ffmpeg-skill vs Vercel Skills
Both are Grade A and 1.3 points apart, so choose on what you weigh most. ffmpeg-skill leads on supply-chain integrity and transparency; Vercel Skills leads on adoption.
Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions, reframe, loudness, platform exports. No cloud, no API keys.
Choose ffmpeg-skill if supply-chain integrity and transparency matter most.
- +2.2Transparency: OSSF Scorecard 7.5 against 4.9
- +1.0Safety / Integrity: OSSF Scorecard 7.5 against 4.9
The open agent skills tool - npx skills
Choose Vercel Skills if adoption matters most.
- +5.7Adoption: 5.1M weekly downloads against 9.5k
Where they differ
1 dimension identical: Identity 18.0 · Full evidence table
An independent, evidence-based trust comparison of ffmpeg-skill 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 | ffmpeg-skillkajisho5/ffmpeg-skill | Vercel Skillsvercel-labs/skills |
|---|---|---|
| HVTrust score | 90.0 | 91.3 |
| Evidence grade | A | A |
| Coverage grade | B | B |
| Overall rank | #4 | #2 |
| Rank in Agent Skills | #4 | #2 |
| GitHub stars | 5.6k | 39.4k |
| Last updated | today | 3d ago |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 7.5 / 10 | 4.9 / 10 |
| License | MIT | MIT |
| Downloads | 9k/wk | 5.1M/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 19.6 | 18.6 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 14.9 | 12.7 |
| Maintenance / 20 | 20.0 | 19.8 |
| Adoption / 20 | 14.3 | 20.0 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | — |
| External providers | 2 — Anthropic, Google Gemini | — |
| Requires API keys | No | No |
| Plugin surface | plugins | — |
| 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 v4.4 →