Agent skill

web-ui-ux

Web UI/UX specialist guidance for designing, reviewing, and polishing web product UI (layout, usability, microcopy, accessibility, responsive behavior, forms, navigation). Use when asked to improve UI/UX, audit a page, design a screen, create a component spec, or generate HTML head/manifest/icon guidance for a web app; optionally applicable to Unreal UI (UMG) for UX heuristics.

Stars 2
Forks 0

Install this agent skill to your Project

npx add-skill https://github.com/ssdeanx/AI-Skills/tree/main/skills/web-ui-ux

SKILL.md

Web UI/UX

You help produce modern, usable, accessible web UI with clear, testable guidance.

How to run this skill well

Establish context quickly (ask only what you need): platform, audience/jobs-to-be-done, the page/component in scope, and constraints (brand, timeline, existing design system).

Prefer concrete outputs: a short prioritized fix list, a component spec (states + interactions), and accessibility notes.

Keep scope tight: avoid broad redesigns unless asked; fix the top usability issues first.

Core workflows

A) UI/UX review of an existing page

Do this when the user shares a screenshot, route/page, or component and asks for improvement.

Steps:

  1. Identify intent and primary action.
  2. Check clarity: hierarchy, CTA prominence, labels, and visual noise.
  3. Check usability: forms, errors, loading/empty states, and navigation.
  4. Check accessibility basics: keyboard, focus order, labels, contrast.
  5. Produce output: top issues (with why), fixes, quick wins vs deeper refactors.

Use detailed checklists in:

  • references/ui-review-checklist.md
  • references/accessibility-checklist.md

B) Designing a new screen/component

Do this when the user asks to design a new page, dialog, component, or flow.

Steps:

  1. Ask for minimum inputs: users + goal, must-have fields/actions, and target content density.
  2. Propose an IA/layout: structure, regions, hierarchy.
  3. Define component spec: states (default/hover/focus/disabled), async states (loading/empty/error), validation, microcopy.
  4. Provide acceptance criteria: responsive behavior and keyboard/focus behavior.

Use system defaults and token guidance in:

  • references/design-system-defaults.md

Output templates

UI/UX findings template

Use this structure:

  • Summary (1-2 sentences)
  • Top issues (prioritized)
    • Issue: ...
    • Why it matters: ...
    • Fix: ...
  • Accessibility notes
  • Responsive notes
  • Copy/microcopy suggestions

Component spec template

Use this structure:

  • Purpose
  • Anatomy (slots/parts)
  • States (default/hover/focus/disabled/loading/error/empty)
  • Keyboard interactions
  • Validation rules (if form-related)
  • Responsive behavior

Notes

  • Keep content ASCII-friendly when possible to avoid Windows encoding pitfalls in older validators.
  • This skill is web-first, but the same heuristics often apply to Unreal UIs (UMG): clarity, hierarchy, navigation, input focus, and feedback.

Expand your agent's capabilities with these related and highly-rated skills.

ssdeanx/AI-Skills

task-generator

Generate structured task lists from specs or requirements. IMPORTANT: After completing ANY spec via ExitSpecMode, ALWAYS ask the user: "Would you like me to generate a task list for this spec?" Use when user confirms or explicitly requests task generation from a plan/spec/PRD.

2 0
Explore
ssdeanx/AI-Skills

icon-generator

Generate web UI/UX icon assets (favicon.ico, apple-touch-icon, PWA icons incl. maskable) and optionally Unreal Engine packaging icons (Windows .ico, macOS .iconset/.icns, Linux .png) from a single source SVG/PNG; use when you need correct multi-size icon files, safe-area guidance, manifests/head tags, or automation.

2 0
Explore
ssdeanx/AI-Skills

hello-world

A simple introductory skill that demonstrates basic OpenCode skill functionality and provides a starting template

2 0
Explore
ssdeanx/AI-Skills

skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

2 0
Explore
davila7/claude-code-templates

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

23,776 2,298
Explore
davila7/claude-code-templates

openrlhf-training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

23,776 2,298
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results