agentsclimarketplace

Ios simulator debugger

Skill Xopoko/build-swift-apps/skills/ios-simulator-debugger

Swift-focused AI agent skills for iOS and macOS: build, debug, simulator, SwiftUI, Xcode, App Store workflows. Part of Plug'n Skills.

Install
npx -y skills add Xopoko/build-swift-apps --skill ios-simulator-debugger

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Build, run, launch, inspect, interact with, and debug iOS simulator apps using XcodeBuildMCP tools, UI descriptions, screenshots, and log capture. Prefer ios-simulator-browser for user-facing browser mirrors, visible simulator proof, or SwiftUI preview viewing.

SKILL.md

2.3 KB, 530 tokens by cl100k_base, as published. Nobody here has run it

iOS Simulator Debugger

Use XcodeBuildMCP for simulator control, build/run, UI inspection, screenshots, interaction, and logs.

If the user should see or interact with the running app, prefer ios-simulator-browser after this skill has selected or launched the Simulator. Keep this skill focused on build/run, logs, bundle IDs, UI tree inspection, and headless simulator automation.

Workflow

  1. Discover a booted simulator with mcp__XcodeBuildMCP__list_sims. If none is booted, ask the user to boot one unless they asked you to boot it.
  2. Set defaults with mcp__XcodeBuildMCP__session-set-defaults: projectPath or workspacePath, scheme, simulatorId, optional configuration: "Debug" and useLatestOS: true.
  3. Build/run with mcp__XcodeBuildMCP__build_run_sim when requested. If the build fails, inspect output and retry only when justified, optionally with preferXcodebuild: true.
  4. After a successful run, verify launch with mcp__XcodeBuildMCP__describe_ui or mcp__XcodeBuildMCP__screenshot before UI interaction.
  5. If only launch is requested, use mcp__XcodeBuildMCP__launch_app_sim. If bundle id is unknown, call mcp__XcodeBuildMCP__get_sim_app_path then mcp__XcodeBuildMCP__get_app_bundle_id.

Interaction

  • Describe before acting: mcp__XcodeBuildMCP__describe_ui.
  • Tap by id or label first; coordinates only when needed.
  • Type after focusing a field with mcp__XcodeBuildMCP__type_text.
  • Use mcp__XcodeBuildMCP__gesture for scrolls and edge swipes.
  • Capture visual proof with mcp__XcodeBuildMCP__screenshot.

Logs

Start capture with mcp__XcodeBuildMCP__start_sim_log_cap and the app bundle id. Stop with mcp__XcodeBuildMCP__stop_sim_log_cap and summarize important lines. For console output, set captureConsole: true and relaunch if required.

Troubleshooting

Wrong app means verify scheme/bundle id. Non-hittable elements require fresh describe_ui after layout changes. Do not keep interacting after an unhandled build or launch failure.

Gives 0 of the 12 instructions most debug triage skills give in 530 tokens

Counted across 839 of the 1,149 authors here whose files we hold, read 2026-08-06

  • investigate root cause before proposing any fixin 102 of 839, across 65 files
  • read error messages completelyin 90 of 839, across 48 files
  • create a failing test case before fixingin 84 of 839, across 44 files
  • reproduce the issue consistentlyin 82 of 839, across 40 files
  • change one variable at a timein 82 of 839, across 42 files
  • check recent changesin 74 of 839, across 35 files
  • write the regression test before fixingin 74 of 839, across 36 files
  • fix the root cause not the symptomin 60 of 839, across 43 files
  • implement a single fix at a timein 59 of 839, across 20 files
  • trace data flow backward to the sourcein 50 of 839, across 20 files
  • remove all debug instrumentationin 49 of 839, across 13 files
  • form a single hypothesisin 48 of 839, across 18 files

Said here and by no other author read

  • discover a booted simulator before running
  • set defaults before building or running
  • launch the app directly when only launch is requested
  • tap elements by id or label first
  • type text after focusing a field
  • capture screenshots for visual proof

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.