implementation-guide
Generates detailed implementation guide with pseudo-code and step-by-step development instructions. Creates IMPLEMENTATION_GUIDE.md from PRD, Architecture, and UX specs. Use when creating development roadmap.
What this skill does
# Implementation Guide Skill
Generate detailed implementation guide with pseudo-code and step-by-step instructions for iOS/macOS app development.
## Metadata
- **Name**: implementation-guide
- **Version**: 1.0.0
- **Role**: Senior iOS/macOS Developer
- **Author**: ProductAgent Team
## When This Skill Activates
This skill activates when the user says:
- "generate implementation guide"
- "create development guide"
- "write implementation steps"
- "generate code guide"
- "create developer guide from specs"
## Description
You are a Senior iOS/macOS Developer AI agent with expertise in Swift, SwiftUI, SwiftData, and modern iOS development patterns. Your job is to transform product requirements, architecture, and UX specifications into a comprehensive, step-by-step implementation guide that enables any competent iOS developer to build the app confidently.
## Prerequisites
Before activating this skill, ensure:
1. PRD exists (from prd-generator skill) with all features defined
2. ARCHITECTURE.md exists (from architecture-spec skill) with tech stack and structure
3. UX_SPEC.md exists (from ux-spec skill) with wireframes and interactions
4. DESIGN_SYSTEM.md exists with colors, typography, components
## Input Sources
Read and extract information from:
1. **docs/PRD.md**
- All features and user stories
- Acceptance criteria
- Success metrics
- Timeline estimates
2. **docs/ARCHITECTURE.md**
- Architecture pattern (MVVM, Clean, TCA)
- Technology stack decisions
- Data models and relationships
- Module structure
- Networking layer design
3. **docs/UX_SPEC.md**
- All screens and wireframes
- User flows
- Interactions and gestures
- States (empty, loading, error)
4. **docs/DESIGN_SYSTEM.md**
- Colors, typography, spacing
- Component styles
- Animation timings
- Design tokens
5. **User clarifications** (ask if needed):
- Xcode version / minimum iOS version preferences
- Any existing codebase to integrate with
- CI/CD preferences (Xcode Cloud, GitHub Actions, Fastlane)
## Output
Generate: **docs/IMPLEMENTATION_GUIDE.md**
Structure (comprehensive, ~3000-5000 lines):
```markdown
# Implementation Guide: [App Name]
**Version**: 1.0.0
**Last Updated**: [Date]
**Platform**: iOS [Version]+
**Language**: Swift 5.9+
**Framework**: SwiftUI
**Xcode**: 15.0+
---
## 0. Quick Start
For the impatient developer:
```bash
# 1. Clone or create new Xcode project
# Template: iOS App (SwiftUI)
# Name: [AppName]
# Organization ID: com.yourcompany.appname
# Language: Swift
# Storage: SwiftData
# Include Tests: Yes
# 2. Set minimum deployment target
# Project Settings → General → Minimum Deployments: iOS 26.0 (or iOS 17+ for broader reach)
# 3. Add dependencies via SPM (if any)
# File → Add Package Dependencies → [URLs from ARCHITECTURE.md]
# 4. Create folder structure (see Section 2)
# 5. Follow implementation phases (Section 3)
# 6. Run tests frequently
xcodebuild test -scheme [AppName]
# 7. Launch and iterate
```
**Estimated Timeline**: [X] weeks for MVP (from PRD)
**Estimated LOC**: ~[Y] lines of Swift code
**Files to Create**: ~[Z] .swift files
---
## 1. Project Setup
### 1.1 Create Xcode Project
1. Open Xcode 15+
2. File → New → Project
3. Choose template: **iOS → App**
4. Configuration:
- **Product Name**: [AppName]
- **Team**: [Your team or Personal Team]
- **Organization Identifier**: com.yourcompany.appname
- **Bundle Identifier**: [Auto-generated]
- **Interface**: SwiftUI
- **Language**: Swift
- **Storage**: SwiftData [or Core Data based on ARCHITECTURE]
- **Include Tests**: ✅ Yes
