Agent skill

ux-review

Quellcode ansehen: nickcrew/claude-cortex

#124Globales Ranking · von 124 SkillsSafe

Installation

npx skills add nickcrew/claude-cortex --skill ux-review

76

Installationen

EU-hosted inference API

Power your AI agent skills with open-source models.

Drop-in OpenAI-compatible API. No data leaves Europe.

MiniMax

MiniMax M3

$0.50 / $1.90

per M tokens

Z.ai

GLM 5.3 Flash

$0.20 / $0.60

per M tokens

MoonshotAI

Kimi K3

$4.00 / $18.00

per M tokens

DeepSeek

DeepSeek V4.1 Flash

$0.40 / $1.42

per M tokens

UX Review

Comprehensive user experience review that coordinates usability, accessibility, and interaction design perspectives for thorough analysis of components, flows, or features.

When to Use This Skill

  • Reviewing new components or features before release
  • Evaluating existing flows for usability issues
  • PR reviews that touch UI/UX code
  • Design system component reviews
  • Onboarding flow or checkout flow optimization
  • Avoid using for purely visual/aesthetic reviews — use ui-design-aesthetics instead

Workflow

Step 1: Gather Context

Answer these questions before reviewing:

  1. What is the user trying to accomplish?
  2. What is this component's role in the larger flow?
  3. Who are the target users (personas, skill level)?
  4. What are the success criteria?

Step 2: Run Heuristic Scan (Nielsen's 10)

Evaluate the interface against each heuristic:

Heuristic Check
Visibility of system status Does the user always know what's happening?
Match with real world Does it use familiar language and concepts?
User control and freedom Can users undo, go back, escape?
Consistency and standards Does it follow platform conventions?
Error prevention Are mistakes prevented before they happen?
Recognition over recall Is information visible rather than memorized?
Flexibility and efficiency Are there shortcuts for expert users?
Aesthetic and minimalist design Is every element necessary?
Error recovery Are error messages helpful and actionable?
Help and documentation Is guidance available when needed?

Step 3: Multi-Perspective Analysis

Usability Perspective

  • User flow: Is the path to completion clear and efficient?
  • Information architecture: Is content organized logically?
  • Cognitive load: Is the interface overwhelming?
  • Mental models: Does it work like users expect?

Accessibility Perspective (WCAG 2.1 AA)

  • Keyboard navigation: Can everything be done without a mouse?
  • Screen reader: Is the experience equivalent for assistive tech users?
  • Color contrast: Do all text/UI elements meet 4.5:1 ratio?
  • Focus management: Is focus order logical, visible, and never trapped?
<!-- Example: Accessible button with proper ARIA -->
<button aria-label="Close dialog" aria-describedby="close-hint">
  <svg aria-hidden="true"><!-- icon --></svg>
</button>
<span id="close-hint" class="sr-only">Press Escape to close</span>

Interaction Design Perspective

  • State coverage: Are all states handled (loading, empty, error, success)?
  • Feedback: Does the user know their action worked?
  • Transitions: Are animations purposeful and under 300ms?
  • Progressive disclosure: Is complexity revealed appropriately?

Step 4: Prioritize Findings

Categorize every finding:

Priority Criteria Action
Critical Blocks usability or fails WCAG AA Must fix before release
High Significantly degrades experience Fix in current sprint
Enhancement Improves delight and efficiency Backlog for next iteration
Future Long-term improvements Track in roadmap

Step 5: Produce Review Report

## UX Review: [Component/Flow Name]

### Summary
[2-3 sentence executive summary]

### Critical Issues
- [ ] Issue 1: [Description, impact, WCAG criterion if applicable]
- [ ] Issue 2: [Description, impact]

### Recommendations by Category

#### Usability
| Finding | Impact | Recommendation |
|---------|--------|----------------|
| [Issue] | High/Med/Low | [Fix] |

#### Accessibility
| Finding | WCAG Criterion | Recommendation |
|---------|----------------|----------------|
| [Issue] | [2.x.x Level] | [Fix] |

#### Interaction Design
| Finding | Impact | Recommendation |
|---------|--------|----------------|
| [Issue] | High/Med/Low | [Fix] |

### Next Steps
1. Create issues for critical findings
2. Add accessibility requirements to acceptance criteria
3. Schedule follow-up review after fixes

Focus Area Deep Dives

Use --focus to narrow the review scope:

  • --focus=ux: User flow mapping, task efficiency, error recovery, learnability
  • --focus=a11y: WCAG 2.1 AA audit, keyboard nav, screen reader, contrast, focus management
  • --focus=interaction: State coverage, feedback timing, micro-interactions, animation review

Best Practices

  • Test with real content — Lorem ipsum hides information architecture problems
  • Check all states — Empty, loading, error, success, and edge-case states
  • Verify keyboard flow — Tab through the entire component without a mouse
  • Use browser dev tools — Lighthouse accessibility audit catches low-hanging fruit
  • Prioritize ruthlessly — A focused list of critical fixes beats a wall of suggestions

So verwenden Sie diesen Skill

  1. 1

    Install ux-review by running npx skills add nickcrew/claude-cortex --skill ux-review in your project directory. Führen Sie den obigen Installationsbefehl in Ihrem Projektverzeichnis aus. Die Skill-Datei wird von GitHub heruntergeladen und in Ihrem Projekt platziert.

  2. 2

    Keine Konfiguration erforderlich. Ihr KI-Agent (Claude Code, Cursor, Windsurf usw.) erkennt installierte Skills automatisch und nutzt sie als Kontext bei der Code-Generierung.

  3. 3

    Der Skill verbessert das Verständnis Ihres Agenten für ux-review, und hilft ihm, etablierte Muster zu befolgen, häufige Fehler zu vermeiden und produktionsreifen Code zu erzeugen.

Was Sie erhalten

Skills sind Klartext-Anweisungsdateien — kein ausführbarer Code. Sie kodieren Expertenwissen über Frameworks, Sprachen oder Tools, das Ihr KI-Agent liest, um seine Ausgabe zu verbessern. Das bedeutet null Laufzeit-Overhead, keine Abhängigkeitskonflikte und volle Transparenz: Sie können jede Anweisung vor der Installation lesen und prüfen.

Kompatibilität

Dieser Skill funktioniert mit jedem KI-Coding-Agenten, der das skills.sh-Format unterstützt, einschließlich Claude Code (Anthropic), Cursor, Windsurf, Cline, Aider und anderen Tools, die projektbezogene Kontextdateien lesen. Skills sind auf Transportebene framework-agnostisch — der Inhalt bestimmt, für welche Sprache oder welches Framework er gilt.

Data sourced from the skills.sh registry and GitHub. Install counts and security audits are updated regularly.