beam-ai-team/notebooklm-connect
skills/integrations/notebooklm/notebooklm-connect/SKILL.md
notebooklm, create notebook, audio overview, podcast.
content-media
Updated Jun 4, 2026
$ install --global
skillsauthnpx skillsauth add beam-ai-team/beam-next-skills notebooklm-connectInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 4, 2026, 4:29 AM146.2s1 file scanned
SKILL.md
- name:
- notebooklm-connect
- version:
- 1.0
- description:
- notebooklm, create notebook, audio overview, podcast.
- category:
- integrations
- platform:
- NotebookLM
- updated:
- 2026-02-24
- visibility:
- public
NotebookLM Connect
Meta-skill for NotebookLM Enterprise operations. Routes to appropriate skills based on user intent.
Pre-Flight Check (ALWAYS FIRST)
Before any operation, verify configuration:
uv run python 00-system/skills/notebooklm/notebooklm-master/scripts/check_notebooklm_config.py --json
Parse ai_action field:
| ai_action | What to Do |
|-----------|------------|
| proceed_with_operation | Continue with user's request |
| install_gcloud | Guide: "Install gcloud from https://cloud.google.com/sdk/docs/install" |
| run_gcloud_auth | Run: gcloud auth login |
| configure_project | Ask for project number, save to .env |
| run_setup_wizard | Run: python .../setup_notebooklm.py |
Workflow Routing
Match user intent to appropriate workflow:
Workflow 1: Create Notebook
Triggers: "create notebook", "new notebook", "make notebook"
Action:
uv run python 00-system/skills/notebooklm/notebooklm-create-notebook/scripts/create_notebook.py --title "TITLE"
Workflow 2: List Notebooks
Triggers: "list notebooks", "show notebooks", "my notebooks", "recent notebooks"
Action:
uv run python 00-system/skills/notebooklm/notebooklm-list-notebooks/scripts/list_notebooks.py
Workflow 3: Get Notebook Details
Triggers: "get notebook", "show notebook", "notebook details"
Action:
uv run python 00-system/skills/notebooklm/notebooklm-get-notebook/scripts/get_notebook.py --notebook-id "ID"
Workflow 4: Delete Notebooks
Triggers: "delete notebook", "remove notebook"
Action:
uv run python 00-system/skills/notebooklm/notebooklm-delete-notebooks/scripts/delete_notebooks.py --notebook-ids "ID1,ID2"
Workflow 5: Share Notebook
Triggers: "share notebook", "give access", "add collaborator"
Action:
uv run python 00-system/skills/notebooklm/notebooklm-share-notebook/scripts/share_notebook.py --notebook-id "ID" --email "[email protected]" --role "READER"
Workflow 6: Add Sources
Triggers: "add sources", "add to notebook", "add url", "add youtube", "add drive file"
Action:
# For web URL
uv run python 00-system/skills/notebooklm/notebooklm-add-sources/scripts/add_sources.py --notebook-id "ID" --type web --url "https://..."
# For YouTube
uv run python 00-system/skills/notebooklm/notebooklm-add-sources/scripts/add_sources.py --notebook-id "ID" --type youtube --url "https://youtube.com/..."
# For text
uv run python 00-system/skills/notebooklm/notebooklm-add-sources/scripts/add_sources.py --notebook-id "ID" --type text --content "Your text..."
