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.
npx skills add sukirman1901/frontend-expert --skill ui-feelgit clone --depth 1 https://github.com/sukirman1901/frontend-expertWrote 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.
[](https://agentmods.dev/skills/sukirman1901/frontend-expert/ui-feel)<a href="https://agentmods.dev/skills/sukirman1901/frontend-expert/ui-feel"><img src="https://agentmods.dev/badge/skills/sukirman1901/frontend-expert/ui-feel/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.
<a href="https://agentmods.dev/skills/sukirman1901/frontend-expert/ui-feel"><img src="https://agentmods.dev/badge/skills/sukirman1901/frontend-expert/ui-feel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00099 | $0.01471 |
| Opus 5 | $0.00049 | $0.00736 |
| Sonnet 5 | $0.00020 | $0.00294 |
| Haiku 4.5 | $0.00010 | $0.00147 |
Grade A, and why
ui-feel 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.
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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Feel
Overview
Great interfaces compound from small craft details. After tokens + structure + anti-slop, apply this skill so the UI doesn’t just look correct — it feels right.
Adapted from make-interfaces-feel-better (MIT) for this pack.
When to use
- Finishing
/uibuilds (afteranti-ai-slop) /polish/ “rapihin detail” / “feels off” / “make it feel better”- Design audits that go beyond slop into craft
- Hover, press, enter/exit, icon swap micro-interactions
When to skip
- Pure token/theme pick with no UI surface
- Backend-only or copy-only edits
- User asked for a one-line fix unrelated to feel
Pack fit
| Skill | Job |
|---|---|
anti-ai-slop |
Kill generic AI aesthetic |
ui-feel |
Micro craft that compounds into polish |
motion |
Larger animation systems (Framer/GSAP timelines) |
accessibility |
Labels, keyboard, contrast (hit areas overlap here) |
Conflict rules (this pack wins):
- Prefer subtle layered transparent shadows — not heavy multi-layer card stacks (
anti-ai-slop) - Image outlines are optional (media cards / product shots), not mandatory on every
<img> - Keep project fonts; only add smoothing / wrap / tabular-nums
- Icons stay Reicon unless project already standardized another lib
Core principles (quick)
- Concentric radius —
outer = inner + padding - Optical > geometric alignment for icons in controls
- Subtle shadows over hard borders between sections (when depth is needed)
- Interruptible — CSS transitions for hover/toggle; keyframes for one-shot only
- Split + stagger enters (~100ms); soft exits (small
translateY, not full height) - Icon swaps — opacity + scale
0.25→1+ blur4px→0(spring bounce0if Motion) - Font smoothing on root (
antialiased) tabular-numsfor dynamic numberstext-wrap: balanceheadings ·prettyshort body- Scale on press — exactly
0.96(never below0.95); disable when distracting initial={false}onAnimatePresencefor default-state UI (skip load flash)- Never
transition: all— name properties will-changesparingly — only transform/opacity/filter when first-frame stutter- Hit area — 44×44 touch/mobile; ≥40×40 dense desktop; no overlapping hit targets
- Type ladder — ≤2 families; one h1/page; h1→body via tokens; body ~60–75ch when long-form (see judgment Typography ladder)
- Mobile craft — thumb-reachable primary actions; full-width CTAs <768 (
responsive-ui); safe-area on sticky chrome; optional sticky CTA bar for long forms — not desktop-only micro-polish
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.
- 9d ago First seen · 128 lines · 99 tokens per session scan A 5117ae8f3ad2
ui-feel is a skill published in the GitHub repository sukirman1901/frontend-expert (10 stars, last pushed 6d ago), licensed MIT. It adds 99 tokens to every session and 1,471 once invoked, about $0.0005 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.
Other skills, from other repositories
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…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
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…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.