UIZZE stops AI coding agents from shipping generic UI with 800,000+ real screens, anti-ui-slop skills, MCP tools, and a GitHub Action.
UIZZE is easy to set up with trust notes worth reviewing. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view uizze/uizze --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
Repository setup guidance
Looks usable, but maintenance, license, or security notes deserve a closer look.
Last commit was about 24 days ago.
6 GitHub stars indicate community interest.
0 open issues signal maintenance load.
MIT license detected.
3 security/trust notes recorded.
Setup difficulty is 2/5.
A public repository of example skills for Claude, demonstrating how to create reusable instructions and resources for specialized tasks.
Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.
An open-source framework to turn HTML, CSS, and animations into deterministic MP4 videos.
A multimodal toolset for AI agents to generate, edit, and display images, videos, and audio via CLI.
UIZZE is a set of tools that helps AI coding agents create better-looking user interfaces. It provides a skill that agents can follow, a tool to check if a UI looks too generic, and a GitHub Action that runs checks on your code. It uses a large database of real web and iOS screens to guide agents toward more distinctive designs.
UIZZE is a comprehensive toolkit designed to combat 'UI slop'—the generic, template-like interfaces often produced by AI coding agents. It offers three complementary surfaces: a free local skill (`anti-ui-slop`) that guides agents through a structured workflow, a deterministic preview MCP tool (`check_ui_slop`) that checks rendered HTML/CSS for finish risks without uploading source or calling a model, and a full hosted MCP service that provides live search across 800,000+ real web and iOS screens, design contracts, validation, audits, and rendered critique. The repository includes integrations for Codex, Claude Code, Cursor, GitHub Copilot, Kiro, Storybook, and a GitHub Action for pull-request finish gates. It also provides a benchmark for reproducible UI quality assessment and a Next.js starter. UIZZE is open-source under MIT and aims to help developers and teams ensure their AI-generated UIs are distinctive, polished, and aligned with design systems.
6
Stars
1
Forks
0
Issues
MIT
License
UIZZE stops AI coding agents from shipping generic UI with 800,000+ real screens, anti-ui-slop skills, MCP tools, and a GitHub Action.
Frontend developers using AI coding assistants, Design engineers and UI/UX developers, Tech leads and engineering managers overseeing AI-assisted development
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
The full hosted MCP service may require an account and could send code or design data to external servers; review privacy policy. The preview tool is deterministic and does not upload source, but the full service may have different data handling.
Similar or complementary options to evaluate include anthropic-skills, bug-hunter, hyperframes.
Aug 20, 2026