agent-creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when building Mac apps — menu bar extras, window management, AppKit integration, or notarized distribution outside the App Store.
$ npx -y skills add fusengine/agents --skill macos --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/macosContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when building Mac apps — menu bar extras, window management, AppKit integration, or notarized distribution outside the App Store.
name: macos description: Use when building Mac apps — menu bar extras, window management, AppKit integration, or notarized distribution outside the App Store. versions: macos: 26 xcode: 26 user-invocable: false references: references/app-structure.md, references/build-tools.md, references/appkit-integration.md, references/notarization.md related-skills: swift-core, swiftui-core, mcp-tools, build-distribution
<objective> Covers macOS-specific development: menu bar apps via MenuBarExtra, multi-window application management, keyboard shortcuts and menus, AppKit integration (NSViewRepresentable) inside SwiftUI, and notarization for distribution outside the Mac App Store.
Lists the XcodeBuildMCP tools for macOS builds (build_macos, build_run_macos, test_macos, launch_mac_app, stop_mac_app) and references for app structure (MenuBarExtra, Settings, Windows), build tooling, AppKit bridging, and code-signing/notarization.
Best practices: support keyboard shortcuts for power users, use MenuBarExtra for utility apps, use WindowGroup/Window for multi-window apps and Settings for the preferences scene, notarize before distributing outside the App Store, and enable sandboxing for App Store submissions. </objective>
macOS-specific development with window management and distribution tools.
Before ANY implementation, spawn 3 agents in parallel, one `Agent` call each with a `name`:
1. **fuse-ai-pilot:explore-codebase** - Analyze existing macOS patterns 2. **fuse-ai-pilot:research-expert** - Verify latest macOS 26 docs via Context7/Exa 3. **mcp__XcodeBuildMCP__build_macos** - Build for macOS validation
After implementation, run **fuse-ai-pilot:sniper** for validation.
---
| Feature | Benefit | |---------|---------| | MenuBarExtra | Background utility apps | | Window management | Multi-window support | | Keyboard shortcuts | Power user productivity | | Notarization | Gatekeeper-safe distribution |
---
---
| Need | Reference | |------|-----------| | MenuBarExtra, Settings, Windows | [app-structure.md](references/app-structure.md) | | XcodeBuildMCP macOS tools | [build-tools.md](references/build-tools.md) | | NSViewRepresentable, menus | [appkit-integration.md](references/appkit-integration.md) | | Code signing, notarization | [notarization.md](references/notarization.md) |
---
1. **Keyboard shortcuts** - Support power users 2. **Menu bar integration** - For utility apps 3. **Multiple windows** - Use WindowGroup/Window 4. **Settings window** - Use Settings scene 5. **Notarization** - Required for distribution 6. **Sandbox** - Enable for App Store
A plugin ecosystem that turns Claude Code into a supervised, multi-agent development environment.
Repo: fusengine/agents
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 feature, refactor, develop).
Use when creating a feature/component or adding functionality. Fires BEFORE APEX Analyze to refine requirements via structured questioning.
Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches the owner (APEX or plain conversation); also fires at every…
Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture violations. Do NOT use for functional…
Use when an expert agent self-reviews and self-corrects code after the Execute phase, before sniper validation (BMAD-METHOD elicitation techniques).