building-frontend-ui

building-frontend-ui is a skill for Claude Code, Codex from Cristhianzl/claude-skills-czl. It costs 0 tokens per session (2,604 once invoked), scanned A, original, MIT.

A set of guidelines for creating, changing, or reviewing the visible parts of a software product, including components, forms, layouts, accessibility, and data handling.

In plain words
What is it for?
Use it when building or reviewing web pages, screens, reusable components, client-side data fetching, and styling.
Why use it?
It helps prevent interfaces that fail during loading, errors, empty results, long content, different screen sizes, or real-world use.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

Good fit Use it when building or reviewing web pages, screens, reusable components, client-side data fetching, and styling.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cristhianzl/claude-skills-czl/building-frontend-ui
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 Cristhianzl/claude-skills-czl --skill building-frontend-ui
Clone the repo
git clone --depth 1 https://github.com/Cristhianzl/claude-skills-czl

Made for: Claude Code, Codex.

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 building-frontend-ui

README.md
[![agentmods](https://agentmods.dev/badge/skills/cristhianzl/claude-skills-czl/building-frontend-ui/github.svg)](https://agentmods.dev/skills/cristhianzl/claude-skills-czl/building-frontend-ui)
Your own site
<a href="https://agentmods.dev/skills/cristhianzl/claude-skills-czl/building-frontend-ui"><img src="https://agentmods.dev/badge/skills/cristhianzl/claude-skills-czl/building-frontend-ui/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 building-frontend-ui

Your own site · 80×15
<a href="https://agentmods.dev/skills/cristhianzl/claude-skills-czl/building-frontend-ui"><img src="https://agentmods.dev/badge/skills/cristhianzl/claude-skills-czl/building-frontend-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,604 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 $0.00000 $0.02604
Opus 5 $0.00000 $0.01302
Sonnet 5 $0.00000 $0.00521
Haiku 4.5 $0.00000 $0.00260

Measured yesterday against content hash 5de7ca98d56f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

building-frontend-ui 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 yesterday.

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.

configs/agnostic/skills/building-frontend-ui/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Building Frontend UI

A frontend change is good when it reuses what already exists, is accessible by default, handles every state (loading, error, empty, long content), performs under real data, and leaks no data to the client. This skill is framework-agnostic: the workflow and rules live here; framework-specific mechanics live in references/<framework>.md and are loaded only when relevant.

Read first (always)

List learnings/ and read every file relevant to the current task — project conventions, the design system, banned dependencies, and component patterns live there and override the defaults in this file. If a learning conflicts with this skill, the learning wins — mention it.

Starting from zero?

If there is no existing design to extend (new site, new product surface, greenfield page), read references/designing-from-scratch.md before Step 0 and deliver its design plan as text before any code: strategy (one measurable goal, one primary action) → structure (sitemap, wireframe, section jobs) → tokens → components → pages. Visual decisions (type, color, space, motion, the generic-page anti-patterns) follow references/design-craft.md. Before declaring from-scratch work done, run the Vibe Check + delivery scorecard in references/anti-vibe-coded.md and report item by item — it is the definition of done for greenfield UI.

When a design system already exists, the opposite applies: the existing tokens, components, and layout are the law (Step 0) — never introduce a parallel style, and never use the from-scratch rules to justify restyling what's already consistent. Only the functional layers of the anti-vibe audit still apply (states, dead clicks, semantics, mobile, a11y).

Step 0 — Audit before you build (do not skip)

Most bad frontend work is net-new code that should have been reuse. Before writing anything:

  1. Find the design system. Grep for the token/theme source — CSS custom properties (--color-*, --space-*), a tailwind.config, a theme file, design-token JSON. Use those tokens; never hardcode raw hex, px spacing, or font sizes in a component. Before defining any new color, sweep the existing palette and name the closest existing tokens — a new token that duplicates (or nearly duplicates) a color that already has a name is a defect, not a choice (hooks/check-design-tokens.py flags this after the fact; the sweep comes first).
  2. Find existing components and utilities. Grep/glob for a component that already does this (button, modal, field, table, empty-state) and reuse or extend it instead of creating a parallel one. Match the established prop and naming patterns.
  3. Find the i18n system, if any. Grep for a locales/ dir, i18n config, or translation calls (t(...), $t, useTranslation, FormattedMessage). If the project has one, every user-facing string goes through it — a hardcoded string in a translated app is a bug, and every new key must be added to all locale files (a key present in one language and missing in another ships broken UI).
  4. Read the surrounding files to copy the project's conventions (file layout, styling approach, state approach, test location).

Read the full file on GitHub · 109 lines

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. yesterday Changed 5de7ca98d56f
  2. 2d ago Changed · +10 lines 91facd4d399d
  3. 12d ago First seen · 99 lines · 0 tokens per session scan A 4538aae46e4a

Subscribe to this mod's changes

building-frontend-ui is a skill published in the GitHub repository Cristhianzl/claude-skills-czl (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,604 tokens. 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

internationalization

Plan and run a multi-language or multi-region site. Use this skill when adding new locales, choosing URL structure for languages (subfolders vs subdomains vs ccTLDs), implementing hreflang, planning translation workflow, handling currency and date formats, designing for RTL languages, or auditing a stalled…

rampstackco/claude-skills · 123 tokens

information-architecture

Design the structure of a website or product including sitemap, navigation, URL structure, content types, taxonomy, and labeling. Use this skill whenever the user asks to plan a sitemap, design navigation, structure URLs, define content types, build taxonomies, design site search, or organize content at the system…

rampstackco/claude-skills · 131 tokens

frontend

Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.

code-yeongyu/oh-my-openagent · 49 tokens

ambience-skill

Layer A ambience-and-typographic-motion reference anchored to the react-bits catalog (reactbits.dev). Stacks on any style skill whenever work adds a hero atmosphere, an animated or shader background, a typographic reveal (split, blur, shimmer, typewriter, count-up, marquee), scroll storytelling, or card surface…

code-yeongyu/oh-my-openagent · 132 tokens

interaction-skill

Layer A interaction-mechanics reference anchored to the beui.dev catalog. Stacks on any style skill whenever work adds or changes motion or interaction — micro-interactions, animated components, transitions, gestures, hover/press/state feedback, loading/success/error morphs, 'make it feel alive'. Mandates reading the…

code-yeongyu/oh-my-openagent · 104 tokens

layout-skill

Layer A layout-mechanics reference. Stacks on any style skill when the screen is an app shell, dashboard, settings, list-detail, mail/inbox, or any layout with fixed regions plus a scrolling body — or when a layout breaks under long, empty, or unbroken content. Owns spatial structure and scroll ownership; owns zero…

code-yeongyu/oh-my-openagent · 88 tokens