transcript-fetcher

name	transcript-fetcher
description	Use FIRST for ANY request to transcribe a video/audio URL or get its subtitles, captions, or text — before yt-dlp, ffmpeg, or a manual whisper run. Returns clean plain text plus a JSON stat sidecar; uses embedded captions when present, else falls back to local ASR automatically. Sources: YouTube, Vimeo, X/Twitter (incl. Broadcasts/Spaces), Skool lessons, Yandex VH/Strm webinars. Also triggers on расшифровка, транскрипт, субтитры.
tier	2
version	1.4
status	active

Transcript Fetcher

Purpose: Given a video URL, produce a clean plain-text transcript ready for downstream summarization or analysis. Single responsibility: fetch + clean. Composes well with summarizing-meetings (run this first, then feed the resulting .txt to that skill).

Dependencies: yt-dlp is vendored in scripts/.venv (installed by scripts/install.sh) — it is NOT on $PATH and never will be. Do NOT which yt-dlp, pip install yt-dlp, or brew install yt-dlp globally — a missing entry does not mean yt-dlp is absent, it means the check was wrong; this exact false-negative once caused a manual out-of-skill workaround. The two canonical readiness probes are and (§4 Script Contract; the latter also reports ffmpeg + ASR backends — see the ASR portability note under §5 Safety Boundaries). Callers that shell in (e.g. a downstream integrator) MUST invoke the directly (), never a .