메뉴
Extracts transcripts from YouTube videos using a bundled Node.js script backed by yt-dlp. Returns cleaned transcript output with timestamps in text or JSON. Use when the user says `$yt-transcript <url>` or asks for a YouTube transcript or cleaned captions.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | youtube-transcript |
| description | Extracts transcripts from YouTube videos using a bundled Node.js script backed by yt-dlp. Returns cleaned transcript output with timestamps in text or JSON. Use when the user says `$yt-transcript <url>` or asks for a YouTube transcript or cleaned captions. |
Use this skill when the user asks for a YouTube transcript.
node <skill-dir>/scripts/youtube-transcript.js <url> [--lang <lang>] [--format json]
The script handles downloading, parsing, and cleaning in one step — no separate download/parse phases needed.
node is preferred, but bun and deno works as well. Use whatever is available in the system.
text (default) — one timestamped segment per line:
[00:01] All right, so here we are, in front of the elephants
[00:05] the cool thing about these guys is that they have really long trunks
json — array of segments with start, end, and text:
[
{"start": 1.2, "end": 3.36, "text": "All right, so here we are..."},
{"start": 5.32, "end": 7.97, "text": "the cool thing about..."}
]
node_modules needed at runtime).