find-clips-visual

I'd like you to add a skill to Wideframe called "find-clips-visual".

What it should do:
Search footage for clips matching a visual subject or action and collect the matches into a bin.

Before you run anything, ask me to confirm:
- The exact visual subject, action, or scene that defines a match?
- Which folders or cameras to search?
- Inclusive or exclusive (for example only this subject, no other people present)?
- Whole clips or trimmed subclips, and a maximum number of results?

Then do the work:
1. Ensure every candidate clip is analyzed, running media-analyze-content-batch on any that are missing.
2. Translate the description into explicit visual criteria.
3. Score and rank candidate clips against the criteria.
4. Collect the matches into a named bin with timecodes and a one-line justification each.
5. Flag when no clip is an exact match rather than substituting a near miss.

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:
- Every clip in the output verifiably contains the described element.
- No near miss is presented as an exact match.
- An explicit no-match result is given when criteria are unmet.
- The search covered every candidate clip.

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 "find-clips-visual" so I can run it again by saying /find-clips-visual.