full-stack-design-skills: Skill for Claude Code

.claude/skills/anti-ai-design-patterns/SKILL.md

anti-ai-design-patterns is a skill for Claude Code from plugin87/full-stack-design-skills. It costs 186 tokens per session (2,457 once invoked), scanned A, original, MIT.

A guide to spotting visual patterns that make interfaces look automatically generated or generic, sometimes called “AI slop.” It promotes deliberate choices in colors, typography, layout, borders, and icons so the interface feels intentional.

In plain words
What is it for?
Reviewing or creating user interfaces, components, landing pages, emails, and design tokens while checking for generic layouts, arbitrary accents, mismatched icons, and default visual choices.
Why use it?
It helps remove repeated template-like choices that can make a design look unfinished or impersonal. The guide gives review criteria for replacing those patterns with purposeful decisions.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is plugin87/full-stack-design-skills's own configuration. It tells Claude Code how to work on full-stack-design-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything full-stack-design-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to plugin87/full-stack-design-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/plugin87/full-stack-design-skills/main/.claude/skills/anti-ai-design-patterns/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/plugin87/full-stack-design-skills

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 anti-ai-design-patterns

README.md
[![agentmods](https://agentmods.dev/badge/skills/plugin87/full-stack-design-skills/anti-ai-design-patterns/github.svg)](https://agentmods.dev/skills/plugin87/full-stack-design-skills/anti-ai-design-patterns)
Your own site
<a href="https://agentmods.dev/skills/plugin87/full-stack-design-skills/anti-ai-design-patterns"><img src="https://agentmods.dev/badge/skills/plugin87/full-stack-design-skills/anti-ai-design-patterns/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 anti-ai-design-patterns

Your own site · 80×15
<a href="https://agentmods.dev/skills/plugin87/full-stack-design-skills/anti-ai-design-patterns"><img src="https://agentmods.dev/badge/skills/plugin87/full-stack-design-skills/anti-ai-design-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 186 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,457 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 $0.00186 $0.02457
Opus 5.5 $0.00074 $0.00983
Sonnet 5.5 $0.00037 $0.00491
Haiku 4.5 $0.00019 $0.00246

Measured 2mo ago against content hash f4bc43d9eea5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

anti-ai-design-patterns 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 2mo 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/anti-ai-design-patterns/SKILL.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anti-AI Design Patterns

A field guide to the visual tells that mark an interface as machine-generated, and the intentional choices that replace them. The goal is not a different template — it is design that reads as deliberate: chosen neutrals, a real type system, asymmetry with reason, and iconography that belongs to one family.

Core principle: intentional beats default

An AI tell is almost never a single ugly element. It is the absence of a decision — the palette that was inherited instead of chosen, the border that decorates instead of encodes, the emoji dropped in because a real icon was more work. Every rule below reduces to one question:

Did a human decide this, or did it fall out of a default?

If you cannot state why a color, radius, border, or glyph is there, it is probably a tell.


1. The border tell — single-side accent rails

The single most common AI slop signature: a rounded card with a colored stripe on one side (usually left) and neutral borders on the other three.

/* ❌ AI TELL — accent rail on a rounded card */
.card {
  border: 1px solid #e5e7eb;
  border-left: 4px solid #6366f1;   /* the giveaway */
  border-radius: 12px;
}

Why it reads as AI: the accent has no informational job — it is applied to every card regardless of state, so it decorates rather than encodes. A colored edge on a rounded corner also fights the geometry (the stripe clips awkwardly at the radius).

Fixes — pick based on intent:

/* ✅ A. If the color means nothing: drop it. Let type + spacing carry the card. */
.card { border: 1px solid var(--line); border-radius: 12px; }

/* ✅ B. If the color must encode STATE (error/warn/success): use a full token
   set — background tint + text + a same-color full border, not a lone rail. */
.card--critical {
  border: 1px solid var(--danger-line);
  background: var(--danger-bg);
  color: var(--danger-ink);
}

/* ✅ C. If you genuinely want an edge accent, make it a deliberate full-bleed
   top border on a SQUARE-topped card, or an inset marker — a decision, not a default. */
.stat { border-top: 3px solid var(--accent); border-radius: 0 0 10px 10px; }

Read the full file on GitHub · 190 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 190 lines · 0 tokens per session scan A f4bc43d9eea5

Subscribe to this mod's changes

anti-ai-design-patterns is a skill published in the GitHub repository plugin87/full-stack-design-skills (11 stars, last pushed 3mo ago), licensed MIT. It adds 186 tokens to every session and 2,457 once invoked, about $0.0007 per session on Opus 5.5. 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

anti-ai-design-patterns compared with skills from other repositories

anti-ai-design-patterns next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
anti-ai-design-patternsplugin87/full-stack-design-skillsSkill113mo agoMITA186Claude Code
webgl-holographic-foilnexu-io/open-designSkill106kyesterdayApache-2.0A41Claude Code, Codex
html-ppt-hermes-cyber-terminalnexu-io/open-designSkill106kyesterdayApache-2.0A53Claude Code, Codex
html-ppt-taste-brutalistnexu-io/open-designSkill106kyesterdayApache-2.0A78Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codexSkill34k3d agoMITA52Codex
glance-canonical-layoutsandroid/skillsSkill10kyesterdayApache-2.0A56Claude Code
accessibilitymicrosoft/hve-coreSkill1.6kyesterdayMITA47Claude Code