UI UX Fixer — AI skill for Claude Code
Claude Code skill (portable to any AI harness) that reviews UI/UX work through Luke Wroblewski's published design principles.
How to install UI UX Fixer
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open nerdstalker/ui-ux-fixer and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What UI UX Fixer does
Claude Code skill (portable to any AI harness) that reviews UI/UX work through Luke Wroblewski's published design principles. Unofficial.
Alternatives in AI
- Impeccable — The design language that makes your AI harness better at design 13.9k ★
- ARIS Agent Guide — For AI agents reading this repo 6.2k ★
- Skill Architecture — System architecture and API design with multi-AI consensus — use for design reviews and new subsystems 2.8k ★
README
UI/UX Fixer
A [Claude Code](https://claude.com/claude-code) skill that reviews and improves UI/UX design work through the lens of **Luke Wroblewski's** published principles. It uses Luke's MCP server to retrieve relevant material from his writings, presentations, books, videos, audio, posts, and other published work for each design task.
**Unofficial.** This skill is based on Luke Wroblewski's public writing, books, and talks ([lukew.com](https://www.lukew.com), *Mobile First*, *Web Form Design*). It is not affiliated with, created by, or endorsed by Luke Wroblewski. All principles are attributed to their published sources.
What it does
Once installed, Claude uses this skill whenever you ask for a design review, UX critique, or design advice. It works in three modes:
- Advise — opinionated guidance while you're designing, grounded in published principles rather than taste.
- Critique — a structured review of a screen, form, flow, or codebase, with findings ordered by user impact, each tied to the principle it violates and its source.
- Apply — with your approval, it implements the agreed fixes in your code.
For Advise and Critique tasks, the skill searches Luke's live archive before forming recommendations, then cites the few sources that materially shaped the answer. The bundled references remain its stable design framework and fallback when the MCP server is unavailable.
Example prompts:
- "Review this sign-up form" (with a screenshot or the component code)
- "Critique the mobile layout of my landing page"
- "What would LukeW say about this checkout flow?"
- "Review the chat UI of my AI app"
What's inside
ui-ux-fixer/
├── SKILL.md # workflow, core philosophy, output format
└── references/
├── forms.md # Web Form Design: labels, validation, errors, gradual engagement
├── mobile.md # Mobile First: thumb zones, touch targets, content-first
├── data-informed.md
Related Skills
Lukew Design Skill
Claude Code skill (portable to any AI harness) that reviews UI/UX work through Luke Wroblewski's published des
AI Agent Harness Learning
This is the repository that summarizes the AI Agent Development courses into a set of production AI Agent deve
Self Learning Design Library
Retrieval library for LLM-assisted design work: distilled designer style profiles, universal principles, and p
Use Crew Gateway
Route an OpenAI/Anthropic-compatible client through the portable farmd control plane's virtual crew model, for
AI Assisted Speedruns
An open standard and plugin framework for AI Assisted Speedruns: an LLM agent plays a game through three harde
Upstream Watch
Review pydantic-ai and pydantic-ai-harness releases published since the last watch entry, and record a verdict
Related Agents
Monk Frontman
General Monk operator for portable AI hosts. Route install, auth, deploy, docs, and editor work through monk-a
Cmp Orchestrator
Coordinator for multi-step Kotlin/Compose Multiplatform harness work — plans, writes self-contained briefs, de
Retro Reviewer
Reviews one prior session through ax's normalized cross-harness Turn view and emits a structured retro (tried