batch-transform

I'd like you to add a skill to Wideframe called "batch-transform".

What it should do:
Apply one transform set (rotate, strip audio, trim, speed) to every clip in a folder, one output each.

Before you run anything, ask me to confirm:
- Which transforms and exact parameters (rotation angle, strip audio, trim rule, speed)?
- Which folder or set of clips?
- Output codec, naming, and destination?
- How is a trim boundary defined (fixed offset, action start/end, silence)?

Then do the work:
1. Enumerate every input clip with media-info-batch.
2. Apply the identical transform chain to each clip.
3. Render each transformed clip to its own output file.
4. Verify the output count equals the input count and spot-check each property.

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:
- The output file count equals the input clip count.
- Each output shows the requested transform (orientation, no audio, duration, or speed).
- There are zero failed or partial renders.
- Any clip that could not be processed is listed.

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 "batch-transform" so I can run it again by saying /batch-transform.