Building a separate app from this template? The App Generator is a standalone macOS product (coming soon) that drives your own coding-agent CLI to scaffold a differentiated, App Store Guideline 4.3-safe app from the boilerplate. See Pricing & License for details and the waitlist.
Recommended Setup
For most SwiftAI Boilerplate Pro projects, start here:Open the repository root
Open the folder that contains
AGENTS.md, SwiftAIBoilerplatePro.xcodeproj, Packages/, and docs/. The root AGENTS.md is the shared entry point that points every agent at docs/CLAUDE.md and docs/INDEX.md.Use Xcode Coding Intelligence for build-aware work
Xcode Coding Intelligence with Claude Agent is a strong fit for Swift apps because it can stay close to Xcode’s project, build, simulator, and diagnostics workflow.
Use Claude Code for larger agentic changes
Claude Code is best when you want the agent to inspect many files, implement a full feature, run commands, and iterate until the project builds.
Tool Comparison
| Tool | Best For | Project Context |
|---|---|---|
| Xcode Coding Intelligence | Swift app work inside Xcode, build issues, simulator-aware iteration | Reads root AGENTS.md → docs/CLAUDE.md when started from the project root |
| Claude Code | Larger autonomous coding tasks and verification loops | Reads root AGENTS.md, which points to docs/CLAUDE.md |
| Cursor AI | Inline edits, refactors, and code review while editing | Reads .cursor/rules/*.mdc (plus AGENTS.md) |
| Bolt AI chat modes | Specialized chat personas and prompt-driven workflows | Uses .bolt/chat-modes.json and project files you provide as context |
Claude Code and Claude Agent (CLAUDE.md)
The boilerplate includes a production-tested docs/CLAUDE.md that gives Claude Code full project context. A root AGENTS.md is the shared entry point all agents read first; it points Claude Code, Cursor, Codex, and others at docs/CLAUDE.md and docs/INDEX.md, so generated code fits the boilerplate from the first message.
What CLAUDE.md Covers
- Architecture: MVVM patterns, module boundaries, which abstractions to use
- Build commands: Environment-aware instructions for Xcode MCP vs Claude Code CLI
- Anti-patterns: No UIKit, no ObservableObject, no raw URLSession
- File conventions: Naming patterns, organization, where new code belongs
- Integration specifics: Supabase, RevenueCat, OpenRouter configuration
How Agentic Development Works
- Open Claude Code in your project directory
- Describe the feature you want
- Claude reads your codebase, generates code following your patterns, builds it, and iterates until it works
Example Workflow
Community Skills
You can extend Claude’s iOS knowledge with community skills. These teach Claude about platform conventions, Xcode tooling, and SwiftUI best practices.Apple Platform Skills
Apple platform conventions, Xcode project structure, SwiftUI, and App Store review awareness.Source: rshankras/claude-code-apple-skills
iOS Simulator
Lets Claude boot, build, install, and interact with the iOS Simulator directly.Source: conorluddy/ios-simulator-skill
/plugin ... commands inside Claude Code or Claude Agent chat. Run git, cp, and npx commands in your terminal. For the full list of recommended skills and module mappings, see the Agentic Development Setup guide.
Cursor AI Rules (.cursor/rules/)
Cursor AI reads .mdc (Markdown Code) files from your project to understand patterns and constraints. Six rule files are included.
Included Rule Files
core.mdc
Applied to: All Swift filesFile size limits (max 400 lines), MVVM patterns, dependency injection, error handling, Swift Concurrency, testing requirements.
swiftui-views.mdc
Applied to: View files (
*View.swift)View composition, state management, list optimization, navigation, form handling, accessibility.architecture.mdc
Applied to: Repositories, Clients, PackagesModular package boundaries, protocol-based APIs, repository pattern, CompositionRoot, structured logging, test doubles.
design-system.mdc
Applied to: DesignSystem, AppShellDSColors tokens, DSTypography type scale, DSSpacing tokens, component library usage, theme consistency.
