image-to-code

leonxlnx/taste-skill/image-to-code

This skill is designed for visually important web tasks. It mandates generating design images first, then deeply analyzing them, and only then implementing the frontend to match the design as closely as possible. It emphasizes preferring large, readable, section-specific images over tiny compressed boards, generating fresh standalone images for sections or detail views instead of cropping old ones, and avoiding lazy under-generation. It also advises against cards-inside-cards UI and keeping the hero clean, spacious, readable, and visible on a small laptop.

Installations · 951Voir la source

Installation

npx skills add https://github.com/leonxlnx/taste-skill --skill image-to-code

Fichiers du skill

SKILL.md

Dernière synchronisation · 20 oct. 2026

agents/openai.yaml›

policy:
  allow_implicit_invocation: false

SKILL.md›

---
name: image-to-code
description: "Moved to github.com/Leonxlnx/imagegen-skills. Runs only when called by name."
disable-model-invocation: true
---

# image-to-code (moved)

This skill now lives in its own repository, with the other image-generation skills: https://github.com/Leonxlnx/imagegen-skills

The install name did not change:

```bash
npx skills add https://github.com/Leonxlnx/imagegen-skills --skill "image-to-code"
```