export-transcript

I'd like you to add a skill to Wideframe called "export-transcript".

What it should do:
Transcribe one or more videos into a standalone, timecoded transcript document or sidecar.

Before you run anything, ask me to confirm:
- Which file(s) to transcribe?
- Output format (txt, SRT, markdown, or Word)?
- Include timecodes and speaker labels?
- Save location, and concatenate multi-part recordings first?

Then do the work:
1. Resolve the target media, concatenating multi-part recordings if asked.
2. Transcribe each source with timecodes, and diarization if requested.
3. Assemble into the requested document format with a heading per source.
4. Write the file to the chosen location.
5. Verify coverage against each source's duration.

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:
- One output per requested source, or one combined document, exists at the stated path and format.
- Timecodes are present and span each clip's duration.
- Every requested source is represented.
- The file opens as valid for its format.

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 "export-transcript" so I can run it again by saying /export-transcript.