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 tsubotax/melta-ui --skill ban-patterngit clone --depth 1 https://github.com/tsubotax/melta-uiWrote 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/tsubotax/melta-ui/ban-pattern)<a href="https://agentmods.dev/skills/tsubotax/melta-ui/ban-pattern"><img src="https://agentmods.dev/badge/skills/tsubotax/melta-ui/ban-pattern/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/tsubotax/melta-ui/ban-pattern"><img src="https://agentmods.dev/badge/skills/tsubotax/melta-ui/ban-pattern.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 | $0.00067 | $0.02777 |
| Opus 5.5 | $0.00027 | $0.01111 |
| Sonnet 5.5 | $0.00013 | $0.00555 |
| Haiku 4.5 | $0.00007 | $0.00278 |
Grade A, and why
ban-pattern 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 1mo 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI生成UIに頻出する「それっぽい」装飾パターンを特定し、DS全体の禁止ルールとして登録する。
手順
Step 1: パターンを特定する
ユーザーの説明(テキスト or スクリーンショット)から、禁止対象のパターンを特定する。
以下を明確にする:
- 何が問題か: どの視覚要素がAI生成っぽいのか
- 該当する Tailwind クラス / CSS: 具体的な実装パターン(例:
border-l-4,bg-gradient-to-r) - 代替パターン: DS準拠の代わりの実装
不明点があれば AskUserQuestion で確認する。推測で進めない。
Step 2: 既存ルールと重複がないか確認する
以下を読み込む:
design/contracts/rules.jsonのrules[](SSOT。機械可読版。同じ pattern / 趣旨のルールが無いか)foundations/prohibited.mdの「AI生成パターンの排除」セクション(人間向けミラー)
既に同じ or 類似のルールが存在する場合は、ユーザーに報告して既存ルールの更新で対応するか確認する。
Step 3: 禁止ルールを登録する
SSOT は design/contracts/rules.json。CI / MCP check_rule / PostToolUse hook はすべて
rules.json を参照する。ここに機械可読ルールを足して初めて「ban → 即 enforcement」が成立する。
prohibited.md は人間向けの解説ミラーであり、enforcement の実体ではない。順序厳守:
3-1. design/contracts/rules.json — 機械可読ルールを追加(最優先)
rules[] 配列にルールオブジェクトを 1 件追加する。スキーマは design/schemas/rule.schema.json。
detector の選び方(これで自動検出されるか・人手参照に留まるかが決まる):
| detector | いつ使う | 必須フィールド | 例 |
|---|---|---|---|
tailwind-class |
単一の固定クラスを禁止 | pattern(クラス名) |
border-l-4, shadow-2xl |
tailwind-class-prefix |
前方一致で複数バリアントを一網打尽 | pattern(接頭辞)。任意値回避経路があれば prefixPatterns も |
bg-gradient- |
tailwind-class-segment |
クラスを - 分割したセグメント一致(色名等) |
matchPatterns(セグメント配列)、pattern: null |
purple/violet |
manual |
静的検出が原理的に不能(文脈判断) | pattern: null、contractLint: "skip" |
「色だけで状態を伝達」 |
フィールド規約:
id: 大文字スネーク(^[A-Z][A-Z0-9_]+$)。AI生成装飾はAI_NO_*、特定コンポーネントは<COMPONENT>_NO_*category:ai-pattern(AI装飾)/ または該当カテゴリ(colorspacingform等、schema の enum 参照)severity:error(明確なNG)/warn(文脈次第・段階導入)alternative: DS準拠の代替実装(必須・具体的に)contractLint:enforce(自動検出可・contract も検査)/warn/skip(manual・html-attr・文脈依存)
テンプレ(自動検出する典型の AI パターン):
{
"id": "AI_NO_GLASS_BLUR",
"category": "ai-pattern",
"severity": "error",
"description": "ガラスモーフィズム(backdrop-blur)はAI生成UIの典型tell。安っぽく散漫に見える",
"detector": "tailwind-class-prefix",
"pattern": "backdrop-blur",
"alternative": "不透明な bg-white / bg-slate-50 + border border-slate-200 で面を作る",
"contractLint": "enforce"
}
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.
- 1mo ago Changed · -4 lines 101f44113ae1
- 1mo ago First seen · 170 lines · 67 tokens per session scan A 33835efa034c
ban-pattern is a skill published in the GitHub repository tsubotax/melta-ui (202 stars, last pushed 12d ago), licensed MIT. It adds 67 tokens to every session and 2,777 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
reimagine-it-lock
Design DNA capture — extracts palette, type stack, motifs, motion, and 3D signatures from a shipped HTML file and saves them as a reusable reference pack. Use when the user says /reimagine-it lock, "lock this design", "save design DNA", "capture this look", or wants to reuse a shipped design on a different target.…
ui-ux-design-pro
Senior-level UI/UX design expert for building data-driven, premium production interfaces. Use when you need to: 1. Design complex applications (dashboards, SaaS, AI tools) from scratch 2. Generate comprehensive design systems (tokens, palettes, typography) 3. Audit existing UI for quality, accessibility, and "craft"…
generate-figma-screen
Kod veya açıklamadan Figma'da tam ekran/sayfa oluşturur. Yayınlanmış design system bileşenlerini arayıp instance olarak yerleştirir; hardcode değer yerine DS token'larını kullanır. "Figma'da ekran oluştur", "kodu Figma'ya çevir", "landing page çiz", "ekran tasarla", "generate screen", "UI'ı Figma'ya aktar"…
apple-design
Cross-platform UI/UX design reviewer grounded in Apple's Human Interface Guidelines (123 pages pulled from developer.apple.com, including 57 component pages) plus a design-craft lens for distinctive, non-templated work. Use it to audit, review, critique, or improve any mobile app (iOS, Flutter, React Native) or…
fmcp-intent-router
F-MCP ile ilgili herhangi bir kullanıcı talebinin ilk giriş noktası. Kullanıcının niyetini analiz eder, hangi hedef SKILL'in çalıştırılacağına karar verir, o SKILL için gereken eksik input'ları tek turda toplar, özet+onay alır ve ondan sonra hedef SKILL'i çalıştırır. "figma", "ekran oluştur", "tasarım yap", "component…
figma-a11y-audit
Figma ekranını erişilebilirlik açısından denetler. Renk kontrastı (WCAG AA/AAA), minimum dokunma hedefi, fokus sırası, metin boyutu ve platform-bazlı ekran okuyucu önerileri (VoiceOver, TalkBack, ARIA) üretir. "a11y audit", "erişilebilirlik kontrol", "kontrast kontrol", "accessibility check", "ekran okuyucu spec"…