ffmpeg-skill vs Larksuite Cli
Both are Grade A and 0.9 points apart, so choose on what you weigh most. ffmpeg-skill leads on transparency and maintenance; Larksuite Cli leads on supply-chain integrity and 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 transparency and maintenance matter most.
- +2.8Maintenance: last push today, against 2d ago
- +1.2Transparency: OSSF Scorecard 7.5 against 6.1
The official Lark/飞书 CLI tool, maintained by the larksuite team — built for humans and AI Agents. Covers core business domains including Messenger, Docs, Base, Sheets, Calendar, Mail, Tasks, Meetings, and more, with 200+ commands and 20+ AI Agent Skills.
Choose Larksuite Cli if supply-chain integrity and adoption matter most.
- +3.1Adoption: 229.3k weekly downloads against 9.5k
- +0.5Safety / Integrity: 100% of recent commits signed, against 55%
Where they differ
1 dimension identical: Identity 18.0 · Full evidence table
An independent, evidence-based trust comparison of ffmpeg-skill and Larksuite Cli, 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 | Larksuite Clilarksuite/cli |
|---|---|---|
| HVTrust score | 90.0 | 89.1 |
| Evidence grade | A | A |
| Coverage grade | B | B |
| Overall rank | #4 | #5 |
| Rank in Agent Skills | #4 | #5 |
| GitHub stars | 5.6k | 18.1k |
| Last updated | today | 2d ago |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 7.5 / 10 | 6.1 / 10 |
| License | MIT | MIT |
| Downloads | 9k/wk | 229k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 19.6 | 20.1 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 14.9 | 13.7 |
| Maintenance / 20 | 20.0 | 17.2 |
| Adoption / 20 | 14.3 | 17.4 |
| 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 →