# For Google Drive
uv run python 00-system/skills/notebooklm/notebooklm-add-sources/scripts/add_sources.py --notebook-id "ID" --type drive --resource-id "DRIVE_FILE_ID"
Workflow 7: Upload File
Triggers: "upload file", "upload pdf", "add file", "upload document"
Action:
uv run python 00-system/skills/notebooklm/notebooklm-upload-file/scripts/upload_file.py --notebook-id "ID" --file "/path/to/file.pdf"
Workflow 8: Get Source Details
Triggers: "get source", "source details", "show source"
Action:
uv run python 00-system/skills/notebooklm/notebooklm-get-source/scripts/get_source.py --notebook-id "ID" --source-id "SOURCE_ID"
Workflow 9: Delete Sources
Triggers: "delete sources", "remove sources", "clear sources"
Action:
uv run python 00-system/skills/notebooklm/notebooklm-delete-sources/scripts/delete_sources.py --notebook-id "ID" --source-ids "S1,S2"
Workflow 10: Create Audio Overview
Triggers: "create audio", "generate podcast", "audio overview", "make podcast"
Action:
uv run python 00-system/skills/notebooklm/notebooklm-create-audio/scripts/create_audio.py --notebook-id "ID" [--focus "Topic focus"] [--language "en"]
Workflow 11: Delete Audio Overview
Triggers: "delete audio", "remove podcast", "delete audio overview"
Action:
uv run python 00-system/skills/notebooklm/notebooklm-delete-audio/scripts/delete_audio.py --notebook-id "ID"
Common Patterns
Create notebook and add sources
# 1. Create notebook
uv run python .../create_notebook.py --title "Research Project"
# Returns: notebookId: abc123
# 2. Add sources
uv run python .../add_sources.py --notebook-id abc123 --type web --url "https://..."
uv run python .../upload_file.py --notebook-id abc123 --file "/path/to/paper.pdf"
# 3. Generate audio
uv run python .../create_audio.py --notebook-id abc123 --focus "Key findings"
Full research workflow
- Create notebook with descriptive title
- Add multiple sources (PDFs, URLs, YouTube)
- Wait for sources to process
- Generate audio overview
- Share with team
Error Handling
On any error, load appropriate reference:
| Error Type | Reference to Load |
|------------|-------------------|
| Authentication | notebooklm-master/references/authentication.md |
| Permission denied | notebooklm-master/references/setup-guide.md |
| API errors | notebooklm-master/references/error-handling.md |
| Unknown | notebooklm-master/references/api-reference.md |
Context Caching
After listing notebooks, cache the IDs for quick reference:
cached_notebooks:
- id: abc123
title: "Research Project"
- id: def456
title: "Meeting Notes"
When user says "add to Research Project", use cached ID.
Version: 1.0 Created: 2025-12-27
Related Skills
beam-ai-team/skills/general/taste-skill
development
VerifiedTrustedCommunity
--- name: taste-skill type: skill version: '1.0' author: Leonxlnx (packaged by Zhichao Li) category: general tags: - frontend - design - anti-slop - landing-page updated: '2026-06-11' visibility: public description: Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check. license: MIT.
SKILL.mdUpdated Jun 12, 2026
beam-ai-team/numbers
development
VerifiedTrustedCommunity
Use when communicating quantitative information in any form — Slack updates, emails, reports, decks, dashboards, landing pages, product UI, public talks. Covers two integrated layers: (1) making numbers semantically meaningful (translation, anchoring, simplification, story-pairing) and (2) showing numbers cleanly (chart vs table vs prose, chart-by-message, pre-attentive emphasis, color discipline, decluttering). Distilled and integrated from *Show Me the Numbers* (Stephen Few) and *Make Numbers Count* (Chip Heath & Karla Starr). Not for raw data analysis or statistics — this is about communication of numbers, not their derivation.
SKILL.mdUpdated Jun 12, 2026
beam-ai-team/impeccable
development
VerifiedTrustedCommunity
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
SKILL.mdUpdated Jun 12, 2026
beam-ai-team/beam-teach
tools
VerifiedTrustedCommunity
Stateful multi-session tutor adapted for Beam — teach a stakeholder to understand, trust, and operate a specific agent, or teach a Solution Engineer a client's business process for delivery. Grounds every lesson in Knowledge Hub sources (real agent graphs, real tasks, transcripts, Linear) before any web resource. Also works for any general topic. Trigger on "teach me", "beam teach", "教我", "onboard <person> on <agent>", "help <stakeholder> understand the agent", "learn this client's process".
SKILL.mdUpdated Jun 12, 2026