video-frames
Extract frames or short clips from videos using ffmpeg.
78
Quality
70%
Does it follow best practices?
Impact
100%
1.31xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./openclaw/skills/video-frames/SKILL.mdEvaluation results
100%
30%Demo Reel Highlights for Stakeholder Review
Timestamp frame extraction for sharing
Uses frame.sh script
100%
100%
Three --time invocations
0%
100%
HH:MM:SS timestamp format
100%
100%
JPEG output format
100%
100%
--out flag present
0%
100%
Output images produced
100%
100%
Source video cleaned up
100%
100%
Without context: $0.2681 · 1m 48s · 17 turns · 19 in / 3,857 out tokens
With context: $0.5806 · 3m 10s · 29 turns · 983 in / 7,583 out tokens
100%
30%Extracting UI Screenshots from a Screen Recording for Product Docs
UI frame extraction for documentation
Uses frame.sh script
100%
100%
Uses --index flag
0%
100%
PNG output format
100%
100%
Three frames extracted
100%
100%
--out flag present
0%
100%
Frame 0 extracted
100%
100%
Source video cleaned up
100%
100%
Without context: $0.2386 · 1m 29s · 19 turns · 23 in / 3,836 out tokens
With context: $0.4189 · 1m 44s · 24 turns · 1,160 in / 4,876 out tokens
100%
10%Video Library Poster Image Generator
Batch first-frame poster generation
Uses frame.sh script
100%
100%
First-frame extraction method
100%
100%
JPEG output format
100%
100%
--out flag present
0%
100%
Three posters produced
100%
100%
Poster filenames match video names
100%
100%
Without context: $0.2364 · 1m 12s · 19 turns · 24 in / 2,913 out tokens
With context: $0.4533 · 1m 48s · 27 turns · 981 in / 5,022 out tokens
- Repository
- trpc-group/trpc-agent-go
- Commit
8763418
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.