Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
A guide for video and audio manipulation using FFmpeg and FFprobe. Covers transcoding between formats and codecs, applying filters, complex filtergraph operations, metadata editing, and live stream output. Includes ready-to-run shell commands for common tasks like cutting, scaling, watermarking, and batch conversion.
FFmpeg handles decoding, filtering, encoding, and muxing in a single command, removing the need for separate tools for each step in a media processing pipeline.
When to use it
- Converting a video to H.265 to reduce file size before sharing
- Cutting a specific segment out of a long recording
- Burning subtitles into a video file for distribution
- Mixing background music under a voiceover at reduced volume
- Pushing a local video file to a YouTube or Twitch live stream
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: add a watermark image to the bottom-right corner of input.mp4
- 1Identify the input video and watermark image paths
- 2Select the overlay filter with position calculated from main dimensions minus overlay dimensions minus padding
- 3Construct the ffmpeg command using -filter_complex with overlay=main_w-overlay_w-10:main_h-overlay_h-10
- 4Run the command and verify the output file is created
ffmpeg -i input.mp4 -i watermark.png -filter_complex "overlay=main_w-overlay_w-10:main_h-overlay_h-10" output.mp4
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.