- **Create Git repository**: ✅ Optional but recommended
5. Click Create
### 1.2 Project Configuration
**File**: Select project in Navigator → General tab
**Deployment Info**:
- **Minimum Deployments**: iOS 26.0 [adjust based on ARCHITECTURE — iOS 17+ still supported for broader reach]
- **Supported Destinations**: iPhone (✅), iPad (based on requirements)
- **Device Orientation**:
- Portrait (✅ Required)
- Landscape Left (based on requirements)
- Landscape Right (based on requirements)
**App Icons & Launch Screen**:
- **App Icon**: Add 1024x1024 icon to Assets.xcassets/AppIcon
- **Launch Screen**: Use default or customize LaunchScreen.storyboard
**Signing & Capabilities**:
- **Team**: Select your development team
- **Signing Certificate**: Automatically manage signing (recommended)
- **Capabilities**: Add as needed:
- Push Notifications (if required)
- iCloud (if using CloudKit sync)
- Background Modes (if needed)
### 1.3 Add Dependencies (if any)
**From ARCHITECTURE.md**, add these packages:
**Example** (adjust based on actual ARCHITECTURE):
```
File → Add Package Dependencies
[If networking library needed]
1. Alamofire: https://github.com/Alamofire/Alamofire
Version: 5.9.0+
[If image loading needed]
2. Kingfisher: https://github.com/onevcat/Kingfisher
Version: 7.10.0+
[Add only packages specified in ARCHITECTURE.md]
```
**Important**: Minimize third-party dependencies. Use native frameworks when possible.
### 1.4 Configure SwiftData
**File**: [AppName]App.swift
```swift
import SwiftUI
import SwiftData
@main
struct AppNameApp: App {
// Define the data model container
var sharedModelContainer: ModelContainer = {
let schema = Schema([
// List all @Model classes here
User.self,
Item.self,
// Add all data models from ARCHITECTURE.md
])
let modelConfiguration = ModelConfiguration(
schema: schema,
isStoredInMemoryOnly: false // Persist to disk
)
do {
return try ModelContainer(
for: schema,
configurations: [modelConfiguration]
)
} catch {
fatalError("Could not create ModelContainer: \\(error)")
}
}()
var body: some Scene {
WindowGroup {
ContentView()
}
.modelContainer(sharedModelContainer)
}
}
```
---
## 2. File Structure
Create this folder hierarchy in your project:
```
[AppName]/
├── App/
│ ├── [AppName]App.swift # Entry point
│ └── ContentView.swift # Root view (delete if not using)
│
├── Features/ # Feature modules
│ ├── Onboarding/
│ │ ├── Views/
│ │ │ ├── OnboardingView.swift
│ │ │ ├── OnboardingStep1View.swift
│ │ │ └── OnboardingStep2View.swift
│ │ └── ViewModels/
│ │ └── OnboardingViewModel.swift
│ │
│ ├── Home/
│ │ ├── Views/
│ │ │ ├── HomeView.swift
│ │ │ ├── HomeCardView.swift
│ │ │ └── HomeEmptyStateView.swift
│ │ ├── ViewModels/
│ │ │ └── HomeViewModel.swift
│ │ └── Models/
│ │ └── HomeFilter.swift # View-specific models
│ │
│ ├── ItemDetail/
│ │ ├── Views/
│ │ │ ├── ItemDetailView.swift
│ │ │ └── ItemDetailHeaderView.swift
│ │ └── ViewModels/
│ │ └── ItemDetailViewModel.swift
│ │
│ ├── AddEditItem/
│ │ ├── Views/
│ │ │ └── AddEditItemView.swift
│ │ └── ViewModels/
│ │ └── AddEditItemViewModel.swift
│ │
│ └── Settings/
│ ├── Views/
│ │ ├── SettingsView.swift
│ │ └── AccountView.swift
│ └── ViewModels/
│ └── SettingsViewModel.swift
│
├── Core/ # Shared infrastructure
│ ├── Networking/
│ │ ├── APIClient.swift # Base HTTP client
│ │ ├── Endpoint.swift # API endpoint definitions
│ │ ├── NetworkError.swift # Error types
│ │ └── APIService.swift # High-level API service
│ │
│ ├── Storage/
│ │ ├── DataManager.swift # SwiftData operations wrapper
│ │ └── CacheManager.swift # Optional: in-memory cache
│ │
│ ├── Extensions/
│ │ ├── View+Extensions.swift # SwiftUI view modifiers
│ │ ├── Color+Extensions.swift # Design system colors
│ │ ├── FRelated in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.