Edit videos locally by running ffmpeg/ffprobe directly. No wrapper scripts needed.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionvideo-editExecute the skills CLI command in your project's root directory to begin installation:
Fetches video-edit from heygen-com/skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate video-edit. Access via /video-edit in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
0
total installs
0
this week
103
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
103
stars
Edit videos locally by running ffmpeg/ffprobe directly. No wrapper scripts needed.
Install ffmpeg (includes ffprobe):
# macOS
brew install ffmpeg
# Ubuntu/Debian
sudo apt update && sudo apt install -y ffmpeg
# Verify
ffmpeg -version && ffprobe -version
ffprobe -v quiet -print_format json -show_format -show_streams video.mp4
ffmpeg -y -ss 00:00:30 -to 00:01:45 -i video.mp4 -c copy trimmed.mp4
# 1. Create a file list
printf "file '%s'\n" clip1.mp4 clip2.mp4 clip3.mp4 > list.txt
# 2. Concat with stream copy
ffmpeg -y -f concat -safe 0 -i list.txt -c copy joined.mp4
ffmpeg -y -i video.mp4 \
-vf "scale=1080:1920:force_original_aspect_ratio=decrease,pad=1080:1920:(ow-iw)/2:(oh-ih)/2:black" \
-c:a copy tiktok.mp4
# 2x faster
ffmpeg -y -i video.mp4 -filter:v "setpts=0.5*PTS" -filter:a "atempo=2.0" fast.mp4
# 0.5x (slow motion)
ffmpeg -y -i video.mp4 -filter:v "setpts=2.0*PTS" -filter:a "atempo=0.5" slow.mp4
ffmpeg -y -i video.mp4 -vn -acodec libmp3lame audio.mp3
ffmpeg -y -i video.mp4 -i audio.mp3 -c:v copy -map 0:v:0 -map 1:a:0 -shortest output.mp4
ffmpeg -y -i video.mp4 -crf 23 -preset medium -c:a copy compressed.mp4
ffmpeg -y -i video.mov output.mp4
# Logo in top-right corner
ffmpeg -y -i video.mp4 -i logo.png \
-filter_complex "overlay=W-w-10:10" -c:a copy watermarked.mp4
| Platform | Resolution | Scale + pad filter |
|---|---|---|
| TikTok | 1080 x 1920 | scale=1080:1920:force_original_aspect_ratio=decrease,pad=1080:1920:(ow-iw)/2:(oh-ih)/2:black |
| YouTube | 1920 x 1080 | scale=1920:1080:force_original_aspect_ratio=decrease,pad=1920:1080:(ow-iw)/2:(oh-ih)/2:black |
| 1080 x 1350 | scale=1080:1350:force_original_aspect_ratio=decrease,pad=1080:1350:(ow-iw)/2:(oh-ih)/2:black |
|
| Square | 1080 x 1080 | scale=1080:1080:force_original_aspect_ratio=decrease,pad=1080:1080:(ow-iw)/2:(oh-ih)/2:black |
| Twitter/X | 1920 x 1080 | scale=1920:1080:force_original_aspect_ratio=decrease,pad=1920:1080:(ow-iw)/2:(oh-ih)/2:black |
Use the filter with: ffmpeg -y -i input.mp4 -vf "<filter>" -c:a copy output.mp4
-y to overwrite output without prompting.-c copy when you only need to cut/join (no re-encoding, very fast).references/operations.md.Prerequisites
Time Estimate
15-45 minutes depending on use case complexity
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
heygen-com/skills
affaan-m/everything-claude-code
remotion-dev/skills
supercent-io/skills-template
zrong/skills
davila7/claude-code-templates
Solid pick for teams standardizing on skills: video-edit is focused, and the summary matches what you get after install.
Useful defaults in video-edit — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
video-edit is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
I recommend video-edit for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
video-edit fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
video-edit fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
Registry listing for video-edit matched our evaluation — installs cleanly and behaves as described in the markdown.
I recommend video-edit for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
video-edit has been reliable in day-to-day use. Documentation quality is above average for community skills.
Useful defaults in video-edit — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
showing 1-10 of 64