programmatic-uikit-layout
Use when building UIKit interfaces without storyboards, setting up Auto Layout constraints with anchors, creating reusable UI components, or encountering layout constraint errors and ambiguous layout warnings
Use when building UIKit interfaces without storyboards, setting up Auto Layout constraints with anchors, creating reusable UI components, or encountering layout constraint errors and ambiguous layout warnings
Use when architecting complex iOS apps with multiple features, long-term maintenance requirements, or team scalability needs. Use when refactoring Massive View Controllers or implementing testable architecture. Do NOT use for simple single-screen apps, rapid prototypes, or small utility tools.
SwiftUI UI component catalog. Use when implementing NavigationStack, Swift Charts, PhotosPicker, TipKit, ScrollView enhancements, animations, layouts, WebView, Liquid Glass and other UI components. Organized by feature category with OS version compatibility info. Reference for discovering available components and implementation patterns.
Migration guide for Swift and iOS. Use when migrating ObservableObject to @Observable (iOS 17), enabling Swift 6/6.2 Strict Concurrency, fixing @MainActor/Sendable warnings, adopting Approachable Concurrency (Swift 6.2), or handling iPadOS 26 windowing system changes (UIRequiresFullScreen deprecation). Covers breaking changes and version upgrade tasks.
Use when implementing Realm database in iOS apps, encountering thread-safety errors, async/await crashes, performance issues with sync/writes, or integrating with Codable APIs
Single Source of Truth (SSOT) guidelines for SwiftUI state management. Use when designing state architecture, choosing between @State/@Binding/@StateObject/@ObservedObject/@EnvironmentObject, fixing state synchronization issues, refactoring duplicated state, or reviewing state management in PRs. Covers SSOT principles, property wrapper selection, state lifting, and common violations.
Generate Koin dependency injection code for Kotlin Multiplatform (KMP) projects using Koin 4.x. Use when (1) Setting up Koin DI in KMP projects, (2) Creating Koin modules for features, (3) Implementing DSL-based or Annotations-based DI, (4) Configuring platform-specific dependencies with expect/actual, (5) Adding ViewModels with Koin, (6) Structuring DI for clean architecture (UI/Domain/Data layers). Triggers: koin, dependency injection, di module, koin module, @Single, @Factory, viewModel{}, single{}, factory{}, kmp di, multiplatform di.
This skill should be used when the user wants to bump versions, create releases, or tag versions. Triggers include: "bump version", "bump the version", "version bump", "release version", "tag a release", "create release", "major/minor/patch bump", "update version", "new version", "/version". Updates plugin.json and marketplace.json. Creates git tag and commit.
Use when the user explicitly requests repeated execution until completion (phrases like "loop until done", "keep iterating", "repeat until fixed"), typically for bug fixes or feature work.
Guide for writing production-quality bash scripts following modern idiomatic practices. Enforces set -euo pipefail, [[ ]] conditionals, ${var} syntax, ShellCheck compliance. Triggers on "bash script", "shell script", ".sh file", "write a script", "automation script", "bash function", "shellcheck", "bash template", "pre-commit hook", "deploy script", "build script", "install script", "setup script", "bash error handling", "bash arrays", "bash loop", "bash conditional", "parse arguments", "getopts", "bash logging", "#!/bin/bash", "source script", "dot script", "shell function", "edit script", "update script", "modify script", "change script", "edit .sh", "update .sh", "modify .sh", "statusline.sh", "hook script". PROACTIVE: MUST invoke BEFORE editing/writing ANY .sh file or pre-commit hook.
Automatically coordinates multi-skill workflows and triggers follow-up actions. Use when completing PRD creation, implementation, or any milestone that should trigger additional skills. This skill reads the auto-trigger configuration and executes the workflow chain.
Execute multiple independent tasks simultaneously using parallel agent coordination to maximize throughput and minimize execution time. Use when tasks have no dependencies, results can be aggregated, and agents are available for concurrent work.
Deploy project to the Agentuity Cloud. Requires authentication. Use for Agentuity cloud platform operations
View logs for a specific deployment. Requires authentication. Use for Agentuity cloud platform operations
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Delegate specialized reviews to subagents and synthesize their findings. Use when reviewing code.