ios-ui-audit 是做什麼的？
來自 DanhDue/ai-agent-tools 的代理技能 'ios-ui-audit'。
這是一個 iOS UI 審查技能，用於檢查和改進 iOS 應用程式的使用者介面。
DanhDue/ios-ui-audit 是一個專為 AI 代理（如 Claude Code、Cursor、Codex 等）設計的技能，用於執行 iOS 使用者介面的自動化審查。它能協助開發者快速識別 UI 元件的一致性問題、佈局偏差、色彩對比度不足以及可訪問性缺陷。該技能支援多種開發平台，並透過分析專案中的程式碼和資源檔案來產生詳細的審查報告。其運作方式基於預定義的 UI 最佳實踐規則集，能夠自動掃描 SwiftUI 或 UIKit 的實作，並提供具體的改善建議，從而提升 iOS 應用程式的整體品質與使用者體驗。
npx skills add https://github.com/DanhDue/ai-agent-tools/tree/main/skills/ios-ui-audit來自 DanhDue/ai-agent-tools 的代理技能 'ios-ui-audit'。
This repo contains 20 individual skills — each has its own dedicated page.
Agent skill 'android-api-integration' from DanhDue/ai-agent-tools.
Agent skill 'android-ui-audit' from DanhDue/ai-agent-tools.
Agent skill 'api_integration' from DanhDue/ai-agent-tools.
Agent skill 'architecture-audit' from DanhDue/ai-agent-tools.
Agent skill 'brainstorming' from DanhDue/ai-agent-tools.
Agent skill 'build_fix' from DanhDue/ai-agent-tools.
Agent skill 'check_secure_files' from DanhDue/ai-agent-tools.
Agent skill 'code-health-audit' from DanhDue/ai-agent-tools.
Agent skill 'copy_secure_configurations' from DanhDue/ai-agent-tools.
Agent skill 'create_new_feature' from DanhDue/ai-agent-tools.
Agent skill 'decision-records' from DanhDue/ai-agent-tools.
Agent skill 'dev-brainstorming' from DanhDue/ai-agent-tools.
Agent skill 'dev-designer' from DanhDue/ai-agent-tools.
Agent skill 'dev-implementation' from DanhDue/ai-agent-tools.
Agent skill 'dev-lifecycle' from DanhDue/ai-agent-tools.
Agent skill 'dispatching-parallel-agents' from DanhDue/ai-agent-tools.
Agent skill 'doc-brainstorming' from DanhDue/ai-agent-tools.
Agent skill 'doc-designer' from DanhDue/ai-agent-tools.
Agent skill 'doc-implementation' from DanhDue/ai-agent-tools.
Agent skill 'doc-lifecycle' from DanhDue/ai-agent-tools.
ElevenLabs text-to-speech with mac-style say UX.
Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.
Capture and automate macOS UI with the Peekaboo CLI.
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".