Swift-focused AI agent skills for iOS and macOS: build, debug, simulator, SwiftUI, Xcode, App Store workflows. Part of Plug'n Skills.
SaferSkills independently audited build-swift-apps (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use this as the first hop when a request could match more than one Build Swift Apps skill. Do not complete domain work from this router alone; choose the narrow skill, read it, then act.
ios-simulator-browser; use ios-simulator-debugger first only to build/run, pick a Simulator UDID, inspect UI trees, logs, bundle IDs, or handle headless automation.ios-rocketsim-operator only when RocketSim-specific UI automation, visible accessibility state, or its bundled CLI is required.ios-ettrace-profiler for CPU/startup/scrolling/runtime performance traces; use ios-memgraph-inspector for leaks, retain cycles, and before/after memory proof.ios-swiftui-architect; for macOS SwiftUI scenes/windows/menus/settings, use macos-swiftui-architect; for platform-neutral SwiftUI refactors, use swiftui-view-architect; for runtime performance review, use swiftui-performance-inspector.xcode-build-strategist unless the user explicitly asks only for a baseline, compile hotspot analysis, project settings audit, or approved tuning. Then route to xcode-build-baseline, xcode-compile-profiler, xcode-project-auditor, or xcode-build-tuner.appstore-release-director for end-to-end publishing, appstore-release-planner for go/no-go readiness planning, and appstore-review-readiness for concrete validate/stage/submit/monitor/cancel/repair commands. Use other focused appstore-* skills for command discovery, ID resolution, archive/upload, build monitoring, TestFlight, metadata, screenshots, signing, pricing, subscriptions, crash feedback, or workflow automation.appstore-metadata-sync for canonical ./metadata JSON field operations, appstore-metadata-localizer for translation/adaptation across listing locales, appstore-release-notes-writer for What's New or promotional text, and appstore-subscription-localizer for subscription/group/IAP display names.macos-signing-inspector for existing-artifact signing/entitlement/Gatekeeper diagnosis, macos-notarization-packager for Developer ID package readiness, and appstore-notary-runner for concrete asc notarization submit/status/log/staple command execution.tuist-migration-planner for conversion, tuist-workspace-navigator for normal generated workspace work, tuist-generation-doctor for generation/build/runtime failures, and tuist-flaky-test-stabilizer for flaky test evidence and fixes.swiftpm-build-inspector; for package-first macOS build/run/test work, use macos-swiftpm-runner.apple-dev-research; for firmware, dyld, Mach-O, entitlements, or private API research, use apple-firmware-inspector.Do not merge skills just because they share a platform word. Keep separate skills when triggers, tools, proof artifacts, or safety boundaries differ. Prefer this router plus focused skills until a decision ledger proves a merge preserves trigger coverage and validation.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.