agent-creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when building iPhone apps — simulator/device testing, UI automation, or debugging — with XcodeBuildMCP tools.
Claude Code
$ npx -y skills add fusengine/claude-plugins --skill ios --agent claude-code
Codex
$ npx skills add fusengine/claude-plugins --skill ios -a codex -y
Cursor
$ npx skills add fusengine/claude-plugins --skill ios -a cursor -y
Gemini CLI
$ npx skills add fusengine/claude-plugins --skill ios -a gemini-cli -y
GitHub Copilot
$ npx skills add fusengine/claude-plugins --skill ios -a github-copilot -y
OpenCode
$ npx skills add fusengine/claude-plugins --skill ios -a opencode -y
Windsurf
$ npx skills add fusengine/claude-plugins --skill ios -a windsurf -y
name: ios description: Use when building iPhone apps — simulator/device testing, UI automation, or debugging — with XcodeBuildMCP tools. versions: ios: 27.2 xcode: 27.2 user-invocable: false references: references/simulator-tools.md, references/device-tools.md, references/ui-automation.md, references/debugging.md, references/uikit-integration.md related-skills: swift-core, swiftui-core, ipados, mcp-tools
<objective> Covers iOS-specific development using XcodeBuildMCP automation tools: building and testing on the iOS Simulator, deploying to physical devices, scripted UI interactions (tap, swipe, screenshot, view-hierarchy snapshot), LLDB debugging, and integrating UIKit views inside SwiftUI.
Lists the concrete MCP tools available for each phase — simulator tools (build_sim, boot_sim, launch_app_sim, test_sim), device tools (build_device, install_app_device, list_devices), and UI automation primitives.
Best practices: build before every commit, iterate on the simulator first, always test on a real device before release, enable accessibility identifiers for UI automation, and validate against the oldest supported iOS version. </objective>
iOS-specific development with XcodeBuildMCP automation tools.
Before ANY implementation, spawn 3 agents in parallel, one `Agent` call each with a `name`:
1. **fuse-ai-pilot:explore-codebase** - Analyze existing iOS patterns 2. **fuse-ai-pilot:research-expert** - Verify latest iOS 27.2 docs via Context7/Exa 3. **mcp__XcodeBuildMCP__discover_projs** - Find Xcode projects
After implementation, run **fuse-ai-pilot:sniper** for validation.
---
| Feature | Benefit | |---------|---------| | XcodeBuildMCP | Automated build and test | | UI Automation | Scripted user interactions | | Simulator tools | Fast iteration cycle | | Device tools | Real hardware testing |
---
---
| Need | Reference | |------|-----------| | Simulator build/test | [simulator-tools.md](references/simulator-tools.md) | | Device deployment | [device-tools.md](references/device-tools.md) | | Touch automation | [ui-automation.md](references/ui-automation.md) | | LLDB debugging | [debugging.md](references/debugging.md) | | UIKit in SwiftUI | [uikit-integration.md](references/uikit-integration.md) |
---
1. **Build validation** - Always build before commit 2. **Simulator first** - Faster iteration 3. **Device testing** - Required before release 4. **Accessibility IDs** - Enable UI automation 5. **Screenshots** - Document UI states 6. **Test on oldest supported** - iOS version compatibility (minimum deployment target, independent of the 27.2 SDK you build with) 7. **27 SDK launch rules** - UIKit apps must use the scene-based life cycle or they fail to launch; Info.plist needs a launch screen key; On Demand Resources is deprecated (Background Assets). Details: `swift-core/references/sdk-27-changes.md`
A plugin ecosystem that turns Claude Code into a supervised, multi-agent development environment.
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when starting ANY development task -- feature, bug fix, refactor, hotfix (triggers: implement, create, build, fix, add…
Use when creating a feature/component or adding functionality. Fires BEFORE APEX Analyze to refine requirements via structured…
Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches the owner (APEX or plain…
Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture…
Use when an expert agent self-reviews and self-corrects code after the Execute phase, before sniper validation (BMAD-METHOD…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.