design-from-app
Skill17 starsChanged 12 days agoMITView on GitHub
Rebuild the look of an app the user likes as a native WinUI 3 design kit, by measuring its screenshots (sizes, spacing, type, colors, icons), building its parts, and comparing pixel by pixel until they match. Use when the user names an app whose look they want, shares screenshots of one, or says "make it look like X".
2 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- Stijnus/dsh-rev-engedited, first seen Nov 8, 2026
- daveebbelaar/bamaedited, first seen Nov 1, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 2
- daveebbelaar/bama★ 1.7k80% same
- Stijnus/dsh-rev-eng★ 179% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- agent-cliSkill
- csharp-winuiSkill
- improve-architectureSkill
- os-integrationsSkill
- performanceSkill
- app-iconSkill
- design-kitSkill
- design-systemSkill
- layout-gridSkill
- ux-designSkill
- windows-designSkill
- cloneSkill
- researchSkill
- user-storiesSkill
- build-and-verifySkill
- distributeSkill
- improve-loopSkill
- test-windows-appSkill
- app-briefSkill
- bawaSkill
- new-windows-appSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. About 0 are common, 2 are distinctive, and 11 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
11
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Look at an app, measure it, and rebuild its design system in WinUI 3.
- Very specific: line 21
Run them with & "${CLAUDE_SKILL_DIR}/scripts/measure.ps1" ....
- Very specific: line 29
Ask for screenshots, or take them with the clone skill.
- Very specific: line 38
Check: info prints the window size in epx, and every screenshot uses the same scale.
- Very specific: line 43
Look at each screenshot and name every distinct part: title bar, sidebar row, section header, primary action, list row, checkbox, date …
- Distinctive: line 48
Check: every visible element on the main screenshot belongs to a part.
- Very specific: line 65
Check: every token and every part size in design/KIT.md has a number from a command.
- Very specific: line 82
Check: design/KIT.md names the font, the icon source, and the icon size and weight.
- Very specific: line 87
Call the Skill tool with design-kit and build the tokens, the parts, the title bar, and the gallery from design/KIT.md.
- Very specific: line 92
Check: a snapshot of that screen (tools/snap.ps1 -Pages <page>) has the same size in pixels as the reference.
- Distinctive: line 107
Check: under 2% of pixels differ on the whole window, and every row and left edge is within 1.5 epx of the reference.
- Very specific: line 112
Before the app ships to anyone else, replace what belongs to the other company: its name, logo, illustrations, and any font or icon it owns.
- Very specific: line 114
Keep the structure, the spacing, and the feel.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Design from app
Look at an app, measure it, and rebuild its design system in WinUI 3. The
result is a design kit (design-kit skill) with the reference app's
numbers, and one reference screen that matches the screenshot.
Guessing gets close. Measuring gets it right. Two scripts do the measuring, next to this skill:
scripts/measure.ps1: sizes, positions, text heights, and colors from a screenshot.scripts/compare.ps1: a side-by-side, a diff, and the share of pixels that differ.
Run them with & "${CLAUDE_SKILL_DIR}/scripts/measure.ps1" .... They run
in Windows PowerShell 5.1 and in pwsh 7. All coordinates are epx: pixels
divided by the display scale. -Scale sets it (1.25 at 125%). A BAWA
snapshot writes its scale into <page>-<mode>-layout.json, and both
scripts read it from there when you leave -Scale out.
1. Get the screenshots
Ask for screenshots, or take them with the clone skill. You need:
- The window only, no desktop, taken on this PC so it has the same
display scale as your snapshots. Snipping Tool (Win+Shift+S) in Window
mode captures one window. Save them as PNG in
design/reference/. - One screen with the most parts on it (a sidebar, a list, a command bar), plus close-ups of menus, dialogs, and dark mode if they matter.
- The window size:
measure.ps1 info shot.png -Scale <display scale>.
Check: info prints the window size in epx, and every screenshot uses
the same scale.
2. List the parts
Look at each screenshot and name every distinct part: title bar, sidebar
row, section header, primary action, list row, checkbox, date chip, icon
button, divider. Start design/KIT.md from the design-kit skill's
kit-spec.md with one section per part.
Check: every visible element on the main screenshot belongs to a part.
3. Measure
Fill design/KIT.md with numbers, not estimates. The recipes and the
traps are in measuring.md. In short:
| To find | Command |
| Sidebar width, panes | hline shot.png <y in an empty area> |
| Row positions and pitch | rows shot.png <x0> <x1> [y0 y1] |
| Left edges, gaps | cols shot.png <y0> <y1> [x0 x1] |
| Selection pill, dividers | vline and hline through it, -Tolerance 4 |
| Text and icon colors | ink shot.png x y w h |
| Surface colors | palette shot.png x y w h |
| A close look | crop shot.png x y w h out.png 4 |
Check: every token and every part size in design/KIT.md has a number
from a command.
4. Find the font and the icons
- Most Windows apps use the system font: Segoe UI Variable on Windows 11, Segoe UI before it. Web and Electron apps often bring their own. Start with the system font. When the letters differ (a, g, t, digits), name the font and pick it or an open alternative with a license that allows bundling.
- Text sizes come from step 6: build, measure the same word in both images, scale.
- Icons: note the size, stroke weight, corners, and whether selected rows
switch to a filled form. Match with Segoe Fluent Icons first; draw the
ones that do not match as
PathIconshapes (design-kitparts.md, Icons).
Check: design/KIT.md names the font, the icon source, and the icon size
and weight.
5. Build the kit and one screen
Call the Skill tool with design-kit and build the tokens, the parts, the
title bar, and the gallery from design/KIT.md. Then build the main
screenshot's screen from kit parts only, with the same data and the same
window size.
Check: a snapshot of that screen (tools/snap.ps1 -Pages <page>) has the
same size in pixels as the reference.
6. Compare until it matches
& "${CLAUDE_SKILL_DIR}/scripts/compare.ps1" design/reference/main.png "$env:TEMP\<App>-shots\<page>-light.png" "$env:TEMP\<App>-compare"
& "${CLAUDE_SKILL_DIR}/scripts/compare.ps1" ... "$env:TEMP\<App>-compare-sidebar" 0 0 320 300Open side-by-side.png and diff.png with the Read tool. Then measure
the same rows, edges, and words in both images, and fix the tokens, not
the views. Order: window size, text sizes, columns and left edges, row
heights, colors, icons.
Check: under 2% of pixels differ on the whole window, and every row and left edge is within 1.5 epx of the reference.
7. Make it yours
Before the app ships to anyone else, replace what belongs to the other
company: its name, logo, illustrations, and any font or icon it owns.
Keep the structure, the spacing, and the feel. Write the replacements in
design/KIT.md.
Done when design/KIT.md has a measured number for every token and part,
the kit's gallery shows every part, the reference screen passes step 6,
and step 7 lists what was replaced.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