app-store-differentiation.mdc
Applied to: Swift, config, and Markdown filesGuideline 4.3(a) differentiation (binary, metadata, concept), the
APP_STORE_4_3_HARDENING.md checklist, and the FeatureChat to AI coupling when removing chat.ios-platform-safety.mdc
Applied to: Swift,
Info.plist, PrivacyInfo.xcprivacyPublic APIs only, Swift 6 concurrency, permission strings and privacy manifests, StoreKit/IAP for digital goods, accessibility baselines, and secrets via the existing HTTPClient + xcconfig.How It Works
Open the project in Cursor. The rules load automatically. Ask Cursor to build something, and it follows your architecture.Example Prompts
Creating Views
Creating Views
@Observable ViewModel with loading and error states.Creating ViewModels
Creating ViewModels
@MainActor @Observable, inject dependencies via initializer, use protocol types, and add structured logging.Creating Feature Packages
Creating Feature Packages
Refactoring
Refactoring
Bolt AI Chat Modes (.bolt/)
Bolt AI provides 12 specialized AI assistants for different development tasks. Each mode loads relevant context and uses a domain-specific system prompt.
Available Chat Modes
iOS Developer
/dev (default). General iOS/SwiftUI development with MVVM and async/await.Architecture Advisor
/arch. Package boundaries, protocol-based APIs, clean architecture.SwiftUI
/ui. View composition, DesignSystem usage, state management, accessibility.Feature Dev
/feature. Self-contained feature modules with protocol APIs and tests.Integration
/integration. Supabase, RevenueCat, Firebase setup and troubleshooting.Testing
/test. Unit tests, mock protocols, test doubles, async testing.Debug
/debug. Bug diagnosis, crash analysis, memory leaks, performance.Performance
/perf. Memory management, lazy loading, rendering optimization.Package Dev
/package. Swift Package Manager, API design, dependencies.Deploy
/deploy. App Store submission, TestFlight, provisioning, CI/CD.Accessibility
/a11y. VoiceOver, Dynamic Type, inclusive design, WCAG compliance.Documentation
/doc. Technical writing, API docs, integration guides.Before and After
Without configurations, AI generates code with hardcoded colors, no ViewModel, direct singleton dependencies, and no error handling. With configurations, the same prompt produces code that follows your architecture.Without Configurations
Prompt: “Create a user profile view with avatar and sign-out”With Configurations
Same prompt, same AI tool:@Observable, localized error handling, loading state, structured logging, @MainActor, async/await. All from the same one-line prompt.
Customization
Modifying Cursor Rules
Edit.mdc files in .cursor/rules/. Each file has YAML frontmatter (description, globs, alwaysApply) followed by markdown sections with good/bad code examples. Changes take effect when you save.
Modifying CLAUDE.md
Editdocs/CLAUDE.md (or the root AGENTS.md entry point). Add your own patterns, anti-patterns, or module-specific instructions. Claude picks up changes on the next conversation.
Adding Bolt Chat Modes
Edit.bolt/chat-modes.json to add custom modes:
Documentation
Agentic Development Setup
CLAUDE.md details and community skills
Cursor Rules README
Detailed guide on Cursor AI rules
Architecture Guide
The patterns AI follows
DesignSystem Guide
Design tokens reference
Questions
Do I need Claude Code, Xcode Coding Intelligence, Cursor, or Bolt?
Do I need Claude Code, Xcode Coding Intelligence, Cursor, or Bolt?
None of them are required. All are supported. Xcode Coding Intelligence is a great default for Swift work inside Xcode. Claude Code works best for agentic development, such as building full features from a description. Cursor works best for inline code generation while you edit. Bolt works best for chat-based task switching. Use whichever fits your workflow, or combine them.
Can I use other AI assistants?
Can I use other AI assistants?
Yes. The root
AGENTS.md is read by most coding agents, and the patterns in docs/CLAUDE.md and the .mdc files work as reference for any AI tool. You can paste relevant sections into ChatGPT, Copilot, or any assistant that accepts context.Will this slow down my development?
Will this slow down my development?
The opposite. AI configurations make code generation faster and more accurate because the AI gets it right the first time. Less time fixing, more time shipping.
Can I modify the configurations?
Can I modify the configurations?
Yes. Edit
docs/CLAUDE.md (or root AGENTS.md), .cursor/rules/*.mdc, or .bolt/chat-modes.json to match your preferences. Changes take effect immediately (Cursor, Bolt) or on the next conversation (Claude Code).Do the rules apply to my manually-written code?
Do the rules apply to my manually-written code?
No. These configurations only guide AI code generation. They don’t lint or enforce anything on code you write by hand.
Next Steps
Build Your First Feature
Use AI to build a feature with your project’s patterns
Architecture Overview
Understand the patterns AI follows
Testing Guide
Let AI write tests for your features
