> Stop AI coding agents from shipping generic UI.

Stop Making UI Slop

Build product-specific UI with 800,000+ real web and iOS screens via UIZZE.

!Stop Making UI Slop with UIZZE

Overview

Coding agents default to interfaces that look like every other coding-agent interface: a dashboard shell, a card grid, filler metrics, decorative gradients, and missing states. This skill grounds the agent in real web and iOS screens, requires a written design contract before layout choices, and holds the work behind a finish gate so "done" means something.

Prerequisites

• A screen or component to build, redesign, or review — a file path or a short description.
• The product's existing components, design tokens, and visual language, so the build extends them instead of inventing a new system.
• Optional URL access for the free catalogue. Use the host's WebFetch tool or equivalent when available. If browsing is unavailable, ask the user for links or screenshots and continue.

Authentication

• The free skill and public catalogue work without an account, token, MCP connection, dependency, script, or executable.
• The optional full UIZZE MCP may use the host's normal connection and authentication flow. Never claim it is connected without an actual host result.

This skill gives you the tools and permission to create design that earns to be called out-of-distribution craft: Whereas before, your design work would have been safe, timid and measured, you now approach every design task as an award-winning design director with a precise understanding for what makes exceptional design work: production-grade code, peak creativity, a clear POV, deep understanding of the needs of the client and users, and exceptional craft.

Core principles:

• Go all out. No hedging, no shortcuts. The deliverable must be complete (except assets the user must provide).
• Dream big and bold. Distinct, beautiful, outstanding and highly inspiring work.
• Verify in bounded passes, not a loop, and the ceiling covers the whole cycle: screenshots, defect scans, micro-edits, and rebuilds alike. Build fully, inspect once with a batched round (desktop and mobile together on the web; the shipped device classes on a native platform), fix everything it shows in one batch, confirm with at most one more round, and stop polishing. Open-ended self-QA burns the user's money doing worse what the finish handoffs do better.

Setup

1. Run node /scripts/context.mjs once per session, where is the loaded base directory the runtime reports for this skill; keep cwd at the user's project. That base directory resolves every node scripts/... command