ios-debugger-agent — Claude skill: build and debug iOS apps
A Claude skill that builds and launches your iOS app on a simulator through XcodeBuildMCP, then lets the agent poke at the UI and read logs.
npx skills add openai/plugins --skill ios-debugger-agent -a codexWhat ios-debugger-agent does
The skill lays out a workflow for driving the simulator with XcodeBuildMCP tools. First the agent looks for a booted simulator via mcp__XcodeBuildMCP__list_sims and picks the one in state Booted. If none are booted, the skill says to ask you rather than boot one on its own.
Session defaults come next: projectPath or workspacePath, the app scheme, and simulatorId. Build and run go through mcp__XcodeBuildMCP__build_run_sim. After a successful build the agent confirms the app actually launched with describe_ui or screenshot. If the build fails, the skill suggests retrying with preferXcodebuild: true or handing the problem back to you.
UI work uses tap, type_text, gesture and screenshot. Logs are captured with start_sim_log_cap and stop_sim_log_cap against the app bundle id. You need XcodeBuildMCP installed and a booted simulator. Worth installing if you run iOS builds from Claude and want the agent to verify the result in the simulator instead of just compiling.
What it helps with
- build and run the project scheme on a booted simulator
- check what is actually on screen with a screenshot or describe_ui
- tap an element by id or label instead of raw coordinates
- capture app logs and pull out the lines that matter
- figure out why the wrong app launched after a build
Example prompts for the agent
- Build and run the current scheme on the booted simulator
- Describe the running app's UI and tap the login button
- Start log capture and show me what crashes on launch
How to install ios-debugger-agent
1Skills CLI (Vercel)
npx skills add openai/plugins --skill ios-debugger-agent -a codex2Manually: put the files in place
.agents/skills/ios-debugger-agent/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add openai/plugins --skill ios-debugger-agent -a claude-code2Manually: put the files in place
~/.claude/skills/ios-debugger-agent/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/ios-debugger-agent/
Manually: put the files in place
.cursor/skills/ios-debugger-agent/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install openai/plugins ios-debugger-agent2Manually: put the files in place
.github/skills/ios-debugger-agent/SKILL.mdPlatform CLI
gemini skills install https://github.com/openai/plugins --path plugins/build-ios-apps/skills/ios-debugger-agentManually: put the files in place
.devin/skills/ios-debugger-agent/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set201
The whole set →Similar
Questions about ios-debugger-agent
How do I install ios-debugger-agent in Claude?
Run npx skills add openai/plugins --skill ios-debugger-agent -a codex. The skill file lands at .agents/skills/ios-debugger-agent/SKILL.md.
What does ios-debugger-agent do?
It gives the agent a sequence for building and launching an iOS app on a simulator with XcodeBuildMCP, plus UI interaction and log capture.
What do I need for the skill to work?
XcodeBuildMCP and a booted simulator. If nothing is booted, the skill asks you to start one yourself.
Source text
SKILL.md · MIT
--- name: ios-debugger-agent description: Build, run, and debug iOS apps on Simulator with XcodeBuildMCP. Use when launching an app, inspecting simulator UI or logs, or diagnosing runtime behavior. --- # iOS Debugger Agent ## Overview Use XcodeBuildMCP to build and run the current project scheme on a booted iOS simulator, interact with the UI, and capture logs. Prefer the MCP tools for simulator control, logs, and view inspection. ## Core Workflow Follow this sequence unless the user asks for a narrower action. ### 1) Discover the booted simulator - Call `mcp__XcodeBuildMCP__list_sims` and select the simulator with state `Booted`. - If none are booted, ask the user to boot one (do not boot automatically unless asked). ### 2) Set session defaults - Call `mcp__XcodeBuildMCP__session-set-defaults` with: - `projectPath` or `workspacePath` (whichever the repo uses) - `scheme` for the current app - `simulatorId` from the booted device - Optional: `configuration: "Debug"`, `useLatestOS: true` ### 3) Build + run (when requested) - Call `mcp__XcodeBuildMCP__build_run_sim`. - **If the build fails**, check the error output and retry (optionally with `preferXcodebuild: true`) or escalate to the user before attempting any UI interaction. - **After a successful build**, verify the app launched by calling `mcp__XcodeBuildMCP__describe_ui` or `mcp__XcodeBuildMCP__screenshot` before proceeding to UI interaction. - If the app is already built and only launch is requested, use `mcp__XcodeBuildMCP__launch_app_sim`. - If bundle id is unknown: 1) `mcp__XcodeBuildMCP__get_sim_app_path` 2) `mcp__XcodeBuildMCP__get_app_bundle_id` ## UI Interaction & Debugging Use these when asked to inspect or interact with the running app. - **Describe UI**: `mcp__XcodeBuildMCP__describe_ui` before tapping or swiping. - **Tap**: `mcp__XcodeBuildMCP__tap` (prefer `id` or `label`; use coordinates only if needed). - **Type**: `mcp__XcodeBuildMCP__type_text` after focusing a field. - **Gestures**: `mcp__XcodeBuildMCP__gesture` for common scrolls and edge swipes. - **Screenshot**: `mcp__XcodeBuildMCP__screenshot` for visual confirmation. ## Logs & Console Output - Start logs: `mcp__XcodeBuildMCP__start_sim_log_cap` with the app bundle id. - Stop logs: `mcp__XcodeBuildMCP__stop_sim_log_cap` and summarize important lines. - For console output, set `captureConsole: true` and relaunch if required. ## Troubleshooting - If build fails, ask whether to retry with `preferXcodebuild: true`. - If the wrong app launches, confirm the scheme and bundle id. - If UI elements are not hittable, re-run `describe_ui` after layout changes.
© OpenAI · MIT · openai/plugins