Appetite UI Symbol
Appetite UI

Your AI reads the same system.

Designers, developers and agents. One source of truth, and the free Core Skill that teaches your agent to use it.

AnthropicClaude
CursorCursor
FigmaFigma Make
OpenAIChatGPT
StitchStitch
Core Skill

One file briefs the agent.

AI can draw a button. It cannot invent your decisions: which spacing step you use, what your error state is called, how your brand maps onto Material roles. The Core Skill writes those decisions down where an agent can read them.

Download the Core Skill.

One free instruction file. It names the layers, the naming logic and the rules of the system.

Typography and action sheet documentation pages with a Core skill badge overlay

Add it to your agent.

Claude, Cursor or any tool that reads instructions. One paste, no plugin, no setup call.

Token names an AI agent reads when generating a screen

Ask for screens.

The agent picks action/primary instead of guessing a hex, because the file tells it which token that is.

AI prompt turning into SwiftUI code built from Appetite spacing, type and color tokens

Ship what you designed.

The same W3C DTCG source generates SwiftUI, Compose, Flutter and CSS, so the build reads the values you set.

Finance, chat and fitness app screens arranged around a central wallet balance screen
The thesis

Agents do not need a bigger library. They need one that explains itself.

That is what a system is: the context layer where your decisions are written down. The kit era optimized for volume. The agent era rewards structure.

Three dark mode screens, fitness dashboard, wallet balance and chat list

Why it works

Written to be read by something that cannot ask a follow up question.

A system an agent can use is a system that explains itself. These four things are the difference between a file a model can read and a file it has to guess at.

Every variable knows its code name.

codeSyntax for web, iOS and Android, written into the variable itself.

Components describe themselves.

All 1,972 carry a written description an agent can parse.

Values trace back to a decision.

Primitive to semantic aliases, so a model can follow the reasoning.

The context pack ships with it.

tokens.md and tokens.json, in the file you bought.

Start designing. Build faster. Look better.

One-time payment  |  Lifetime updates  |  Works on the free Figma plan