beautify-decoration
FeaturedIterate on the visual identity of a top-down pixel-art decoration (sprite + layout integration) in pixtuoid. Use when redesigning an existing decoration (pantry, lounge, meeting room, cubicle decor) or adding a new one. Captures the rebuild trap, the visual-verification loop, resolution constraints, sprite-format pitfalls, and the layout-integration checklist that we learned the hard way during the pantry beautify session.
Install
Quality Score: 92/100
Skill Content
Details
- Author
- IvanWng97
- Repository
- IvanWng97/pixtuoid
- Created
- 4 months ago
- Last Updated
- today
- Language
- Rust
- License
- MIT
Similar Skills
Semantically similar based on skill content — not just same category
beautify-site
Use when the user wants a website, page, or UI to look better — "make this site look better", "beautify my landing page", "redesign this UI", "make it look professional", "this page looks bland/generic/cheap", "polish the design", "make it look expensive", "make it extravagant". Runs one ordered pipeline — pin a design direction, fit components to it, layer motion, then strip every AI tell in a mandatory final pass. Bold and extravagant by default. Fully self-contained — every helper tool is optional with a documented fallback. Produces a persisted design-system MASTER.md plus implemented, accessibility-checked, AI-tell-free UI.
design-refinement
Use to make a UI distinctive instead of generic — when a design "looks AI-made / Claude-type / templated", needs to be bolder or quieter, or before shipping any user-facing surface. Picks real fonts (not training-data defaults), commits to a color strategy, kills cliché patterns, and runs an audit -> polish pass. Trigger on "make it look better", "less generic", "design critique", "polish the UI", "pick fonts/colors", "this looks like AI slop".
repaint
Build production-grade frontend UI that doesn't read as "AI-made" — and behaves like an elite product, not just looks like one. A self-contained pipeline — research real references, lock a register + anchor, commit OKLCH tokens + distinctive type, design the interaction (feedback, forgiving input, keyboard, recovery), make it accessible and SEO-ready (semantic HTML, landmarks, alt, metadata), build, then iterate against slop + experience + a11y/SEO audits and a live browser-screenshot loop. Grounded in the industry-standard design systems (Material 3, Apple HIG, Carbon, Polaris, Fluent, Ant, shadcn) and the psychology of interface design (Gestalt, Hick, Fitts, peak-end), with manipulative dark patterns banned. Use for any page, component, dashboard, landing page, settings, data table, onboarding, or app surface — especially when output looks generic, templated, or "AI-made", feels hollow, or is inaccessible/invisible to search; aim at Linear/Vercel/Stripe/Notion quality. Ships a reference library + 23 evals.