Skip to content
SkillModel-led2,871 tokens in use

frontend-ui-engineering

Build accessible, responsive, production-quality interfaces with composable components and the project's own design system.

119,377 stars on the repository MIT Licenseaddyosmani/agent-skills · skills/frontend-ui-engineering
npx skills add addyosmani/agent-skills --skill frontend-ui-engineering
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing frontend-ui-engineering costs

58tokens idle
2,871tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure19/25
  • Examples12/15
  • Output15/15
  • Size13/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community76
  • Maturity32
  • Momentum40

Frontend UI Engineering guides an agent when it builds or changes user-facing interfaces. It covers component file structure, composition, separating data fetching from presentation, a state management ladder and design system adherence.

The skill lists the visual habits that make generated UI look generic, sets WCAG 2.1 AA requirements for keyboard use, labels and focus, and requires loading, empty and error states and testing at four breakpoints.

What You Get

  • Component architecture patterns with React examples
  • A table that maps common AI-generated UI defaults to production-quality choices
  • WCAG 2.1 AA guidance for keyboard, ARIA labels, focus and empty states
  • A verification checklist and red flags such as components over 200 lines

Common Use Cases

  • Building new components or pages
  • Making an interface responsive
  • Fixing accessibility and keyboard issues in a UI
  • Choosing where state should live

What Makes It Unique

The skill names the visual tells of generated UI and replaces each with an instruction to use the project’s own palette, radii and spacing scale. It also describes reference-led design, which turns observed screens into a design contract and forbids copying another product’s branding or layout.

Under The Hood

The skill is a single SKILL.md of instructions with React, TypeScript, CSS and Tailwind examples. It runs no scripts and installs nothing. The agent is told to run the project’s own test, type check and lint commands and to report which checks it could not run.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers