Claude Skill

image-to-code

Turn a reference image, screenshot, or mockup into token-driven, accessible code — infer the design system from the reference (palette, type scale, spacing, radius, layout archetype), map it to the 3-tier tokens, rebuild it, then verify with the kit's gates. Use when the user pro

LLM Mart · 0 points · 1 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download plugin87-ux-ui-agent-skills-.claude_skills_image-to-code-278e9d9.zip · 1 KB

plugin87/ux-ui-agent-skills 1406 145 forks MIT Updated 9d ago

Part of plugin87/ux-ui-agent-skills — 18 skills

Install

skills CLI npx skills add https://github.com/plugin87/ux-ui-agent-skills/tree/main/.claude/skills/image-to-code

Claude Code

claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install plugin87-ux-ui-agent-skills@llmmart

Git git clone https://github.com/plugin87/ux-ui-agent-skills.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole plugin87/ux-ui-agent-skills collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Skill: Image to Code

Reconstruct a design from a visual reference as a real design system, not a one-off copy. Match the system (color/type/spacing language), never lift copyrighted imagery or brand assets.

Steps

Read the reference like a designer. Infer and write down:
- Palette — 1 dominant surface family, text colors, 1 primary action + at most 1 accent (sample the hues; don't guess random hex).
- Type — family feel (geometric/grotesk/serif), the scale jumps, display vs. body contrast, weights.
- Spacing & density — base unit, section rhythm, card padding; airy vs. compact.
- Radius & depth — radius language (sharp/soft/pill), shadow vs. hairline separation.
- Layout archetype + sequence — full-bleed hero / asymmetric split / bento / editorial stack (taste/design-taste.md → Variance Mandate).
Anchor to a known system if it's close — browse taste/aesthetic-systems.md / python3 scripts/design_systems.py search <term> and adopt that recipe to stabilize decisions.
Build the token theme from the inferred values → 3-tier DTCG (design-tokens skill); generate a single theme.css. Verify every color pair with scripts/contrast.py / scripts/validate_contrast.py (light + dark) — a sampled brand color that fails AA gets adjusted; taste never overrides POUR.
Rebuild layout + components token-driven via frameworks/adapter-protocol.md + components/*: one shared primitive layer, all 8 states, a11y wired, no emoji (lucide), single theme. Apply taste (design-taste.md) so it doesn't regress to generic.
Verify against the reference — render and screenshot it, compare side-by-side to the reference; run node scripts/measure_render.mjs, lint_hardcodes.py, taste_audit.mjs, and npm run verify.

Verification (definition of done)

npm run verify is 100% (tokens resolve, contrast AA light+dark, no hardcodes/emoji, real-render WCAG).
The rebuilt UI uses ONE inferred token theme — no per-section palettes.
A screenshot of the result visibly matches the reference's design language.

Honest limit: this matches the design system, not a pixel-perfect copy. Do not reproduce the reference's photographs, logos, or copyrighted copy — substitute your own or generic placeholders.

Files (ux-ui-agent-skills)

SKILL.md 2.7 KB

---
name: image-to-code
description: Turn a reference image, screenshot, or mockup into token-driven, accessible code — infer the design system from the reference (palette, type scale, spacing, radius, layout archetype), map it to the 3-tier tokens, rebuild it, then verify with the kit's gates. Use when the user provides a design/screenshot and wants matching UI code.
invocation: user
---

# Skill: Image to Code

Reconstruct a design from a visual reference as a real design system, not a one-off copy. Match the *system* (color/type/spacing language), never lift copyrighted imagery or brand assets.

## Steps
1. **Read the reference like a designer.** Infer and write down:
   - **Palette** — 1 dominant surface family, text colors, 1 primary action + at most 1 accent (sample the hues; don't guess random hex).
   - **Type** — family feel (geometric/grotesk/serif), the scale jumps, display vs. body contrast, weights.
   - **Spacing & density** — base unit, section rhythm, card padding; airy vs. compact.
   - **Radius & depth** — radius language (sharp/soft/pill), shadow vs. hairline separation.
   - **Layout archetype + sequence** — full-bleed hero / asymmetric split / bento / editorial stack (`taste/design-taste.md` → Variance Mandate).
2. **Anchor to a known system** if it's close — browse `taste/aesthetic-systems.md` / `python3 scripts/design_systems.py search <term>` and adopt that recipe to stabilize decisions.
3. **Build the token theme** from the inferred values → 3-tier DTCG (`design-tokens` skill); generate a single `theme.css`. Verify every color pair with `scripts/contrast.py` / `scripts/validate_contrast.py` (light + dark) — a sampled brand color that fails AA gets adjusted; taste never overrides POUR.
4. **Rebuild layout + components** token-driven via `frameworks/adapter-protocol.md` + `components/*`: one shared primitive layer, all 8 states, a11y wired, no emoji (lucide), single theme. Apply taste (`design-taste.md`) so it doesn't regress to generic.
5. **Verify against the reference** — render and screenshot it, compare side-by-side to the reference; run `node scripts/measure_render.mjs`, `lint_hardcodes.py`, `taste_audit.mjs`, and `npm run verify`.

## Verification (definition of done)
- `npm run verify` is 100% (tokens resolve, contrast AA light+dark, no hardcodes/emoji, real-render WCAG).
- The rebuilt UI uses ONE inferred token theme — no per-section palettes.
- A screenshot of the result visibly matches the reference's design language.

> Honest limit: this matches the design **system**, not a pixel-perfect copy. Do not reproduce the reference's photographs, logos, or copyrighted copy — substitute your own or generic placeholders.