Skill Frontend Ux Guardrails logo

Skill Frontend Ux Guardrails

Organization
IAPro-Community
skill-frontend-ux-guardrails

Use as a frontend UX quality gate for responsive behavior, overflow, accessibility, interaction usability, touch targets, typography, layout stability, mobile behavior, focus states, reduced motion, and final visual validation.

Overview

PublisherIAPro-Community
RepositoryOrquestrador-Maestro
Skill nameskill-frontend-ux-guardrails
Stars
63
Forks
11
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by IAPro-Community on GitHub. Read the source before you install it.

Installation

Install the Skill Frontend Ux Guardrails AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/IAPro-Community/Orquestrador-Maestro/tree/v1/codex/skills/skill-frontend-ux-guardrails
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/IAPro-Community/Orquestrador-Maestro.git /tmp/Orquestrador-Maestro
mkdir -p .claude/skills
cp -r /tmp/Orquestrador-Maestro/codex/skills/skill-frontend-ux-guardrails .claude/skills/skill-frontend-ux-guardrails
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Skill Frontend Ux Guardrails in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Skill Frontend Ux Guardrails on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Skill Frontend Ux Guardrails is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Skill Frontend UX Guardrails

Run this skill near the end of a frontend change, especially after a complex marketing experience, redesign, or interaction pass. It is a quality gate, not a replacement for experience strategy, visual direction, component implementation, or browser automation.

Gate Order

  1. Inspect the real rendered surface, routes, components, tokens, breakpoints, states, and test expectations.
  2. State the primary user task and record P0/P1 issues before polish.
  3. Fix layout stability and comprehension before visual refinement.
  4. Validate desktop, laptop, tablet, and mobile behavior, including long realistic content.
  5. Check keyboard, focus, labels, contrast, touch targets, reduced motion, and non-pointer use.
  6. Run the lightest meaningful lint, typecheck, build, targeted test, browser, or screenshot gate available.
  7. Report tested viewports, corrected issues, and residual risk.

Quality Rubric

Score the target from 0 to 4 for hierarchy, contrast, responsiveness, accessibility, performance, interaction usability, and visual integrity. Resolve P0/P1 findings before delivery. Defer P2/P3 refinements only when they do not affect the requested task or the primary user path.

Responsive And Layout

  • Verify 320x568, 390x844, 768x1024, 1024x768, and 1440x900 or a representative desktop width.
  • At 320px, check button wrapping, text clipping, tables, dialogs, sticky areas, and bottom bars.
  • At tablet widths, check sidebars, drawers, charts, grids, and action collisions.
  • At desktop widths, prevent unreadable line lengths, sparse accidental grids, and stretched media.
  • Test long names, emails, plan labels, currencies, percentages, error messages, and localized values.
  • Check page-level overflow, duplicate scrollbars, wrapping, sticky offsets, z-index collisions, layout shift, and safe areas.
  • Do not require horizontal scrolling for core comprehension. If a table must scroll, keep its context, labels, and actions usable.

Accessibility And Interaction

  • Require semantic HTML, logical keyboard order, visible focus states, accessible names, sufficient contrast, readable text, and usable touch targets.
  • Verify loading, empty, no-results, error, disabled, success, pending, selected, validation, and destructive-confirmation states where relevant.
  • Do not hide critical actions only on hover or require color, animation, or pointer input to understand content.
  • Include and test @media (prefers-reduced-motion: reduce); simplify or disable non-essential motion without losing meaning.
  • Confirm forms preserve user input after errors and that dialogs, menus, popovers, and table actions are dismissible and keyboard-accessible.

Visual Integrity

Inspect screenshots or browser snapshots when changing layout, typography, navigation, charts, modals, sticky behavior, or motion. Check hierarchy, line breaks, clipping, overlap, blank canvases, invisible text, icon alignment, contrast, layout shift, and animation glitches. Compare before/after for redesigns or visual cleanup.

Generated-UI Smells

Flag generic gradients, gratuitous glassmorphism or glow, side-accent cards, nested cards, flat hierarchy, one-font-everywhere treatment, giant icon tiles, redundant helper copy, and modal abuse. Keep an intentional pattern only when the product, content, or experience strategy explains it. Use skill-open-design-ui for visual-system changes and skill-impeccable for focused polish; do not expand a layout fix into an unrequested redesign.

Completion Criteria

  • No unintended page-level horizontal overflow.
  • Desktop and mobile are intentionally designed and stable.
  • Primary actions, system states, and recovery paths are clear.
  • Focus, contrast, touch, reduced motion, spelling, accents, and UTF-8 are safe.
  • Existing routes, forms, analytics, and behavior are preserved unless explicitly changed.
  • The rendered result, not only the source or build, was verified.

Related Skills

  • skill-premium-web-experience — final gate for complex premium web experiences.
  • skill-open-design-ui — visual direction, tokens, and visual QA.
  • skill-modern-ui-patterns — components and interaction states.
  • skill-impeccable — bounded critique and polish.
  • skill-webapp-testing — E2E or visual regression when a flow changes.

Frequently asked questions

What does the Skill Frontend Ux Guardrails AI skill do?

Use as a frontend UX quality gate for responsive behavior, overflow, accessibility, interaction usability, touch targets, typography, layout stability, mobile behavior, focus states, reduced motion, and final visual validation.

Why use Skill Frontend Ux Guardrails on TypingMind?

Because you install it once and use it with any model. Skill Frontend Ux Guardrails is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Skill Frontend Ux Guardrails in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/IAPro-Community/Orquestrador-Maestro/tree/v1/codex/skills/skill-frontend-ux-guardrails. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Skill Frontend Ux Guardrails?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Skill Frontend Ux Guardrails?

As many as you like. As long as a model supports skills, you can use Skill Frontend Ux Guardrails with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Skill Frontend Ux Guardrails AI skill free?

Yes. It is published on GitHub by IAPro-Community under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