Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nicepkg/transcribe-and-analyze
Transcribe audio and video from URLs (YouTube, direct media links) using WhisperKit locally. Optionally analyze transcripts with AI when explicitly requested.
Passed 22 of 22 test cases with the skill, and 7 of 22 without it.
and 25 more in the full report
15 fixed7 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
I have a transcript located at whisper-transcriptions/interview.md. I want to analyze it locally using Ollama with the llama3.2 model. What is the precise command?
| Checked | Without skill | With skill |
|---|---|---|
| Runs python3 scripts/analyze_transcript.py on whisper-transcriptions/interview.md | Missed | Passed |
| Includes the --local flag in the command | Missed | Passed |
| Includes --model llama3.2 in the command | Missed | Passed |
The instructions your model reads when the skill loads.
Local transcription of audio/video content using WhisperKit. Analysis is available on request using OpenAI or local Ollama.
python3 scripts/transcribe.py "https://youtube.com/watch?v=..."
python3 scripts/transcribe.py "https://youtube.com/watch?v=..."
python3 scripts/analyze_transcript.py whisper-transcriptions/video.md
python3 scripts/transcribe.py "https://youtube.com/watch?v=..."
python3 scripts/analyze_transcript.py whisper-transcriptions/video.md --local
# Basic
python3 scripts/transcribe.py "URL"
# Custom output directory
python3 scripts/transcribe.py "URL" --output-dir "/path/to/save"
test cases passed, vs 7 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.