Registry › Compare › Notebooklm Py vs Vercel Skills

Notebooklm Py vs Vercel Skills

Both are Grade A and 1.2 points apart, so choose on what you weigh most. Notebooklm Py leads on maintenance and transparency; Vercel Skills leads on adoption and supply-chain integrity.

A Notebooklm Py 88.7

Unofficial Python API and agentic skill for Google Gemini Notebook. Full programmatic access to NotebookLM's features—including capabilities the web UI doesn't expose—via Python, CLI, and AI agents like Claude Code, Codex, and OpenClaw.

teng-lin/notebooklm-py · #4 overall · #4 Agent Skills · coverage B (3/5)

Choose Notebooklm Py if maintenance and transparency matter most.

+2.1Maintenance: last push today, against 8d ago
+0.8Transparency: OSSF Scorecard 6.0 against 5.1

A Vercel Skills 89.9

The open agent skills tool - npx skills

vercel-labs/skills · #3 overall · #3 Agent Skills · coverage B (3/5)

Choose Vercel Skills if adoption and supply-chain integrity matter most.

+3.5Adoption: 5.0M weekly downloads against 31.7k
+2.5Safety / Integrity: 100% of recent commits signed, against 29%

Where they differ

16.4

Safety / IntegrityVercel Skills +2.5

18.9

13.6

TransparencyNotebooklm Py +0.8

12.8

20.0

MaintenanceNotebooklm Py +2.1

17.9

16.3

AdoptionVercel Skills +3.5

19.8

+4.4

Runtime calibrationNotebooklm Py +1.9

+2.5

1 dimension identical: Identity 18.0 · Full evidence table

An independent, evidence-based trust comparison of Notebooklm Py and Vercel Skills, two Agent Skills projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.

Full evidence

Signal	Notebooklm Pyteng-lin/notebooklm-py	Vercel Skillsvercel-labs/skills
HVTrust score	88.7	89.9
Evidence grade	A	A
Coverage grade	B	B
Overall rank	#4	#3
Rank in Agent Skills	#4	#3
GitHub stars	19.5k	32.5k
Last updated	today	8d ago
Build provenance	Yes	Yes
OSSF Scorecard	6.0 / 10	5.1 / 10
License	MIT	MIT
Downloads	32k/wk	5.0M/wk
Trust dimensions (points earned)
Safety / integrity / 25	16.4	18.9
Identity & provenance / 18	18.0	18.0
Transparency / 17	13.6	12.8
Maintenance / 20	20.0	17.9
Adoption / 20	16.3	19.8
Runtime capability surface (full matrix)
MCP server	Implemented	—
External providers	—	—
Requires API keys	No	No
Plugin surface	—	—
Provenance drift	Match	Match

Open in the live compare tool → Notebooklm Py profile Vercel Skills profile More Agent Skills →

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.3 →