Skip to content

Xcode Simulator Testing

Build, run and test an iOS app in a simulator and report evidence-backed PASS/FAIL results.

Stars
25,850
Licence
MIT
Files
4 files

What it does

Once installed, the agent can build an iOS app in Xcode's simulator, launch it, walk through the screens and flows you approve, and capture screenshots, console logs and human-verification notes. It ends with a structured report giving an overall PASS, FAIL or PARTIAL and a status for each tested area. It is designed to test and report only; any diagnosis or fix is handed to a separate debugging skill and it does not commit, push or open pull requests.

Great for

  • iOS developers who want simulator evidence attached to a change before handing it off
  • Teams that need a consistent test report format across iOS builds
  • Developers already using XcodeBuildMCP in their agent setup

Skip it if

  • Non-iOS projects, since it is specific to Xcode and the iOS simulator
  • Anyone without a Mac with Xcode installed, because simulator builds cannot run elsewhere
  • Testing apps against production accounts or real user data, since the skill drives the app and captures logs that may contain sensitive information

Try asking

  • “Build the current scheme in the simulator and test the onboarding flow, then give me a PASS/FAIL report with screenshots”
  • “Run the iOS app on an iPhone simulator and verify the settings screens before I hand this off”
  • “Test the checkout screens on the default scheme and list any console errors”
Step-by-step guide: how to use Xcode Simulator TestingInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 4 original files, the MIT licence and an attribution note.

    ce-test-xcode.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip ce-test-xcode.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip ce-test-xcode.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Name the scheme explicitly, or pass 'current' to use the default, so the agent builds the right target
  • Define the screens and flows in scope before running, since the skill keeps simulator interaction within what you specify
  • Expect some flows (such as SwiftUI inline links) to need a human to verify manually

What's inside

  • agents/openai.yaml
  • references/setup-and-build.md
  • references/test-and-report.md
  • SKILL.md

Redistributed unmodified from EveryInc/compound-engineering-plugin under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.