Ztgc Taste Image To Code Bridge

---
name: ztgc-taste-image-to-code-bridge
description: "Focused Perfect_AI Taste Skill specialist: image to code bridge"
---

# Image To Code Bridge

## Responsibility
Translate references into design tokens and structural descriptions; never pretend image-derived code is original site source.

## Entry conditions
- Load the parent `$ztgc-taste-creative-direction` only when Taste Skill is relevant to this task.
- Collect concrete routes/files, user objective, dependency versions and current behavior.
- Do not rename or delete old skills or overwrite existing project content.

## Method
1. Extract brand story, audience, functional requirements, legal/asset limits and language direction.
2. Generate multiple fundamentally distinct composition concepts: editorial, restrained, kinetic, brutalist, immersive; avoid cosmetic-only palette variants.
3. Produce a layout grammar including headline widths, typographic axes, negative space, image treatment and mobile reading order.
4. Select based on accessibility, load budget, originality relative to supplied references and ease of maintenance.
5. Do not invent or scrape copyrighted assets; keep original source attribution and user-provided references.

## Specialized verification
- [ ] Readable Persian shaping and realistic sample content
- [ ] Headlines do not rely on arbitrary fixed line counts
- [ ] Variants maintain usable navigation and responsive reading order

## Tool usage and artifacts
- Tools: Optional: Python/GSAP only when selected; avoid treating style recipes as universal rules.
- Evidence: baseline, exact reproduction command, before/after details, screenshot or console logs when relevant.
- Minimum outcome: separate PASS/FAIL/NOT_RUN records, with a description of any unavailable runtime or device.
- Reference: `https://github.com/Leonxlnx/taste-skill/blob/main/skills/SKILL.md`. This locally authored guidance is not a copied GitHub Skill.