uiux-frontend-engineering

uiux-frontend-engineering is a skill for Claude Code, Codex from oghie/skillsets. It costs 78 tokens per session (1,801 once invoked), scanned A, original, MIT.

A guide for planning, designing, implementing, and checking user interfaces for websites, mobile apps, and other interactive products. It covers how screens work, look, adapt to different devices, and support users with accessibility needs.

In plain words
What is it for?
Use it for user flows, wireframes, visual designs, design systems, frontend implementation, responsive layouts, accessibility reviews, and Figma-to-code handoffs.
Why use it?
It helps connect user goals and business needs to concrete interface decisions before the product is shipped. It also provides ways to check whether the result works across screen sizes and interaction styles.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the skillsets plugin — 9 skills, 4 commands, 1 hook, 4 MCP servers shipped together

Good fit Use it for user flows, wireframes, visual designs, design systems, frontend implementation, responsive layouts, accessibility reviews, and Figma-to-code handoffs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oghie/skillsets/uiux-frontend-engineering
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add oghie/skillsets --skill uiux-frontend-engineering
Clone the repo
git clone --depth 1 https://github.com/oghie/skillsets

Made for: Claude Code, Codex.

Or install skillsets, the plugin that ships this one along with the rest of its 9 skills, 4 commands, 1 hook, 4 MCP servers.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for uiux-frontend-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/oghie/skillsets/uiux-frontend-engineering/github.svg)](https://agentmods.dev/skills/oghie/skillsets/uiux-frontend-engineering)
Your own site
<a href="https://agentmods.dev/skills/oghie/skillsets/uiux-frontend-engineering"><img src="https://agentmods.dev/badge/skills/oghie/skillsets/uiux-frontend-engineering/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for uiux-frontend-engineering

Your own site · 80×15
<a href="https://agentmods.dev/skills/oghie/skillsets/uiux-frontend-engineering"><img src="https://agentmods.dev/badge/skills/oghie/skillsets/uiux-frontend-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,801 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.01801
Opus 5 $0.00039 $0.00901
Sonnet 5 $0.00016 $0.00360
Haiku 4.5 $0.00008 $0.00180

Measured 9d ago against content hash ff95234af5fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

uiux-frontend-engineering scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/theme_catalog.py, scripts/uiux_static_audit.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/uiux-frontend-engineering/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UIUX Frontend Engineering

Core Rule

Treat UI as a tested product interface, not decoration: connect user goals, business goals, interaction model, visual system, implementation constraints, and validation evidence before shipping screens or components.

First Pass

  1. Classify the task: UX strategy, research, persona, UX mapping, IA/sitemap, user flow, wireframe, prototype, mockup, UI pattern selection, visual UI, design system, frontend stack/library selection, frontend implementation, responsive/mobile, accessibility, redesign/review, handoff, or XR/spatial interface.
  2. Identify target surface: web, mobile web, native mobile, desktop web app, kiosk, embedded screen, WebXR, VR, AR, MR, or spatial computing.
  3. Name users, context, primary jobs, failure modes, conversion or task metric, platform constraints, input method, and trust/safety concerns.
  4. Decide fidelity: sketch/flow, low-fidelity wireframe, clickable prototype, high-fidelity visual, coded prototype, production component, or XR graybox.
  5. Select validation before implementation: heuristic review, accessibility audit, responsive screenshots, usability test, click/first-impression test, A/B test, performance check, or XR comfort review.

