Miliastra Image Editor CSS Builder
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_3a6be892/miliastra-image-css-builder.
About this skill
Problem
The Miliastra image editor import pipeline expects a strict CSS scene format. Typical web CSS can silently drop elements when it uses pseudo-elements, gradients, percentage sizes, or malformed rotation. Without an explicit canvas size and element budget, the editor preview, PNG export, and GIA assets can shift or fall back to unexpected colors.
How It Works
The skill generates importable CSS through a planning-first workflow:
- Confirm the element budget and canvas size first; the full-canvas background rectangle counts toward the budget.
- Extract 3–6 primary colors, map canvas regions such as sky, subject, and foreground, then plan layers by z-index.
- Use only supported primitives: rectangles, ellipses with border-radius: 50%, and triangles with the exact clip-path template.
- Use rotated ellipses for soft light, shadow, and color blending; use opaque rectangles or triangles for hard-edged subjects; keep rotated bounding boxes inside the canvas.
- Return only CSS, with usage comments such as 11/20 elements used.
Boundaries
This approach is best for quick, round-trip scene generation within an element budget. It does not support gradients, rgba, percentage sizes, pseudo-elements, box-shadow, filter, or transforms other than rotate(Ndeg). For native stars, precise triangle rotation, or higher fidelity, switch to JSON import instead of approximating with CSS.
Use Cases
- Turn a reference image into importable editor CSS scenes.
- Build a sunset scene within a 20-element editor budget.
- Check local round-trip imports and fit.png warnings.
- Plan palette, regions, and z-index before writing final CSS.
Best For
- Import pipeline engineers who need stable, parseable CSS.
- Design engineers building budgeted editor scenes from images.
- Frontend engineers reducing silent export shifts and color fallbacks.
- Visual asset engineers who validate exports before delivery.
Related Skills
Excalidraw Wrap is an Excalidraw-focused wrapper, with tags for TypeScript, GitHub, and automation.
Calibrate vague brand inputs, expose contradictions, distill a brand core and positioning boundaries, then stress-test the result into an executable brand skeleton.
Generate localized Chinese brand names, naming directions, slogans, and risk checklists with reusable templates and trademark search reminders.
A beginner-friendly photo analysis tool that infers shooting parameters from visual features and suggests post-processing, optimization, and learning keywords.