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 "captions".
What it should do:
SRT or burned-in captions, set to your line length and reading speed.
Before you run anything, ask me to confirm:
- Sidecar (SRT/VTT) or burned-in
- Max chars/line + max lines/caption
- Target reading speed (CPS)
- Speaker labels? Profanity handling?
Then do the work:
1. caltools media-transcript-get-batch for word-level timestamps.
2. Wrap text into caption cues honoring chars/line, lines/caption, and CPS; split cues that exceed CPS.
3. Sidecar: write valid SRT/VTT. Burned-in: sequence-text-overlay-add + render-final with the confirmed style.
4. Validate every cue against the limits.
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:
- Cues are timed to speech (spot-checkable) and non-overlapping.
- Zero cues exceed chars/line, lines, or CPS limits (report any the source forced).
- Output validates as well-formed SRT/VTT or renders clean.
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 "captions" so I can run it again by saying /captions.RUN IT AGAIN
Once it’s saved, run it on the next project with /captions, or just say:
“Make me an SRT at 42 chars a line, two lines max, under 17 CPS, no speaker labels.”Run it on your own footage.
7-day free trial. Requires Apple Silicon.
RELATED SKILLS