Install Skills directly in chat.Install the MochiLab Skills assistant in OpenClaw, connect your account, then find, install and update Skills in chat.
See how to connect →
MOCHILAB / AI SKILL
Audio Loudness Preparation
Read a supplied ffprobe JSON and prepare the first loudness-analysis filter without altering audio or inventing measurements.
What it does
Read a supplied ffprobe JSON and prepare the first loudness-analysis filter without altering audio or inventing measurements.
How to use it
Give the assistant the concrete task and required inputs. This fictional request illustrates the contract; use your selected files and parameters for real work.
{
"probeFile": "samples/probe.json",
"targetLufs": -16
}
Output and verification
Creates a JSON report and, when applicable, CSV, Markdown or document artifacts in the current workspace. Inputs remain intact. Five offline tests cover the example, invalid input, actual CLI output, path boundaries and non-overwrite behavior. Live account, browser and visual results require separate verification.
Scope
Requires ffmpeg/ffprobe for actual media work; these binaries are not bundled. Run analysis first, use measured loudnorm fields for a second pass, save a new output and listen to it. Loudness normalization is not noise removal.