Analysis updated 2026-05-18
Score an AI-generated frontend from 0 to 100 for generic visual patterns and get a fix report
Define a product-specific Design Contract before writing any UI code
Trace user journeys to catch dead buttons, stub handlers, and missing error states
| eid0lon/zero-slop | 0-bingwu-0/live-interpreter | 0xkaz/llm-governance-dashboard | |
|---|---|---|---|
| Stars | 2 | 2 | 2 |
| Language | Python | Python | Python |
| Setup difficulty | easy | moderate | hard |
| Complexity | 2/5 | 2/5 | 4/5 |
| Audience | developer | general | ops devops |
Figures from each repo's GitHub metadata at analysis time.
zero-slop is a set of three agent skills designed to help AI-generated user interfaces escape the generic visual patterns that AI coding tools tend to produce by default. When an AI builds a UI, it draws from training data and gravitates toward familiar clichés, purple-to-indigo gradients, glassmorphism cards with backdrop blur, feature grids with rocket and sparkle icons, and marketing copy like "empower your workflow." This project provides tools to detect, fix, and prevent those patterns. The three skills work as a pipeline. The no-slop skill scans frontend code files and gives the UI a 0, 100 score based on how many generic patterns it finds. It can produce an "AI UI Autopsy" report that identifies what feels off and suggests a fix order, apply targeted improvements with a --fix flag, or rethink the entire interface with --redesign. The perfect-design skill focuses on building a product-specific direction before any code is written, using a Design Contract that defines who the product is for, what job it does, and the right visual approach. It has six product archetypes, operational SaaS, dashboard, commerce, portfolio, editorial, and developer tool, and scores results against a 14-dimension rubric. The reality-skill then checks whether the finished interface actually works end-to-end: tracing user journeys, catching dead buttons, placeholder data, stub handlers, and missing error or loading states. Install via npx skills add Eid0lon/zero-slop and activate whichever skills your agent needs. The full README is longer than what was provided.
A set of three AI agent skills that detect, fix, and prevent generic-looking AI-generated user interfaces.
Mainly Python. The stack also includes Python.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.