By hoangdh2001
AI-driven UI test automation for iOS, iPadOS, and macOS apps — runs on simulators and real targets via xcodebuildmcp and AXe CLI.
iOS UI test automation agent. Use when asked to test an iOS app feature, run regression tests, or automate UI testing on a simulator. Orchestrates verify-cli-env, load-test-cases, run-test-case, and generate-test-report skills. Outputs a Markdown report with screenshots.
iOS UI test automation agent for iPad simulators. Use when asked to test an iPad app feature, run iPad regression tests, or automate UI testing on an iPad simulator. Includes iPad-specific checks: split-view, slide-over, popover, multitasking. Outputs a Markdown report with screenshots.
iOS UI test automation agent for iPhone simulators. Use when asked to test an iPhone app feature, run iPhone regression tests, or automate UI testing on an iPhone simulator. Outputs a Markdown report with screenshots.
macOS UI test automation agent. Use when asked to test a macOS app feature, run macOS regression tests, or automate UI testing on the host Mac. Supports native macOS targets and Mac Catalyst. No simulator required. Outputs a Markdown report with screenshots.
Generate a Markdown test report from completed test case results. Used by all platform agents after all test cases have been executed. Writes the report to tests/reports/ and returns the file path.
Detect test mode (ad-hoc vs regression) and return a list of test cases to run. Used by all platform agents (iphone-tester, ipad-tester, macos-tester). For regression: reads tests/ios-tests.yaml or infers cases from the codebase. For ad-hoc: generates a minimal test plan from the user's description.
Execute a single UI test case and return its result. Works across iPhone, iPad, and macOS — pass the platform param to adjust behavior. Requires the app to already be built and running before calling this skill. Returns: pass, flaky, or fail — with screenshot path, logs, and root cause on failure.
List available simulators, filter to iPad only, and recommend one based on test content. Use inside ipad-tester agent after load-test-cases and before build-and-launch. Includes iPad-specific checks: split-view, slide-over, multitasking layout. Presents recommendation with reasoning and waits for user confirmation.
List available simulators, filter to iPhone only, and recommend one based on test content. Use inside iphone-tester agent after load-test-cases and before build-and-launch. Presents recommendation with reasoning and waits for user confirmation.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
AI-driven UI test automation for iOS, iPadOS, and macOS apps — powered by Claude Code, xcodebuildmcp, and AXe CLI.
| Tool | Install |
|---|---|
xcodebuildmcp | npm install -g xcodebuildmcp@latest |
axe | github.com/cameroncooke/AXe |
macOS only: Grant Accessibility permission to your terminal — System Settings → Privacy & Security → Accessibility.
Verify both are installed:
xcodebuildmcp --version
axe --version
Note: Verify exact Claude Code plugin commands against the official docs before use — command syntax may vary by version.
/plugin marketplace add https://github.com/hoangdh2001/apple-app-ui-test-automation
/plugin install apple-ui-test-automation
Open a Claude Code session in your Xcode project directory, then invoke an agent:
# iPhone
Use the iphone-tester agent to run a regression suite on my app
# iPad
Use the ipad-tester agent to test split-view behavior
# macOS
Use the macos-tester agent to run the full test suite
# Auto-detect iPhone/iPad
Use the ios-ui-automation-tester agent
Each agent runs a 7-phase workflow: environment check → project discovery → load tests → select device → build & launch → run tests → generate report.
Define regression tests in tests/ios-tests.yaml:
suite: Suite Name
version: 1.0
cases:
- id: kebab-case-id
name: "Human readable name"
feature: "Tab > Section"
steps:
- navigate: <tab name> # tap tab bar by label
- tap: "<element label>" # tap UI element by label
- select: "<option>" # tap picker or menu item
- type: "<text>" # type into focused field
expect:
- ui_contains: "<label>" # assert element exists
- element_not_exists: "<label>" # assert element absent
A skeleton example is provided in tests/ios-tests.yaml.
After each run, a Markdown report is generated at:
tests/reports/YYYY-MM-DD-HH-MM-<platform>-<suite>.md
Screenshots are stored in tests/reports/screenshots/. The tests/reports/ directory is gitignored.
MIT — © hoangdh2001
npx claudepluginhub hoangdh2001/apple-app-ui-test-automation --plugin apple-ui-test-automationTools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
AI-powered development tools for code review, research, design, and workflow automation.