Carousel and outfit-change factory
viral-content-factoryPROcontentsocial
Builds carousels and outfit-change videos for TikTok and Instagram around invented characters.
Was er tut
- Triggers when you need a new carousel, an outfit-change video, or more content for an existing character.
- Starts with questions: what the product is, who the characters are, what references and keys exist. It won't generate before that.
- Carousels are seven or eight slides per topic, in three recognisable styles: shot-on-a-phone, editorial infographic, and a separate one for animal characters.
- Outfit-change videos are built from a single anchor frame — a faceless figure in a black morph suit — and every later frame edits that same anchor, otherwise the background and body drift.
- Keeps a checklist of how these images usually fail — extra fingers, garbled text, the suit disappearing — and regenerates the one bad frame rather than the whole batch.
Wozu er gut ist
The failure mode of this kind of pipeline is quiet drift: the background is slightly off, the body is slightly off, and the cut stops reading as one person. Everything here hangs off one anchor frame plus a checklist run before assembly. On top of that there's a hook bank across nine categories — not “content ideas” but formulas with the reason each one works.
Wohin damit
- 1Legen Sie im Projekt den Ordner .claude/skills/viral-content-factory an
- 2Legen Sie dort eine SKILL.md mit dem Text unten ab
- 3Fertig. Claude Code lädt den Skill selbst, sobald eine Aufgabe zur Beschreibung passt
Damit der Skill in allen Projekten statt nur in einem funktioniert, legen Sie ihn in ~/.claude/skills statt in den Projektordner.
SKILL.md-Datei
# Viral Content Factory
End-to-end system for generating viral TikTok/Instagram content promoting a product through AI-generated characters. Creates two content types:
1. **Carousels** — sets of 7-8 styled images per topic (Gemini image generation)
2. **Mannequin videos** — outfit-change animations using morph suit figures (Gemini + Kling 3)
---
## Phase 0: Gather Requirements
Before generating anything, collect this information from the user:
### Required
1. **Product** — What app/product are we promoting? What does it do? What's the price?
2. **Characters** — Who are the AI personas? For each character:
- Name and handle (@)
- Visual description (age, ethnicity, build, hair, style aesthetic)
- Voice/personality (how they talk, what makes them unique)
- Content themes that work for them
3. **Reference images** — Ask user to provide:Die Datei dieses Skills gehört zur PRO-Auswahl
Zugang freischalten