Agent Skills

video-edit

Edit videos locally using ffmpeg. Trim, concat, resize, speed, overlay, extract audio, compress, and convert. Use when: (1) Trimming or cutting video segments, (2) Concatenating multiple clips, (3) Resizing video for social platforms, (4) Extracting or replacing audio, (5) Compressing video, (6) Converting video formats, (7) Getting video info.

Install

npx skills add https://github.com/calesthio/openmontage --skill video-edit
SKILL.md

Video Edit

Edit videos locally by running ffmpeg/ffprobe directly. No wrapper scripts needed.

Prerequisites

Install ffmpeg (includes ffprobe):

# macOS
brew install ffmpeg

# Ubuntu/Debian
sudo apt update && sudo apt install -y ffmpeg

# Verify
ffmpeg -version && ffprobe -version

Quick Reference

Get video info

ffprobe -v quiet -print_format json -show_format -show_streams video.mp4

Trim

ffmpeg -y -ss 00:00:30 -to 00:01:45 -i video.mp4 -c copy trimmed.mp4

Concatenate clips

# 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

Resize for platform

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

Change speed

# 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

Extract audio

ffmpeg -y -i video.mp4 -vn -acodec libmp3lame audio.mp3

Replace audio

ffmpeg -y -i video.mp4 -i audio.mp3 -c:v copy -map 0:v:0 -map 1:a:0 -shortest output.mp4

Compress

ffmpeg -y -i video.mp4 -crf 23 -preset medium -c:a copy compressed.mp4

Convert format

ffmpeg -y -i video.mov output.mp4

Add image overlay

# 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 Presets

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
Instagram 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

Tips

  • Always use -y to overwrite output without prompting.
  • Use -c copy when you only need to cut/join (no re-encoding, very fast).
  • Lower CRF = better quality, larger file. Range 18-28 is typical; 23 is the default.
  • For detailed recipes and flag explanations, see references/operations.md.

Related skills

video-editgenmedia-labs715KEdit existing video on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Wan 2.7 Edit-Video (general restyle / background swap / packaging swap, identity + motion preservation), Kling 2.6 Pro Motion Control (transfer precise motion from a reference video to a target character), or Lucy Edit Restyle (lightweight identity-stable restyle / outfit swap). Bundles each model's documented prompting patterns so the skill gets shai-video-generationgenmedia-labs714KGenerate AI videos on RunComfy via the `runcomfy` CLI — a smart router across the full video-model catalog: HappyHorse 1.0 (Arena #1, native in-pass audio), Wan-AI Wan 2-7 (open weights, audio-driven lip-sync), ByteDance Seedance v2 / 1-5 / 1-0 (multi-modal cinematic), Kling 3.0 / 2-6, Google Veo 3-1, MiniMax Hailuo 2-3, ByteDance Dreamina 3-0. Covers text-to-video (t2v), image-to-video (i2v), and Veo's video-extend endpoint. The skill picks the right model for the user's intent (Arena-#1 qualitai-musicgenmedia-labs714KGenerate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right model fimage-to-videogenmedia-labs713KAnimate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio, identity preservation) for general animations, Wan 2.7 with `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image + reference video + reference audio. Bundles each model's documented prompting patterns so the caller gets sharper output without burning iterat

Search skills and MCP servers

Fuzzy search across 23,137 skills and servers