This is a full research pipeline for identifying what's actually working on TikTok right now. You point it at competitor accounts, it pulls recent videos via Apify, runs statistical analysis to find outliers (anything performing above mean plus 2 standard deviations), then uses AI to extract the actual hook formulas and content patterns from the top 5 videos. The output is a structured report with replicable techniques, not just metrics. It's legitimately useful if you're trying to reverse engineer viral content in a niche, though you'll need both Apify and Gemini API keys. The engagement scoring formula weights comments and shares heavily, which feels right for TikTok's algorithm.
npx skills add https://github.com/bradautomates/head-of-content --skill tiktok-research