What is image-to-code?

A process for turning screenshots, mockups, or Figma designs into responsive frontend code that matches the visual layout.

Use it to build HTML, CSS, React, SwiftUI, or similar interfaces from images and design files.

It helps translate a visual design into structured code while preserving its spacing, components, styling, and behaviour across screen sizes.

image-to-code — Cursor rule for Cursor by GktuOktay

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/GktuOktay/ai-skills

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/rules/gktuoktay/ai-skills/image-to-code/github.svg)](https://agentmods.dev/rules/gktuoktay/ai-skills/image-to-code)

Your own site

<a href="https://agentmods.dev/rules/gktuoktay/ai-skills/image-to-code"><img src="https://agentmods.dev/badge/rules/gktuoktay/ai-skills/image-to-code/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/rules/gktuoktay/ai-skills/image-to-code"><img src="https://agentmods.dev/badge/rules/gktuoktay/ai-skills/image-to-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Nothing until a file matches its globs; then the whole rule loads.

When invoked 1,328 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.01328
Opus 5	$0.00000	$0.00664
Sonnet 5	$0.00000	$0.00266
Haiku 4.5	$0.00000	$0.00133

Measured 8d ago against content hash c96102d3161e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

image-to-code scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/cursor/rules/image-to-code.mdc · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image to Code Conversion Skill

Overview

This skill defines the systematic process for analyzing static images (screenshots, design mockups) and translating them into high-quality, production-ready frontend code (HTML/CSS, React, SwiftUI, etc.). The goal is pixel-perfect accuracy, responsive behavior, and semantic structure.

Phase 1: Visual Analysis Workflow

Before writing any code, systematically break down the image.

1. Structural Layout

Identify the Grid/Layout Model: Is it a column-based layout, a grid of cards, or a single column? (Flexbox vs. CSS Grid).
Macro Regions: Divide the design into header, sidebar, main content area, and footer.
Alignment & Spacing: Mentally measure the gaps. Are they consistent? (e.g., 16px, 24px, 32px gaps).

2. Component Identification

Break down regions into reusable components:

Buttons (primary, secondary, icon-only)
Cards
Input fields and forms
Badges/Tags
Navigation items

3. Style Extraction (Educated Guessing)

Colors: Identify the primary brand color, background colors, text colors (primary, secondary, muted), and border colors.
Typography: Estimate font families (serif, sans-serif, monospace), weights (regular, medium, bold), and sizing hierarchy (H1 down to captions).
Radii & Shadows: Note corner rounding (e.g., 4px subtle, 999px pill, 16px card) and the direction/softness of drop shadows.

Phase 2: Reconstruction Strategy

1. The Semantic Skeleton (HTML/JSX)

Always start by writing semantic HTML without styles.

Use <header>, <main>, <section>, <article>, <nav>, <aside>.
Ensure accessibility: use <button> for actions, <a> for links, and add aria-labels for icon-only buttons.

<!-- Example of a good structural skeleton -->
<article class="card">
  <div class="card-image-wrapper">
    <img src="..." alt="..." />
  </div>
  <div class="card-content">
    <span class="badge">Technology</span>
    <h3 class="title">Understanding AI</h3>
    <p class="description">A deep dive into...</p>
    <div class="card-footer">
      <div class="author">...</div>
      <button>Read More</button>
    </div>
  </div>
</article>

Read the full file on GitHub · 123 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 123 lines · 1,328 tokens per session scan A c96102d3161e

Subscribe to this mod's changes

image-to-code is a cursor rule published in the GitHub repository GktuOktay/ai-skills (2 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,328 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

CSS and styling Claude Code Design and UX Frontend agent-skills ai-agents ai-skills anti-sycophancy antigravity

motion-designer

Act as a Senior Motion Designer to specify and ship purposeful UI animation — micro-interactions, transitions, scroll-driven sequences, p...

rajitsaha/100xprism · 26 tokens

ui-components

USE WHEN: Building UI components, structuring layouts, and applying styles using Tailwind CSS.

virastack/ai · 0 tokens

figma-translator

Translate any technical specification into five precise, self-contained Figma Make prompts ready to paste and generate.

rajitsaha/100xprism · 19 tokens

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Covers design thinking, typography pairing, color theory, motion design, spatial composition, and code quality. Generates real working code — HTML/CSS/JS or React — with intentional aesthetic direction, not generic AI output.

thatrebeccarae/claude-marketing · 55 tokens

canonical__hhadcn-ui

Cursor rule "canonical__hhadcn-ui" from Bilal140202/the-lord-of-the-skills, covering shadcn/ui best practices, installation, initial setup, initialize shadcn/ui in your project and add components as needed.

Bilal140202/the-lord-of-the-skills · 0 tokens

accessibility

Web accessibility best practices for WCAG compliance and inclusive design.