extract-audio
Installation
SKILL.md
Format Decision Tree
| User wants | Format | Flags | Why |
|---|---|---|---|
| Music, archive quality | FLAC | -c:a flac |
Lossless, no quality loss |
| Music, small + transparent | MP3 VBR | -c:a libmp3lame -q:a 0 |
~200kbps avg, perceptually lossless |
| Podcast / voice | MP3 128k CBR | -c:a libmp3lame -b:a 128k |
Sufficient for speech, universally compatible |
| Mobile / streaming | AAC 192k | -c:a aac -b:a 192k |
Better than MP3 at equivalent bitrate |
| DAW / editing | WAV | -c:a pcm_s16le -ar 44100 |
No encoding loss, widest DAW support |
| Source already target format | Copy | -c:a copy |
No re-encode, instant, lossless |
Process
1. Probe audio streams
ffprobe -v quiet -print_format json -show_streams "$INPUT" | \
python3 -c "
import json, sys
Related skills
More from gupsammy/claudest
create-skill
>
14generate-image
>
12improve-skill
>
10repair-skill
This skill should be used when the user asks to "repair my skill", "audit this skill", "fix my skill", "review skill quality", "check if my skill is well-written", "diagnose skill problems", "what's wrong with this skill", or wants structural correctness fixes. Not for adding features or improving effectiveness — use improve-skill for that. Not for agents — use repair-agent.
8brainstorm
>
7run-research
>
4