tiktok-research

Identify high-performing TikTok videos, extract viral hooks, and generate actionable content insights. Research high-performing TikTok videos, identify outliers, and analyze top video content for hooks and structure. Verify setup: Parameters: Output JSON contains: Extracts from each video: See the video-content-analyzer skill for full output schema and hook/format types. Read {RUN_FOLDER}/outliers.json and {RUN_FOLDER}/video-analysis.json , then generate {RUN_FOLDER}/report.md . Report Structure: Focus on actionable insights. The "Top Performing Hooks" section with replicable formulas should be prominent. Full pipeline: Then read both JSON files and generate the report. Engagement Score : likes + (3 x comments) + (2 x shares) + (2 x saves) + (0.05 x views) Outlier Detection : Videos with engagement rate > mean + (threshold x std_dev) Engagement Rate : (score / followers) x 100 - Fetches videos from tracked accounts using Apify's TikTok Scraper, then applies statistical outlier detection to surface top performers - Analyzes the top 5 outlier videos with AI to extract hook techniques, content structure, retention patterns, and CTA strategies - Generates structured markdown reports ranking videos by engagement, mapping content patterns, and synthesizing replicable formulas for your own content - Requires Apify and Gemini API credentials, plus a pre-configured list of TikTok...