Skills youtube-audio-download

Youtube Audio Download

install

source · Clone the upstream repo

git clone https://github.com/openclaw/skills

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/banner90/youtube-audio-download" ~/.claude/skills/clawdbot-skills-youtube-audio-download && rm -rf "$T"

manifest: skills/banner90/youtube-audio-download/SKILL.md

source content

Youtube Audio Download

Usage

python scripts/download_audio.py <URL> [--cookies cookies.txt] [--output-dir dir]

Parameters

```
url
```
(required): YouTube video URL
```
cookies_path
```
(optional): Path to cookies.txt for age-restricted videos
```
output_dir
```
(optional): Output directory, default: "works/audio"

Returns

{
  "success": true,
  "audio_path": "H:/works/audio/video_title-xxxxx.mp3",
  "title": "Video Title",
  "duration": 1200,
  "file_size_mb": 15.5
}

Tools

download_audio

Download YouTube audio to MP3

Workflow Integration

This skill is part of the YouTube translation workflow:

youtube-audio-download: Download audio from YouTube
doubao-launch: Launch Doubao translation window
audio-play: Play the downloaded audio
doubao-capture: Capture translated subtitles

Execution

All skills execute on Windows Python via WSL cross-platform call:

wsl -> python.exe scripts/download_audio.py ...

Error Handling

All skills return JSON with

success

field:

```
success: true
```
- Operation completed
```
success: false
```
- Check
```
error_code
```
and
```
error_message
```

Notes

Windows GUI automation requires visible desktop (no RDP disconnect)
Output files are stored in Windows
```
works/
```
directory
WSL accesses Windows files via
```
/mnt/h/...
```