Menu

Individual skill

gpt-ui-assets

0upvotes

Design app, tablet, foldable, desktop-app and website screens with OpenAI's GPT image and vision models (API key or the local Codex CLI), then turn an approved design into production assets redrawn 1:1, never cropped: SVG/VectorDrawable icons, PNG/WebP illustrations, launcher icons, frame, Lottie and AVD animation, smoke/steam/rain loops, theme code and fonts measured from the pixels, a screenshot diff of the built UI, and App Store / Google Play screenshot sets composited from real captures. Also writes GPT-researched feature blueprints. Use whenever the user wants GPT/ChatGPT to design screens, icons, illustrations or an app icon; approves a GPT design ("go ahead", "build it", "give me the assets"); wants assets used in the UI; wants an animated drawable, Lottie or AVD from existing art; wants store screenshots or a Play feature graphic; or complains that GPT cropped assets out of a mockup. Not for go/no-go idea validation, or design direction without GPT.

skills/gpt-ui-assets/SKILL.md

Read pinned source

Source commit 9ebd736e363526aa7d5b60c5e27f2359c6e61320

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
15
Repository last updated
Nov 10, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# GPT UI assets

**You are the driver.** GPT is one instrument among several. Route every job to whoever does it best, and never
accept "GPT can't" as the end of the road:

| Job | Best done by |
|---|---|
| Market research (web-searched, cited) and the feature blueprint | GPT reasoning with web search (`research`, `blueprint`) |
| Screen mockups, painterly art, illustrations, photos, textures, raster frames | GPT image (`mockup`, `forge`, `frames`) |
| Concept screens that must look finished, or move | **You** build the screen in HTML/CSS/JS; GPT paints only the materials (`material`, `state`); `stage` renders it |
| Asset inventory, design QA, icon-set style, vector keyframes | GPT vision (`manifest`, `critique`, `iconspec`, `vectorize`) |
| Flat/line icons as vectors | GPT vision writes SVG (`svg`, `icons`). If it stays weak after its retry, **you** fix the SVG by hand, then `svg --check` |
| Ranking, colour correction, safe zones, registration, QA | Local measurement in the kit. Trust numbers over the model's claims |
| Raster art → vectors, animatable parts | Local tracing and rigging (`trace`, `rig`, `animate`) |
Back to top