Required Reads By Task

  • End-to-end UX process, discovery, personas, user interviews, analytics, card sorting, surveys, support tickets, wireframes, validation, handoff, or QA: references/ux-process-and-research.md.
  • Persona strategy, "Comparing Key Persona Types", buyer/customer/user/proto-persona distinction, goal-directed/role-based/fictional/engaging personas, customer journey maps, empathy maps, experience maps, service blueprints, touchpoints, or friction mapping: references/personas-and-ux-mapping.md.
  • Information architecture, IA principles, taxonomy, labels, navigation models, search, card sorting, tree testing, HTML/XML/mobile/image/video/news sitemaps, or sitemap handoff: references/information-architecture-and-sitemaps.md.
  • Wireframes, prototypes, mockups, fidelity choice, paper/Wizard-of-Oz/clickable/coded prototypes, microcopy, microinteractions, or mockup-to-implementation readiness: references/wireframes-prototypes-and-mockups.md.
  • UI pattern selection, visual hierarchy patterns, Z-pattern/F-pattern layouts, primary actions, forgiving input, breadcrumbs, progressive disclosure, lazy registration, infinite scroll, modals, cards, autocomplete, sticky navigation, mobile UI patterns, or dark-pattern review: references/ui-patterns-catalog.md.
  • Psychology laws, cognitive load, target sizing, choice overload, familiarity, aesthetics, memory, complexity, responsiveness, ethics, or dark-pattern risk: references/psychology-and-interaction-laws.md.
  • Visual UI composition, Gestalt, hierarchy, color, typography, spacing, affordance, signifiers, forms, cards, states, icons, illustrations, or motion: references/visual-interface-composition.md.
  • Figma, design systems, tokens, components, auto layout, constraints, responsive/adaptive design, plugin/handoff flow, or developer collaboration: references/responsive-design-systems-and-handoff.md.
  • Frontend framework/library selection, styling approach, component library choice, Radix UI, shadcn/ui, Ant Design, Mantine UI, MUI, vanilla CSS, CSS Modules, Linaria, PostCSS, Bulma, Tailwind CSS, or stack trade-offs: references/frontend-stack-and-library-selection.md.
  • Frontend implementation, accessibility, performance, state coverage, visual QA, component contracts, framework-neutral CSS/component mapping, or production readiness: references/frontend-implementation-quality.md.
  • Mobile/touch design, one-handed use, touch targets, mobile navigation, forms, gestures, device preview, or native-app constraints: references/mobile-and-touch-ux.md.
  • XR, spatial computing, WebXR, VR, AR, MR, 3D UI, spatial objects, OOUX, locomotion, comfort, haptics, voice, gaze, avatars, embodiment, safety, or spatial analytics: references/xr-spatial-ux-and-3d-interfaces.md.
  • AI-assisted design, generative assets, design copilots, AI disclosure, sourcing, IP, safety, privacy, transparency, or manipulation risk: references/ai-assisted-and-ethical-design.md.
  • Theme/style selection, static token database, CSS variables, framework/library token mapping, or visual style guardrails: references/theme-token-database.md and the relevant file under theme/.

Read the full file on GitHub · 77 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 77 lines · 78 tokens per session scan A ff95234af5fb

Subscribe to this mod's changes

uiux-frontend-engineering is a skill published in the GitHub repository oghie/skillsets (9 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 1,801 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

accessibility-compliance

Web accessibility patterns for news and academic sites. Use for WCAG audits, alt text, accessible data viz, and assistive tech.

jamditis/claude-skills-journalism · 32 tokens

web-ui-best-practices

Signs of taste in web UI. Use when building or reviewing web interfaces, dashboards, SaaS apps, or internal tools.

jamditis/claude-skills-journalism · 32 tokens

web-design-picker

Use when creating distinct website directions, a client review picker, asset catalog, previews, and Cloudflare-ready handoffs.

jamditis/claude-skills-journalism · 28 tokens

light-frontend-design

A design and implementation guide for building or improving web and app interfaces with React, Tailwind, or shadcn. It covers visual choices, responsive layouts, accessibility, and checks in a real browser.

Light0305/Light-skills · 459 tokens

chakra-ui-builder

Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…

chakra-ui/chakra-ui · 214 tokens

frontend-visual-qa

Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…

daymade/claude-code-skills · 145 tokens