---
name: multi-agent-test
language: en
description: "UI Bug Hunter  -  iOS Simulator (simctl) + Android Emulator (adb). Auto-detects platform. Screenshot + tap + analyze on the booted device. The Phase 5 Manual Test flow lives at multi-agent-manual-test. Use when a running app should be driven on a simulator or emulator to hunt UI bugs."
user-invocable: true
argument-hint: '[scenario]  -  e.g. "dark mode" | "accessibility" | "dynamic type" | "screenshot tr" | "store-ready" | (empty = full sweep)'
---

# multi-agent-test  -  UI Bug Hunter

Mobile UI test runner. Boots a simulator / emulator, drives it via MCP tools, and audits the running app for visual / accessibility / platform issues. Auto-detects iOS vs Android from cwd.

**Input**: $ARGUMENTS (optional  -  test scenario tag).

## Dispatcher

This skill delegates to the full UI Bug Hunter flow. Read and follow:

```
$HOME/.copilot/multi-agent/sim-test.md
```

(Equivalent on Claude Code: `$HOME/.claude/commands/sim-test.md`.)

Pass `$ARGUMENTS` through verbatim  -  the target doc picks the right test matrix based on the argument.

## Quick reference

| Invocation | Fixed-scenario alias | What it does |
|---|---|---|
| `multi-agent-test` | - | Walk all screens, collect screenshot + UI tree, general report |
| `multi-agent-test "dark mode"` | `multi-agent-test-dark-mode` | Light/dark comparison, contrast + color bugs |
| `multi-agent-test "accessibility"` | `multi-agent-test-accessibility` | VoiceOver label + tap target + contrast audit |
| `multi-agent-test "dynamic type"` | `multi-agent-test-dynamic-type` | XL-XXXL text-size layout check |
| `multi-agent-test "screenshot <lang>"` | `multi-agent-test-screenshots [locale]` | App Store screenshot set in a locale (alias defaults to tr) |
| `multi-agent-test "store-ready" [path]` | hands off to `multi-agent-store-ready` | package validation, not a UI test |

Both columns are supported and neither is deprecated; the aliases exist so the
scenario list autocompletes off `test-` instead of having to be remembered.

`store-ready` is the odd one out: it validates a built **package** rather than a
running app, so it is not implemented here at all. `multi-agent-store-ready` owns
it on both platforms  -  three gates per platform, plus this file's sweep as its
Step A. `multi-agent-testflight-validation` is the iOS-pinned alias of that skill.
The quoted tag is kept as a hand-off so an existing invocation still lands
somewhere correct.

## Requirements

- **iOS**: Xcode + booted Simulator (`xcrun simctl list | grep Booted`)
- **Android**: Android SDK + running emulator or USB device (`adb devices`)
- **MCP**: `multi-agent-toolkit` MCP server registered (tool names start with `mcp__multi-agent-toolkit__*`)

For the Phase 5 manual test mode (branch checkout + Xcode hint), use `multi-agent-manual-test` instead.