youtube-video-evaluatorlisted

# YouTube Idea Evaluator Takes video candidates (usually from `youtube-idea-finder`) and produces an actionable diagnostic report per video: what its thumbnail and editing actually look like and why, what topics/tech/format it covers, and a concrete "replicate this, fix that, do this for your own calendar" brief. This skill does not search YouTube or apply any pass/fail filter — every candidate handed to it gets a full write-up. The point isn't to find gaps to exploit, it's to reverse-engineer what worked (and what didn't) well enough to turn it into a content calendar entry. **Do not modify `youtube-idea-finder`.** It stays a standalone skill. This skill only consumes its output (or a manually supplied list of video IDs/URLs). ## Inputs - A JSON output file from `youtube_idea_finder.py` (has a `candidates` array with `video_id` per entry), or - A plain list of YouTube video IDs or URLs the user pastes in directly If the user hasn't run the finder yet and asks for both in one request, run the finder first, show its table, then feed its candidates into this skill. The finder needs a search term/niche to run — if the user hasn't given one (e.g. they just said "find me some video ideas and evaluate them"), ask for it before invoking the finder. Don't guess a query on their behalf. If a `--finder-json` file is supplied instead (e.g. from an earlier session, or handed off without restating the query in this conversation), read the search term for the output filename direc