agent-creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when building Apple Watch apps — complications, workouts, HealthKit, or iPhone-Watch connectivity.
Claude Code
$ npx -y skills add fusengine/claude-plugins --skill watchos --agent claude-code
Codex
$ npx skills add fusengine/claude-plugins --skill watchos -a codex -y
Cursor
$ npx skills add fusengine/claude-plugins --skill watchos -a cursor -y
Gemini CLI
$ npx skills add fusengine/claude-plugins --skill watchos -a gemini-cli -y
GitHub Copilot
$ npx skills add fusengine/claude-plugins --skill watchos -a github-copilot -y
OpenCode
$ npx skills add fusengine/claude-plugins --skill watchos -a opencode -y
Windsurf
$ npx skills add fusengine/claude-plugins --skill watchos -a windsurf -y
name: watchos description: Use when building Apple Watch apps — complications, workouts, HealthKit, or iPhone-Watch connectivity. versions: watchos: 27.2 user-invocable: false references: references/complications.md, references/workouts.md, references/watch-connectivity.md related-skills: swift-core, swiftui-core, ios, mcp-tools
<objective> Covers watchOS-specific development for Apple Watch: watch-face complications for glanceable data, workout sessions and fitness tracking, HealthKit access to health metrics, and Watch Connectivity for iPhone-Watch sync.
Includes design considerations specific to the platform — small display with large touch targets, glanceable information with minimal text, Digital Crown scrolling/input, swipe/tap gestures, and battery-conscious background work.
Best practices: keep information glanceable, use large tap targets, minimize text input, drive watch-face updates through complications, use efficient background refresh, and always validate on real hardware since the simulator behaves differently. </objective>
watchOS-specific development for Apple Watch experiences.
Before ANY implementation, spawn 3 agents in parallel, one `Agent` call each with a `name`:
1. **fuse-ai-pilot:explore-codebase** - Analyze existing watchOS patterns 2. **fuse-ai-pilot:research-expert** - Verify latest watchOS 27.2 docs via Context7/Exa 3. **mcp__apple-docs__search_apple_docs** - Check watchOS patterns
After implementation, run **fuse-ai-pilot:sniper** for validation.
---
| Feature | Benefit | |---------|---------| | Complications | Glanceable data on watch face | | Workouts | Fitness and health tracking | | HealthKit | Access health metrics | | Connectivity | Sync with iPhone |
---
| Need | Reference | |------|-----------| | Watch face complications | [complications.md](references/complications.md) | | Workout sessions, HealthKit | [workouts.md](references/workouts.md) | | iPhone ↔ Watch sync | [watch-connectivity.md](references/watch-connectivity.md) |
---
Source: https://developer.apple.com/design/human-interface-guidelines/accessibility
---
1. **Glanceable** - Quick information access 2. **Large targets** - Easy tapping 3. **Minimal input** - Reduce typing 4. **Complications** - Update watch face data 5. **Background refresh** - Efficient updates 6. **Test on device** - Simulator differs from hardware 7. **No new WKExtension code** - `WKExtension` / `WKExtensionDelegate` are deprecated for apps with a minimum deployment target of watchOS 9.2 or later (watchOS 27 release notes, https://developer.apple.com/documentation/watchos-release-notes/watchos-27-release-notes)
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.