Notebooklm Py vs Skill Scanner
An independent, evidence-based trust comparison of Notebooklm Py and Skill Scanner, two Agent Skills projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Skill Scanner leads on trust — 82.6/100 (Grade A) vs 78.7/100 (Grade B), a 3.9-point gap. Full breakdown below.
| Signal | Notebooklm Pyteng-lin/notebooklm-py | Skill Scannercisco-ai-defense/skill-scanner |
|---|---|---|
| HVTrust score | 78.7 | 82.6 |
| Evidence grade | B | A |
| Coverage grade | B | B |
| Overall rank | #8 | #4 |
| Rank in Agent Skills | #8 | #4 |
| GitHub stars | 19.1k | 2.5k |
| Last updated | today | 2d ago |
| Build provenance | Yes | Yes |
| OSSF Scorecard | — | 6.1 / 10 |
| License | MIT | NOASSERTION |
| Downloads | 37k/wk | 118k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 10.1 | 19.9 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 8.5 | 13.7 |
| Maintenance / 20 | 20.0 | 15.5 |
| Adoption / 20 | 16.4 | 14.9 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | — |
| External providers | — | 5 — Amazon Bedrock, Anthropic, Google Gemini, … |
| Requires API keys | No | Yes |
| Plugin surface | — | — |
| Provenance drift | Match | Match |
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 →