No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by conorluddy · MCP Server · ★ 1.2k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ios-simulator-skill safe to install? View the security audit →
iOS Simulator Skill for Claude Code Production-ready automation for iOS app testing and building. 21 scripts optimized for both human developers and AI agents. This is basically a Skill version of my XCode MCP: https://github.com/conorluddy/xc-mcp [!WARNING] You want to take the directory from this repo and drop it into your skills directory - not this entire repo. I'll update this soon with an easier approach. Feel free to fork this and get Claude to adjust it to your specific needs. MCPs load a lot of tokens into the context window when they're active, but also seem to work really well. Skills don't load in any context. I'll make a plugin next and try to find the balance... Updated: The Plugin version lets you easily disable MCPs for different tool groups. Optimise your context window by only enabling the tools you're actively using, such as xcodebuild: https://github.com/conorluddy/xclaude-plugin What It Does Instead of pixel-based navigation that breaks when UI changes: Uses semantic navigation on accessibility APIs to interact with elements by their meaning, not coordinates. Works across different screen sizes and survives UI redesigns.
| Stars | 1,249 |
| Forks | 91 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 76.7368235025194/100 |
| Open Issues | 20 |
| Last Updated | 2026-09-13 |
| Created | 2025-10-17 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~16k |
These tools work well together with ios-simulator-skill for enhanced workflows:
Looking for a ios-simulator-skill alternative? If you're comparing ios-simulator-skill with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies
A practical Claude Code guide with clear mental models and copy-paste examples — setup, prompt engineering, sl
Skybridge is a full-stack TypeScript framework for MCP Apps and ChatGPT Apps. Type-safe. React-powered. Platfo
Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks from beginner to power user!
A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Cl
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Mode
Explore other popular mcp server tools:
ios-simulator-skill is An IOS Simulator Skill for ClaudeCode. Use it to optimise Claude's ability to build, run and interact with your apps, and to proxy xcodebuild to save token and context wastage.. It is categorized as a MCP Server with 1.2k GitHub stars.
ios-simulator-skill is primarily written in Python. It covers topics such as agent, agentic-ai, ai-agents.
You can find installation instructions and usage details in the ios-simulator-skill GitHub repository at github.com/conorluddy/ios-simulator-skill. The project has 1.2k stars and 91 forks, indicating an active community.
ios-simulator-skill is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to ios-simulator-skill on Agent Skills Hub include linkedin-mcp-server, Claude-Code-Everything-You-Need-to-Know, skybridge. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: