Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →taracodlabs/youtube-content
YouTube: transcripts, audio/video downloads (yt-dlp, transcript-api)
Passed 20 of 21 test cases with the skill, and 18 of 21 without it.
2 fixed19 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am on a metered internet connection and want to download https://www.youtube.com/watch?v=dQw4w9WgXcQ capped at a maximum height of 720p while keeping the best audio in an MP4 container. How should the format filter string be constructed?
| Checked | Without skill | With skill |
|---|---|---|
| Uses -f containing bestvideo[height<=720]+bestaudio | Missed | Passed |
| Includes --merge-output-format mp4 | Passed | Passed |
The instructions your model reads when the skill loads.
Extract transcripts, download audio or video, and retrieve metadata from YouTube using youtube-transcript-api (Python) and yt-dlp.
pip install youtube-transcript-api
pip install yt-dlp
# Verify
yt-dlp --version
from youtube_transcript_api import YouTubeTranscriptApi
video_id = "dQw4w9WgXcQ" # from youtube.com/watch?v=<id>
transcript = YouTubeTranscriptApi.get_transcript(video_id)
text = " ".join(entry["text"] for entry in transcript)
print(text[:2000])
from youtube_transcript_api import YouTubeTranscriptApi
video_id = "dQw4w9WgXcQ"
test cases passed, vs 18 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.