
Youtube Transcribe Skill
This does exactly what it says: pulls transcripts from YouTube videos and saves them locally. It tries the fast path first with yt-dlp if you have it installed, complete with cookie handling to dodge sign-in walls. If that's not available, it falls back to browser automation through chrome-devtools-mcp, clicking through the UI to expand descriptions and extract transcripts via DOM injection. The browser fallback is clever but requires setup. You'll want this when you need video content in text form for analysis, documentation, or just archiving what someone said. Works with multiple subtitle languages and handles the timestamp formatting for you.
- skills.sh installs
- 114
- GitHub stars
- 249
- last updated
- Mar 9, 2026
Install
$ npx -y skills add feiskyer/codex-settings --skill youtube-transcribe-skill --agent claude-codeInstalls into .claude/skills of the current project.
Files
YouTube Transcript Extraction
Use the bundled scripts/transcribe_youtube.py wrapper for the primary workflow. It downloads subtitles with yt-dlp, selects the preferred language, converts WebVTT cues into timestamped plain text, and reports the output path and line count.
Requirements
- Install
yt-dlpand confirmyt-dlp --versionsucceeds. - Resolve the absolute directory containing this
SKILL.md; refer to it as<skill-dir>. - Keep the output in the user's current working directory unless they request another location.
The Python wrapper itself uses only the standard library. It can display --help without yt-dlp being installed.
Primary workflow
Run without browser cookies first:
python3 "<skill-dir>/scripts/transcribe_youtube.py" \
"<youtube-url>" \
--output-dir "$PWD"
The default language preference is Simplified Chinese, Traditional Chinese, other Chinese variants, then English. Override it when the user requests another language:
python3 "<skill-dir>/scripts/transcribe_youtube.py" \
"<youtube-url>" \
--languages "ja.*,en.*" \
--output-dir "$PWD"
Sponsors
Details
- Repository
- github.com/feiskyer/codex-settings
- License
- MIT
- First seen
- Jun 11, 2026