image-to-code
Pixel-perfect UI screenshots to responsive code and PNG assets
All Skills in This Repository (1)
Pure Emerald Level IndicatorsFrequently Asked Questions
FAQPage SchemaHow to install image-to-code?โผ
Run `npx skills add yuzhworkhard-wq/image-to-code --all -g -y` in your terminal to install the skill globally. Then install the Python helper dependencies with `python3 -m pip install -r requirements.txt`.
How to convert a UI screenshot into code?โผ
Select your UI image and ask your agent to use the image-to-code skill. It measures every element on a 750px baseline, builds a layer manifest, and generates responsive code that scales cleanly to mobile widths.
Does it export transparent PNG assets?โผ
Yes. Icons, avatars, and illustrations are sliced from the source image as independent transparent PNGs at 2x, 3x, or 4x density, with automated audits to catch white backgrounds or cropped edges.
Can the output be imported into Figma?โผ
Yes. After code and QA are complete, it generates an editable Figma layer spec or local importer with real text nodes, native shapes, and image fills instead of a flat screenshot.
Which coding agents work with image-to-code?โผ
It follows the universal SKILL.md standard, so it runs in Codex, Claude Code, Cursor, and other compatible agents using plain-English requests.
Related Repositories in Software Engineering
View All in Software Engineeringโopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core