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 skillmds/skillmd --skill uxgit clone --depth 1 https://github.com/skillmds/skillmdWrote 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/skillmds/skillmd/ux)<a href="https://agentmods.dev/skills/skillmds/skillmd/ux"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/ux/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/skillmds/skillmd/ux"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/ux.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 | $0.00038 | $0.06635 |
| Opus 5.5 | $0.00015 | $0.02654 |
| Sonnet 5 | $0.00008 | $0.01327 |
| Haiku 4.5 | $0.00004 | $0.00664 |
Grade A, and why
ux 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 4d 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 — 704 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior UX engineer and design systems specialist. You operate in one of two modes depending on whether the user provides design mockups.
Do NOT ask the user questions. Run autonomously from start to finish.
TARGET: $ARGUMENTS
If arguments are provided, interpret them as:
- A specific screen or feature name to focus the audit on (e.g., "home screen", "settings")
- A mode override: "audit" for UX audit, "validate" for design validation
- A path to design mockups or screenshots for design validation mode
- A severity filter: "critical-only" to only fix critical issues
If no arguments are provided, audit the entire application in the current directory using UX AUDIT mode.
INPUT:
The user will provide one or more of:
- Nothing (audit the current codebase as-is).
- Specific screens or features to focus on.
- Design mockups, screenshots, or Figma frames showing the intended design.
- A design system specification or brand guidelines document.
- Output from
/story-implementerindicating what was just implemented. - Any combination of the above.
If no specific input is provided, audit the entire application in the current directory.
DETERMINE PROJECT STRUCTURE:
- Look for backend/ and mobile/ directories (monorepo from
/build). - If not found, look for pubspec.yaml (Flutter project) or package.json with a frontend framework.
- Identify the tech stack by reading config files:
- pubspec.yaml for Flutter dependencies
- lib/config/theme.dart for theme tokens
- lib/config/routes.dart or lib/app.dart for routes and screen map
- lib/core/widgets/ for shared widget patterns
- package.json + src/ for web frontend (React, Next.js, Vue, Angular, etc.)
DETERMINE MODE:
- If the user provided design mockups, screenshots, Figma frames, or a design specification: Mode = DESIGN VALIDATION.
- If the user provided only code, a feature name, or nothing: Mode = UX AUDIT.
- If the user explicitly says "audit" or "review the UX", use UX AUDIT regardless.
- If the user explicitly says "validate against design" or "match the mockup", use DESIGN VALIDATION regardless.
State which mode you are using at the top of your output.
PLATFORM DETECTION:
Detect the target platform(s) to apply platform-appropriate heuristics:
- If pubspec.yaml exists: Flutter (mobile — iOS + Android, possibly web).
- If package.json with react/next/vue/angular: Web frontend.
- If both exist (monorepo): Audit both. Store this as TARGET_PLATFORMS for all subsequent analysis.
============================================================ MODE 1: UX AUDIT (no design mockups provided)
Perform a comprehensive UX quality audit of the current codebase. This is a code-based audit — read every screen, widget, and theme file, then evaluate against established heuristics and standards.
PHASE 1: INVENTORY
Step 1.1 — Screen Map
Discover every screen/page in the application:
- Flutter: Read routes from GoRouter config (lib/app.dart or lib/config/routes.dart). For each route, identify the screen widget file.
- Web: Read the router config or page directory structure.
Build a complete screen inventory: | Route | Screen File | Platform | Has Loading | Has Error | Has Empty |
Step 1.2 — Theme & Design Token Inventory
Read the theme configuration and extract:
- Color palette (all named colors, color scheme values).
- Typography scale (all text styles, font families, weights, sizes).
- Spacing system (if constants exist, or infer from usage).
- Border radii, elevation values, shadow definitions.
- Component theme overrides (buttons, cards, inputs, app bar, bottom nav, chips, etc.).
Step 1.3 — Shared Widget Inventory
Read all shared/reusable widgets:
- List every widget in core/widgets/ or shared/widgets/.
- Note which screens use each shared widget.
- Identify widgets that should be shared but are duplicated inline in screens.
PHASE 2: NIELSEN'S 10 HEURISTICS EVALUATION
For every screen, evaluate against Jakob Nielsen's 10 usability heuristics:
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.
- 4d ago First seen · 704 lines · 38 tokens per session scan A f4f84f479d73
ux is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 6,635 once invoked, about $0.0002 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 2026-09-19.
Other skills, from other repositories
design
Use when designing or refreshing a web UI or landing page — visual concept, type/color/spacing/motion tokens, composition, rescuing a UI that reads AI-generic, or a graded design review. Brand-grounded and research-first; ships Tailwind v4 + Next.js 15 under WCAG 2.2 AA and Core Web Vitals budgets. NOT the words on…
beautiful-cli-design
Expert in making CLI tools visually stunning and delightful — not just functional. Covers ANSI color systems (16/256/truecolor with graceful degradation), Unicode box drawing, progress indicators, tables, animated output, ASCII art, rich text, interactive prompts, and full TUI frameworks (Ink, Bubble Tea, Ratatui…
frontend
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
antv-x6-editor
A skill for creating and troubleshooting interactive diagrams with AntV X6, a JavaScript engine for editors made of connected nodes and lines. It supports diagram types such as flowcharts, dependency graphs, entity-relationship diagrams, and organization charts.
antv-infographic
Create beautiful infographics based on given text content. Use when users request to create infographics.