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 LuuOW/meridian-mcp --skill ux-ui-expertgit clone --depth 1 https://github.com/LuuOW/meridian-mcpWrote 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/luuow/meridian-mcp/ux-ui-expert)<a href="https://agentmods.dev/skills/luuow/meridian-mcp/ux-ui-expert"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/ux-ui-expert/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/luuow/meridian-mcp/ux-ui-expert"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/ux-ui-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00033 | $0.01521 |
| Opus 5.5 | $0.00013 | $0.00608 |
| Sonnet 5.5 | $0.00007 | $0.00304 |
| Haiku 4.5 | $0.00003 | $0.00152 |
Grade A, and why
ux/ui expert 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.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ux/ui expert
Frontend + UX/UI Skill Matrix — applicable to Next.js App Router, Astro, and React projects.
1) Framework Context
Next.js App Router
- Server Components by default — no hooks, no browser APIs, fetch data directly
'use client'only at interaction boundaries (forms, polling, real-time, toggles)- Layouts stay server-side; push client components as far down the tree as possible
- Use
min-h-svhon main shells (handles mobile browser dynamic toolbars)
Astro
- Islands architecture: static shell + selectively hydrated React islands
client:load→ immediate,client:idle→ non-critical,client:visible→ below fold- Zero JS by default — every hydrated component must justify its cost
- Layout, nav, header: pure
.astro— no'use client'equivalent needed
Shared Principles
- Composition over configuration for UI primitives
- Token-driven design (CSS variables) — never hardcode colors or spacing values
- Mobile-first: smallest breakpoint first, larger overrides progressively
- Semantic HTML first — ARIA only where semantic HTML is insufficient
2) Design System Engineering
- Build reusable primitives: Button, Card, Badge, Table, EmptyState, Skeleton
- Token system: color, spacing, typography, radius, shadow, motion
- Theming (light/dark) via
.darkclass on<html>+ CSS variable overrides in.dark {} - Never hardcode colors — always
var(--token-name) box-sizing: border-boxglobally — predictable sizing- Interaction: meaningful transitions (120–320ms), feedback without noise
prefers-reduced-motion: always disable/minimize animations when set
3) UX Quality Bar
- Define user goal, UX constraints, success criteria before implementation
- Every interactive section must have all states: loading, empty, success, failure, validation
- Conversion-oriented hierarchy: primary action visible, above fold, high contrast
- Mobile ergonomics: tap targets ≥44px, readable density, minimal-friction forms
- Error prevention first; clear recovery pathways second
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.
- 2mo ago First seen · 158 lines · 33 tokens per session scan A 71692035fbd2
ux/ui expert is a skill published in the GitHub repository LuuOW/meridian-mcp (0 stars, last pushed 27d ago), licensed MIT. It adds 33 tokens to every session and 1,521 once invoked, about $0.0001 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 2026-09-03.
ux/ui expert compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ux/ui expertLuuOW/meridian-mcp | Skill | 0 | 27d ago | MIT | A | 33 | Claude Code, Codex |
| anti-ui-slopsickn33/agentic-awesome-skills | Skill | 49k | 2d ago | MIT | A | 39 | Claude Code |
| designericrisco/rsc-harness | Skill | 555 | 5d ago | MIT | A | 78 | Claude Code, Codex |
| redesign-screenmobbin/skills | Skill | 66 | 7d ago | MIT | A | 146 | Claude Code |
| plain-writingmobbin/skills | Skill | 66 | 7d ago | MIT | A | 85 | Claude Code |
| impeccableoyi77/1ai-skills | Skill | 17 | yesterday | MIT | A | 83 | Claude Code |
| searchmobbin/skills | Skill | 66 | 7d ago | MIT | A | 62 | Claude Code |