Kann ich Wholana vibecoden?

Build me a personal TikTok outlier tracker to replace Wholana. Requirements:

- A nightly Node script (node-cron) that pulls recent videos for up to 25 handles listed in
  handles.txt, using a TikTok scraper actor on Apify, token in .env. Do not scrape TikTok
  directly, you will be blocked inside a day.
- Store videos in SQLite via better-sqlite3: handle, video id, url, caption, posted date,
  views, likes, comments, shares, date first seen. Upsert on video id so a re-scrape
  updates metrics instead of duplicating rows.
- Per creator, keep a rolling median of views over their last 30 videos and score each
  video as views divided by that median. 3x or higher is a breakout. Skip creators under
  10 videos, the median is noise below that.
- Label each breakout with one LLM call (Anthropic or OpenAI, key in .env): caption plus
  the first 15 seconds of subtitles from yt-dlp, returning one hook type from a fixed list
  of 12 in hooks.json. Fixed list, not free text, or nothing groups.
- A page on localhost:3000 (Express, server-rendered HTML, Chart.js): last 7 days of
  breakouts sorted by score, filterable by handle, each row showing score, views, hook
  type, and a link, plus a per-creator sparkline of views over time.
- A save button per row that writes the video into a swipe collection and appends it to
  swipe.md, so my picks survive the database.
- Localhost only. No accounts, no telemetry, everything on my machine except the Apify and
  LLM calls.
- Out of scope: search across creators I am not already tracking, and a shared craft
  taxonomy. Do not build auth, multi-user workspaces, or hosting config.
- README: Apify token and actor id, the cron entry, and the cost per 1,000 videos scraped.
  The scraper bill, not the code, is what makes people quit this build.

Antworte mir auf Deutsch. Oberfläche, Kommentare und README auf Deutsch, alle Bezeichner wie Tabellen, Spalten, Variablen, Routen und Dateinamen bleiben Englisch.