs as sources, then generate a mindmap."
After completing actions, Claude returns a structured confirmation:
## NotebookLM — Actions Completed
**Notebook:** [Notebook name]
**URL:** [Direct link to the notebook]
**Actions completed:**
- [x] Created notebook: "[Name]"
- [x] Added source: [URL or file name]
- [x] Added source: [URL or file name]
- [x] Triggered: Mindmap generation
**Status:** [Any pending items — e.g. "Audio overview is generating, check back in 5–10 minutes"]
**Notes:** [Any issues encountered or deviations from the requested actions]
If an action fails, the failed step is marked with [ ] and a reason is provided. See Error Handling below.
Before opening any browser, parse the full request into discrete steps:
If anything is ambiguous — e.g. "add my research sources" without specifying what they are — ask for clarification before proceeding. Do not guess at source URLs.
Confirm browser automation is available via the Claude Chrome extension. If it is not active, stop and report:
"This skill requires the Claude Chrome extension to be installed and active. Please install it at [extension URL] and try again."
Open or navigate to https://notebooklm.google.com. Confirm the user is logged in. If a login screen appears, stop and ask the user to log in manually, then retry.
Execute each action in the sequence requested. After each action, confirm it completed before moving to the next. Do not batch actions speculatively.
Creating a notebook:
Adding a URL source:
Adding pasted text:
Generating a mindmap:
Generating an audio overview:
Return the structured output described in the Output Structure section above, including the direct notebook URL and a checklist of completed/failed actions.
If any step fails, do the following:
Common failures and workarounds:
| Failure | Likely Cause | Manual Workaround | |---------|-------------|-------------------| | Extension not detected | Extension not installed or disabled | Install from Chrome Web Store | | Login screen appears | Session expired | Log in manually, then retry | | Source fails to process | URL is paywalled or blocked | Download content and add as pasted text instead | | Mindmap not available | Source volume too low | Add more sources (NotebookLM requires minimum content) | | Audio overview grayed out | Sources not yet indexed | Wait 1–2 minutes for indexing, then retry |
business
Analyze why deals are won and lost and turn it into an action plan. Use when asked to run a win/loss analysis, review closed-won and closed-lost deals, understand why the team is losing to a competitor, or summarize sales feedback into patterns. Produces a structured win/loss report with themes, win/loss rates by segment and competitor, representative quotes, and prioritized actions for product, marketing, and sales.
development
Route a fuzzy request to the right skill in this library. Use when the user is unsure which skill fits, asks 'which skill should I use for X', describes a task without naming a skill, or when a request could plausibly match several skills. Produces a best-fit recommendation with the inputs to gather, a runner-up with the tie-breaker, and a workflow recipe when the job spans multiple skills.
testing
Triage a vulnerability or scanner finding — assess real severity, exploitability, and how urgently to fix. Use when asked to triage a CVE, prioritize scanner/pentest findings, assess a vuln's risk, or decide what to patch first. Produces a triage verdict: CVSS-informed severity adjusted for your context, exploitability, real risk, a fix/mitigation, and an SLA — so you fix what matters, not just what's red.
development
Stand up a Voice of Customer (VoC) program that turns feedback into action. Use when asked to build a VoC program, design a customer feedback loop, consolidate feedback sources, or set up a closed-loop feedback process. Produces a VoC program design — objectives, feedback sources and channels, a taxonomy, collection and analysis cadence, closed-loop routing, ownership, and success metrics.