This skill drives the Stitch MCP tools for design work. It improves each prompt with UI and UX terminology, then generates screens from text, recreates screens from uploaded images, edits screens with targeted prompts and produces variants.
Generated HTML and screenshots are downloaded to .stitch/designs, and the metadata file is kept current. It leaves colors and fonts to the project’s design system.
What You Get
- Screens created in a Stitch project from a structured layout prompt
- Edited screens that follow one focused change at a time
- Up to five variants with a chosen creative range and aspects
- Downloaded HTML and screenshots under .stitch/designs
- An updated .stitch/metadata.json after edits
Common Use Cases
- Creating a mobile browse tab from a short text idea
- Recreating a dashboard mockup image as an editable Stitch screen
- Exploring layout and color scheme variants of a home screen
What Makes It Unique
A prompt enhancement pipeline maps vague wording to professional UI terms from bundled reference files. The skill keeps colors, fonts and roundness out of generation prompts when a design system exists, which avoids conflicts with project-level tokens.
Under The Hood
The skill calls Stitch MCP tools such as list_projects, generate_screen_from_text, edit_screens and generate_variants. It downloads output files with curl through the shell and writes them under .stitch/designs. It delegates image upload to upload-to-stitch and design system setup to manage-design-system.