App POV Device Demo — trending format for phone & app screens

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the use-case page.

"POV: you're using my app": a phone mockup swiping through items with a 3D tilt and an ambient color wash.

What it does

An indie-app demo framed as a POV: a device mockup on white, a carousel swiped with a slight 3D tilt, a background tint that shifts to each item's dominant color, and one object effect that sells the app's idea (in the sample, posters cut into perforated stamps). The post earned 298 bookmarks on 24K views, a 0.70 save ratio that says creators keep it as a template. An agent recreates the screens in HTML or uses the user's screenshots, wraps them in an original device frame, drives the carousel physics and color extraction in HyperFrames, and exports 4:5 and 9:16.

Status

A format people ask for that has no dedicated skill yet. Make it with the skills on the use-case pages below, or with varg directly.

Example: https://x.com/tweetbylokki/status/2074809676664107064

How an agent would make it: Screens (HTML recreation or screenshots) → original device frame → carousel with 3D tilt and per-item color sampling → effect mask (stamp perforation, polaroid, die-cut) → "POV:" caption → 4:5 and 9:16 render

Models it drives: render

Example output

https://skills.varg.ai/previews/want-app-pov-device-demo.mp4 — 'POV: you're browsing your favorite stamps in Stamply': a phone mockup on white swipes through stamp cards while the screen tint shifts to each stamp's color (first 8 s of 13.5 s) (credit: Lokki (@tweetbylokki), https://x.com/tweetbylokki/status/2074809676664107064)

Used for

More phone & app screens skills

Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.