Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.
77
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Multi-panel viz grid
Uses songsee command
0%
100%
--viz flag present
0%
100%
Multiple viz types specified
0%
100%
Valid viz type names
0%
100%
Comma-separated or repeated flag syntax
0%
100%
Output file specified
0%
100%
Grid understanding
0%
100%
No separate call per panel
100%
100%
Correct input file usage
0%
100%
--format flag used
0%
0%
Without context: $0.5717 · 2m 48s · 29 turns · 35 in / 8,811 out tokens
With context: $0.2665 · 50s · 18 turns · 177 in / 2,816 out tokens
Time slice and style options
Uses songsee command
0%
100%
--start flag used
0%
100%
--duration flag used
0%
100%
--style flag used
0%
100%
Valid style value
0%
100%
--format flag used
0%
100%
Output file named with -o
0%
100%
--width or --height specified
0%
100%
Start/duration values are numeric
0%
100%
Audio file as positional arg
0%
100%
Script accepts configurable params
100%
100%
Without context: $0.2483 · 58s · 17 turns · 21 in / 3,540 out tokens
With context: $0.4771 · 1m 29s · 30 turns · 282 in / 5,059 out tokens
Stdin pipeline and frequency range
Uses songsee command
0%
100%
Stdin input with `-`
0%
100%
Audio piped via stdin
0%
100%
--format flag in stdin mode
0%
100%
--min-freq flag used
0%
100%
--max-freq flag used
0%
100%
--window flag used
0%
100%
--hop flag used
0%
100%
Output file specified with -o
0%
100%
Without context: $0.4484 · 2m 10s · 24 turns · 30 in / 7,505 out tokens
With context: $0.2892 · 1m 2s · 17 turns · 20 in / 3,482 out tokens
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.