Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →sonichi/media-transcript
Pull a video's transcript (captions/subtitles) as clean text — the doc-ingest sibling for video. Any task that references a YouTube (or other yt-dlp-supported) URL can consume the spoken content as text instead of being blind to it.
Passed 17 of 21 test cases with the skill, and 14 of 21 without it.
and 3 more in the full report
4 fixed15 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
If a developer mistakenly passes a local disk file `/tmp/lecture.mp4` to the transcript script instead of an online web URL, what numerical exit status does the script return?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies exit code 3 as the return code for local media files. | Missed | Passed |
| Directs the user to skills/audio-transcribe for local file transcription. | Missed | Passed |
The instructions your model reads when the skill loads.
Pull a video's transcript (captions/subtitles) as clean text — the doc-ingest sibling for video. Any task that references a YouTube (or other yt-dlp-supported) URL can consume the spoken content as text instead of being blind to it.
Usage:
python3 skills/media-transcript/scripts/transcript.py <url> [--lang en] [--timestamps] [--json]
Prints the transcript to stdout. --timestamps prefixes blocks with [mm:ss] cue starts (use when the question asks when/after what something was said). --json wraps the result as {"url", "ok", "kind", "text"|"error"} for programmatic callers.
Not for:
skills/audio-transcribe (whisper on the audio track); the script points there and exits 3.--lang preference (default en) with graceful fallback to available English variants.yt-dlp is probed at runtime (PATH binary, else the importable module) — a host without it gets one actionable error naming the install, never a crash (same design language as doc-ingest's extractor probing).Exit codes: 0 transcript printed · 1 failure (no captions / tool error) · 2 bad invocation · 3 handled-elsewhere pointer (local media file).
test cases passed, vs 14 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.