ADD THIS SKILL
paste into a new chat
Copy this into a blank Wideframe chat. It tells the agent to build the skill, what to confirm with you first, the steps to follow, and how to verify the result.
PROMPT
I'd like you to add a skill to Wideframe called "normalize-loudness".
What it should do:
Hit -14 LUFS for YouTube or -16 for podcast, with a true-peak ceiling.
Before you run anything, ask me to confirm:
- Target integrated LUFS
- True-peak ceiling (dBTP)
- Per-clip vs whole-sequence
- Whether to preserve existing ducking/mix automation
Then do the work:
1. caltools sequence-analyze-lufs-adaptive to measure integrated LUFS + true peak.
2. Compute the gain offset to the target; verify it won't breach the true-peak ceiling (limit if needed).
3. Apply gain via sequence-clips-update (preserving confirmed automation) or ffmpeg loudnorm.
4. Re-measure to confirm.
Do not grade your own work. When the output is ready, hand it to a separate verification subagent that has its own context window. Give it the output, the choices I confirmed, and the pass criteria below. It reviews the quality, writes specific feedback, and returns PASS or FAIL.
Pass criteria:
- Re-measured LUFS within +/-0.5 LU of target.
- True peak <= ceiling.
- Before/after table reported per clip (or for the sequence).
If it returns FAIL, apply the feedback, redo the affected work, and verify again with a new subagent. Repeat until it returns PASS, then show me the result.
Once it works, save it as a reusable skill named "normalize-loudness" so I can run it again by saying /normalize-loudness.RUN IT AGAIN
Once it’s saved, run it on the next project with /normalize-loudness, or just say:
“Bring this sequence to -16 LUFS, ceiling at -1 true peak, don’t touch my ducking.”Run it on your own footage.
7-day free trial. Requires Apple Silicon.
RELATED SKILLS