ios-simulator-skill

An IOS Simulator Skill for Agents. Use it to optimise their ability to build, run and interact with your apps, and to proxy xcodebuild to save token waste. Work

What is ios-simulator-skill?

An IOS Simulator Skill for Agents. Use it to optimise their ability to build, run and interact with your apps, and to proxy xcodebuild to save token waste. Works with Claude, Codex, etc

Overview of ios-simulator-skill

What it is

An iOS Simulator Skill for Agents. It is a production-ready set of 29 scripts for building, testing, and automating iOS apps. The skill optimizes the ability of agents to build, run, and interact with apps, and proxies xcodebuild to save token and context wastage.

Key features

  • Wraps xcodebuild with progressive error disclosure that returns a one-line summary with an xcresult ID and allows drilling into errors, warnings, or logs on demand.
  • Uses iOS accessibility APIs (via xcrun simctl and idb) for semantic UI navigation instead of fragile pixel coordinates.
  • Automatically resizes and compresses screenshots to minimize token cost; default output across all scripts is 3–5 lines, a stated 96% reduction vs raw tool output.
  • Provides scripts for appearance changes (dark mode, dynamic type, locale, region), GPS simulation, and app launching/deep linking.
  • Includes accessibility auditing (WCAG compliance), visual diffing between screenshots, and automated test documentation with screenshots.
  • All scripts support --help and --json flags.

Use cases

Automated building and testing of Xcode projects with token-efficient output for AI agents. Semantic navigation and interaction with iOS Simulator elements (tapping, swiping, typing) based on meaning rather than coordinates. Visual verification and debugging using screenshots, accessibility audits, and state capture. Simulating device conditions such as location, dark mode, or text size during testing.

Getting started

Via the plugin marketplace in Claude Code: /plugin marketplace add conorluddy/ios-simulator-skill /plugin install ios-simulator-skill@conorluddy Manual installation from a release: bash curl -L https://github.com/conorluddy/ios-simulator-skill/releases/latest/download/ios-simulator-skill.zip -o skill.zip unzip skill.zip -d ~/.claude/skills/ios-simulator-skill Prerequisites: macOS 15 (Sequoia)+, Xcode 26+ with Command Line Tools, Python 3.12+, idb (CLI + companion) 1.5.1+, and optionally Pillow for visual diffs. Verify with bash scripts/sim_health_check.sh.

License and pricing

License: MIT. Pricing: open source.

這是什麼

這是一套針對代理人設計的 iOS Simulator 技能。它包含 29 個正式等級的腳本,用於建置、測試以及自動化 iOS 應用程式。此技能可最佳化代理人建置、執行及與應用程式互動的能力,並代理 xcodebuild 以節省 token 及脈絡的浪費。

主要功能

  • 包裝 xcodebuild,提供漸進式錯誤揭露,回傳一行摘要(含 xcresult ID),並可按需查看錯誤、警告或記錄。
  • 透過 iOS 無障礙功能 API(經由 xcrun simctl 和 idb)進行語義式 UI 導航,取代脆弱的像素座標。
  • 自動調整螢幕截圖尺寸與壓縮以降低 token 成本;所有腳本的預設輸出為 3–5 行,宣稱比原始工具輸出減少 96%。
  • 提供外觀切換(深色模式、動態字型、語系、地區)、GPS 模擬以及應用程式啟動/深層連結等腳本。
  • 包含無障礙稽核(WCAG 遵循度)、螢幕截圖視覺差異比對,以及附截圖的自動化測試文件記錄。
  • 所有腳本皆支援 --help 與 --json 標記。

使用情境

以 token 高效率的方式自動化建置與測試 Xcode 專案,供 AI 代理人使用。根據意義而非座標對 iOS Simulator 元件進行語義式導航與互動(點擊、滑動、輸入文字)。使用螢幕截圖、無障礙稽核與狀態快照進行視覺驗證與除錯。在測試期間模擬裝置條件,例如位置、深色模式或文字大小。

快速開始

透過 Claude Code 的外掛市場安裝: /plugin marketplace add conorluddy/ios-simulator-skill /plugin install ios-simulator-skill@conorluddy 從發行版本手動安裝: bash curl -L https://github.com/conorluddy/ios-simulator-skill/releases/latest/download/ios-simulator-skill.zip -o skill.zip unzip skill.zip -d ~/.claude/skills/ios-simulator-skill 必要條件:macOS 15 (Sequoia) 以上、Xcode 26 以上(含 Command Line Tools)、Python 3.12 以上、idb(CLI + companion)1.5.1 以上,以及選用的 Pillow(用於視覺差異比對)。可使用 bash scripts/sim_health_check.sh 進行驗證。

授權與價格

授權:MIT。價格:開放原始碼。

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/conorluddyios-simulator-skill.svg)](https://yunodb.com/tools/conorluddyios-simulator-skill?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/conorluddyios-simulator-skill?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/conorluddyios-simulator-skill.svg" alt="Featured on YunoDB" height="20"></a>