accessibility
FreeEnsure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
The English summary is being prepared. Showing the original description.
iOS development expert including SwiftUI, UIKit, and Apple frameworks
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
When reviewing or writing code, apply these guidelines:
When reviewing or writing code, apply these guidelines:
When reviewing or writing code, apply these guidelines:
@MainActor for UI updates — SwiftUI and UIKit views must be modified on the main thread; background thread UI updates cause runtime crashes or silent visual corruption.@State for data that is shared between views — @State is local to the view and does not propagate changes to siblings or parents; use @ObservedObject, @EnvironmentObject, or @StateObject for shared model data.[weak self] in closures that capture self — strong self capture in closures that are held by the captured object creates retain cycles and memory leaks.const constructors and mark SwiftUI views as struct — class-based SwiftUI views lose automatic diffing optimization; struct views enable efficient identity tracking.| Anti-Pattern | Why It Fails | Correct Approach |
|---|---|---|
| UI updates from background threads | UIKit/SwiftUI are not thread-safe; random crashes, visual corruption, or silent failure | Dispatch to main: DispatchQueue.main.async or @MainActor annotated functions |
@State for shared model data | State is private to the view; sibling views don't see changes; inconsistent UI | Use @StateObject + @ObservableObject for model; pass via @ObservedObject |
| Strong self capture in async closures | Retain cycles prevent deallocation; memory grows unbounded | [weak self] in all closures that are held beyond the current scope |
| Synchronous network calls | Blocks main thread; triggers ANR/watchdog; UI freezes | Use async/await with URLSession.data(for:) or Combine; always on background |
| Class-based SwiftUI views | Opt out of struct diffing optimization; slower rendering; lifecycle issues | Define all views as struct; only use class for ObservableObject models |
This expert skill consolidates 1 individual skills:
Before starting:
cat .claude/context/memory/learnings.md
After completing: Record any new patterns or exceptions discovered.
ASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
The English summary is being prepared. Showing the original description.
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
The English summary is being prepared. Showing the original description.
N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.
The English summary is being prepared. Showing the original description.
Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze
The English summary is being prepared. Showing the original description.
Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.
The English summary is being prepared. Showing the original description.
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
The English summary is being prepared. Showing the original description.