no-ai-slop

no-ai-slop is a skill for Claude Code from claudiusararu/unslop-ui-skill. It costs 131 tokens per session (1,834 once invoked), scanned A, original, MIT.

A design guide for creating or reviewing website, web-app, and mobile-app interfaces that avoid common AI-generated visual patterns.

In plain words
What is it for?
Use it when building or checking user interfaces, especially their typography, colors, spacing, headings, and layout decisions.
Why use it?
It helps identify and remove generic choices such as default fonts, predictable layouts, weak contrast, and overused gradients.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it when building or checking user interfaces, especially their typography, colors, spacing, headings, and layout decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/claudiusararu/unslop-ui-skill/no-ai-slop
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 claudiusararu/unslop-ui-skill --skill no-ai-slop
Clone the repo
git clone --depth 1 https://github.com/claudiusararu/unslop-ui-skill

Made for: Claude Code.

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 no-ai-slop

README.md
[![agentmods](https://agentmods.dev/badge/skills/claudiusararu/unslop-ui-skill/no-ai-slop/github.svg)](https://agentmods.dev/skills/claudiusararu/unslop-ui-skill/no-ai-slop)
Your own site
<a href="https://agentmods.dev/skills/claudiusararu/unslop-ui-skill/no-ai-slop"><img src="https://agentmods.dev/badge/skills/claudiusararu/unslop-ui-skill/no-ai-slop/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 no-ai-slop

Your own site · 80×15
<a href="https://agentmods.dev/skills/claudiusararu/unslop-ui-skill/no-ai-slop"><img src="https://agentmods.dev/badge/skills/claudiusararu/unslop-ui-skill/no-ai-slop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,834 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 $0.00131 $0.01834
Opus 5 $0.00066 $0.00917
Sonnet 5 $0.00026 $0.00367
Haiku 4.5 $0.00013 $0.00183

Measured 12d ago against content hash e9e2c489ec4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

no-ai-slop 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 12d 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.

.claude/skills/no-ai-slop/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

No AI Slop

AI- and template-built UIs share a recognizable set of "tells." The root cause is always the same: uniformity + unconsidered defaults - one font, one accent, one card, one centered template applied to everything. Build UI that looks deliberately designed by applying both layers.

How to use

  • Generating UI -> apply Layer 1 always + the active Layer 2 style.
  • Reviewing UI -> scan against Layer 1 and fix every hit (use the self-check).
  • Full reference: TELLS.md (~100 tells across 9 categories). This file is the distilled, always-on set.

Layer 1 - Universal anti-tells

Fonts & type

  • Don't ship default fonts: Inter, Geist, or the "Space Grotesk + Instrument-Serif-italic + Inter" trio. Choose a face with a point of view; pair display + body with real contrast.
  • Solid heading color - no gradient-clipped text.
  • Real weight hierarchy - not font-semibold/font-medium as the heaviest weight on the page.
  • Headings wrap naturally: no manual <br>, no text-balance on everything, no 4-line or orphan-word headlines. Keep them tight (~5-9 words).
  • Left-aligned body/subtitles run to the container's content width; only CENTERED text gets a max-width measure. Never a thin floating column.
  • Sentence case for headings/buttons. No spaced-out eyebrow/kicker over headings (pill, rule+caps, or spaced-caps) - the heading leads.
  • tabular-nums for prices/stats; no negative tracking on body.

Color & background

  • No indigo/violet-600 default primary, no "VibeCode purple" #8B5CF6, no purple-to-blue (or amber-to-pink) gradients.
  • No cream/#faf8f4 default background; no dotted-grid, mesh-blob, aurora, or spotlight backgrounds; no glassmorphism by default.
  • High-contrast body text (near-black on light, slate-200+ on dark) - never gray-400/500 as body. Verify WCAG AA.
  • One deliberate accent (not blue/purple by reflex), used sparingly, built as a ramp. No raw Tailwind status colors; no default blue focus ring.
  • Don't default to dark-only. Avoid uniform soft shadows; use borders/contrast + a real elevation ramp.

Read the full file on GitHub · 81 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. 12d ago First seen · 81 lines · 131 tokens per session scan A e9e2c489ec4a

Subscribe to this mod's changes

no-ai-slop is a skill published in the GitHub repository claudiusararu/unslop-ui-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 131 tokens to every session and 1,834 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

theming-components

Provides design token system and theming framework for consistent, customizable UI styling across all components. Covers complete token taxonomy (color, typography, spacing, shadows, borders, motion, z-index), theme switching (CSS custom properties, theme providers), RTL/i18n support (CSS logical properties), and…

ancoleman/ai-design-components · 117 tokens

designing-layouts

Designs layout systems and responsive interfaces including grid systems, flexbox patterns, sidebar layouts, and responsive breakpoints. Use when structuring app layouts, building responsive designs, or creating complex page structures.

ancoleman/ai-design-components · 45 tokens

premium-hero-builder

Build premium, dark-themed hero sections and landing pages with cinematic video backgrounds, liquid glass morphism, editorial typography, and pixel-perfect specifications. Based on the Viktor Oddy methodology of detailed design prompts that produce agency-quality results from AI code generation. Use when building hero…

sacredvoid/skillkit · 74 tokens

web-prototype

General-purpose desktop web prototype. Single self-contained HTML file built by copying the seed assets/template.html and pasting section layouts from references/layouts.md. Default for any landing / marketing / docs / SaaS page when no more specific skill matches.

nexu-io/open-design · 59 tokens

velar-luxury-real-estate

Use this plugin when the user wants a high-end luxury real-estate / architecture landing page with cinematic scroll choreography: a typewriter preloader that lifts away, a scroll-driven house image that rises from below and scales up while pinning to a dark statement section, a sticky dark stats band with count-up…

nexu-io/open-design · 119 tokens

web-prototype-taste-brutalist

Swiss industrial-print web prototype. Newsprint canvas, monolithic black grotesque, viewport-bleeding numerals, hairline grid dividers, hazard-red accent, ASCII syntax decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Swiss Industrial Print mode).

nexu-io/open-design · 70 tokens