Screenshot to ui spec

Skill swd3k/skills/agent-skills/workflows/screenshot-to-ui-spec

Turn screenshots or screen recordings into structured UI implementation specs and prompts. Use when recreating interfaces from references or briefings with images.From its SKILL.md

Install

npx -y skills add swd3k/skills --skill screenshot-to-ui-spec

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

25 days oldThe repository was created 25 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

0.9 KB, 174 tokens by cl100k_base, as published. Nobody here has run it

Screenshot → UI Spec

Steps

Inventory regions (nav, hero, cards, forms, footer).
Measure hierarchy: what draws the eye first?
Extract tokens: colors, radii, shadows, type sizes (approx OK).
Note interactions if video: hover, scroll, loaders.
Write implementation spec:
- layout
- components list
- states
- copy (exact if legible)
Call out originality: inspire structure, don't steal brand assets/copy.

Output template

## Thesis
## Layout
## Tokens
## Components
## Motion
## Copy
## Non-goals / differences from reference

Pitfalls

Pixel-copying trademarked brands
Ignoring responsive behavior not visible in one frame

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.