agentleFS
hamzaciftcihamzaciftci/coding-orchestra/skills/frontend-engineering/SKILL.md

frontend-engineering

Skill0 starsChanged 38 days agoMITView on GitHub

Builds and polishes React, Next.js App Router and Tailwind interfaces to a professional standard, covering server and client component boundaries, forms, loading, empty and error states, accessibility, responsive layout, dark mode, performance, visual consistency and microcopy. Use when creating or changing pages or components, when an interface looks amateur or inconsistent and needs polish, or when reviewing frontend code, a dashboard or a landing page for quality.

13 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use observability, api-design and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • OpenAISkill

    observability

    Vercel Observability expert guidance — Drains (logs, traces, speed insights, web analytics), Web Analytics, Speed Insights, runtime logs, custom events, OpenTelemetry integration, and monitoring dashboards. Use when instrumenting, debugging, or optimizing application performance and user experience on Vercel.

    Also in 3 projects that use this

  • MicrosoftSkill

    api-design

    Guide for designing and documenting RESTful APIs. Use when asked to design an API, create endpoints, or document an API.

    Also in 4 projects that use this

  • Microsoft AzureSkill

    git-workflow

    Squad branching model: dev-first workflow with insiders preview channel

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    It holds at 360 px and at 1440 px: No accidental horizontal scroll, touch targets around 44 px, tables that reflow or scroll inside their …

    line 21
  2. Distinctive:

    It holds in both themes: if the project has dark mode, which means colours come from tokens.

    line 22

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Frontend engineering

Start from what the project already has. Find its components, tokens, spacing scale, form and data-fetching patterns, and build with those. A new screen that introduces its own button style, colour values or state library makes the product look less finished, however good it is in isolation. If the project has no system yet, say so and propose a small one (tokens and a handful of base components) before styling screens individually.

What "done" means for an interface

Most unfinished UI is finished on the happy path only. A screen is done when:

  • Every state is designed. Loading without layout shift, empty with an explanation and a next action, error in plain language with a way to retry, partial failure that does not take down the page, and success feedback.
  • It works without a mouse and without perfect eyesight. Real buttons and links, labelled inputs, visible focus, errors tied to their fields, contrast at WCAG AA, nothing conveyed by colour alone.
  • It holds at 360 px and at 1440 px. No accidental horizontal scroll, touch targets around 44 px, tables that reflow or scroll inside their own container.
  • It holds in both themes if the project has dark mode, which means colours come from tokens.
  • Forms defend against real use. Field-level errors, disabled and busy states during submit, no double submission, input preserved after a failed submit. Client validation is for the user's benefit; the server validates again.
  • Destructive actions say what will happen and ask first.
  • Copy is specific. Buttons name the action, errors say what to do next.

App Router specifics

The server and client component boundary, caching, Server Actions and hydration are where current React differs from what older code and habits assume. Read references/app-router-notes.md when working in a Next.js App Router project, and before adding "use client", useEffect data fetching or a global store.

Polish work

When the task is to make an existing interface look and feel professional, review before restyling. references/polish-review.md gives the dimensions to assess (hierarchy, type, spacing, colour, states, forms, mobile, copy, landing pages) and how to turn them into a prioritized list. Fix system-level causes first: one corrected token or base component improves every screen, and screen-by-screen tweaks drift apart again.

Polish must not change behaviour. Form submission, navigation, analytics hooks and query parameters should work exactly as before; if a visual change requires a behaviour change, call it out.

Verifying

Look at the result in a browser if you have any way to (a dev server and a browser tool, screenshots, the project's visual or end-to-end tests), at mobile and desktop widths and in both themes. Run typecheck, lint and tests. If you could not see it rendered, say so plainly; UI that only compiled has not been verified.

Changes to global tokens, the theme or shared base components affect every screen. Check a few unrelated screens after touching them, and mention the reach of the change in your summary.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.