Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →understudy-ai/songsee
Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.
Passed 22 of 22 test cases with the skill, and 3 of 22 without it.
and 20 more in the full report
19 fixed3 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 19 test cases the skill fixed. Same model, same prompt, with and without the skill.
Extract an audio spectral graphic for 'live.wav' spanning 30 seconds starting from 120 seconds in, saving directly to 'excerpt.jpg'.
| Checked | Without skill | With skill |
|---|---|---|
| Uses the songsee command-line tool. | Missed | Passed |
| Passes --start 120 --duration 30. | Missed | Passed |
| Passes -o excerpt.jpg. | Passed | Passed |
The instructions your model reads when the skill loads.
Generate spectrograms + feature panels from audio.
Quick start
songsee track.mp3songsee track.mp3 --viz spectrogram,mel,chroma,hpss,selfsim,loudness,tempogram,mfcc,fluxsongsee track.mp3 --start 12.5 --duration 8 -o slice.jpgcat track.mp3 | songsee - --format png -o out.pngCommon flags
--viz list (repeatable or comma-separated)--style palette (classic, magma, inferno, viridis, gray)--width / --height output size--window / --hop FFT settings--min-freq / --max-freq frequency range--start / --duration time slice--format jpg|pngNotes
--viz renders a grid.test cases passed, vs 3 / 22 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.