agentsclimarketplace

Design ui

Skill vasu-devs/Forge/skills/design-ui

Build or redesign frontend UI that doesn't look templated or AI-generated. Use when creating components, pages, landing pages, or restyling existing UI — before writing CSS/markup, and before shipping any visual work.From its SKILL.md

Install
npx -y skills add vasu-devs/Forge --skill design-ui

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

4.8 KB, ~1.1k tokens by cl100k_base, as published. Nobody here has run it

██████╗ ███████╗███████╗██╗ ██████╗ ███╗   ██╗      ██╗   ██╗██╗
██╔══██╗██╔════╝██╔════╝██║██╔════╝ ████╗  ██║      ██║   ██║██║
██║  ██║█████╗  ███████╗██║██║  ███╗██╔██╗ ██║█████╗██║   ██║██║
██║  ██║██╔══╝  ╚════██║██║██║   ██║██║╚██╗██║╚════╝██║   ██║██║
██████╔╝███████╗███████║██║╚██████╔╝██║ ╚████║      ╚██████╔╝██║
╚═════╝ ╚══════╝╚══════╝╚═╝ ╚═════╝ ╚═╝  ╚═══╝       ╚═════╝ ╚═╝

Design UI with taste (anti-slop)

Default AI design fails because it reaches for statistical clichés. This skill replaces "looks fine" with deliberate, checkable taste. The premise: bad AI UI is predictable, so the fixes can be mechanical.

Start with a Design Read + dials

Before any markup, state one line: "Reading this as a <page kind> for <audience>, vibe <word>, leaning <direction>." Then set three dials (1-10) and let them drive choices:

  • DESIGN_VARIANCE — low = clean/centered; high = asymmetric/editorial
  • MOTION_INTENSITY — low = hover/focus transitions only; mid = entrance + scroll reveals; high = scroll-scrub/parallax/magnetic
  • VISUAL_DENSITY — low = spacious; high = dense dashboard

The dials are constraints, not decoration — let the value gate the technique: MOTION_INTENSITY ≤ 3 → no scroll-jacking/parallax, hover/focus only; VISUAL_DENSITY ≤ 3 → generous whitespace, one primary action per view. If a choice violates its dial, change the choice.

Commit to one direction

Pick a single aesthetic and execute it fully — minimalist editorial (Notion/Linear), high-end agency, brutalist/industrial, etc. Averaging directions produces mush. If the user hasn't chosen, propose one with rationale.

Mechanically-checkable anti-slop bans

These are the AI tells; treat them as hard checks, not suggestions:

  • No em-dash in UI copy. Binary ban — not "use sparingly." (Em-dashes are the #1 AI-text tell.)
  • No Inter/Roboto as the default font, and no system-font-stack-by-default. Use ≥2 deliberate weights/sizes from a stated type scale (name the ratio, e.g. 1.25).
  • No AI-purple / generic gradient-on-white hero. No #8B5CF6-family default gradients.
  • No three-equal-cards row as the default content layout.
  • Eyebrow restraint: at most ~1 uppercase-tracked "eyebrow" label per 3 sections. Count them; if more, cut.
  • Kill the cheap defaults — by rendered property, not framework class: no hairline neutral-gray 1px border on every surface; no single uniform low-opacity drop shadow on everything (shadow-md-equivalent); no default linear/ease-in-out timing. Use intentional borders, layered/soft shadows, and ≥1 custom easing or spring. (Tailwind names are just examples — the rule is the rendered property, so it applies equally on vanilla CSS, styled-components, SwiftUI, etc.)

Verify visually — never ship CSS blind

Render the real view (dev-preview harness + headless browser / Playwright with system Chrome), then re-read the screenshots — don't infer from CSS. Make it a mechanical gate: capture at 390 / 768 / 1280 px widths, save to a scratch dir, and forbid "done" unless those files exist and you've inspected them for spacing, hierarchy, contrast, overflow, and small-screen fit. A screenshot you never open is not verification. (This is forge:verify applied to pixels.)

Pre-flight gate

Before "done," tick: direction committed · type deliberate · spacing rhythm consistent · hierarchy clear · states (hover/focus/empty/error) handled · responsive checked · text contrast ≥ 4.5:1 (WCAG AA) on the rendered output · visible focus ring on every interactive element · all motion gated behind prefers-reduced-motion: no-preference · all bans above honestly clear · rendered-and-eyeballed. If any box can't be honestly ticked, it isn't finished.

Note

For reference-image-first workflows (generate comps, then build to match), the tasteskill:imagegen-* and tasteskill:image-to-code skills complement this — this skill is the code-side taste enforcer.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 1 of the 12 instructions most design frontend skills give in ~1.1k tokens

Counted across 1,179 of the 2,086 authors here whose files we hold, read 2026-09-06

  • Commit to a bold aesthetic directionhere, and in 31 of 1179, across 24 files
  • Prefer component composition over inheritancein 28 of 1179, across 14 files
  • Animate only transform and opacity propertiesin 27 of 1179, across 22 files
  • Memoize expensive computations with useMemoin 26 of 1179, across 13 files
  • Use semantic HTML elementsin 24 of 1179, across 23 files
  • Virtualize long lists for performancein 21 of 1179, across 10 files
  • Use CSS variables for design tokensin 20 of 1179, across 14 files
  • Implement loading, empty, and error statesin 20 of 1179
  • Lazy load heavy components with Suspensein 19 of 1179, across 8 files
  • Respect prefers-reduced-motion media queriesin 18 of 1179, across 10 files
  • Prioritize CSS-only animations for HTMLin 18 of 1179, across 16 files
  • Use compound components for related UI elementsin 18 of 1179, across 7 files

Said here and by no other author read

  • State page kind audience vibe and direction
  • Use at least two deliberate font weights
  • Use intentional borders and layered shadows
  • Use custom easing or spring animations
  • Inspect screenshots for spacing and hierarchy
  • Gate motion behind prefers reduced motion media query

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.