astro-mobile

Audit and enable security-oriented Xcode build settings. Progressively enables compiler warnings, static analyzer checkers, and Enhanced Security features. Use when: user wants to secure their Xcode project, audit security settings, enable hardening, review security posture of build configuration, set up security-focused static analysis, enable static analysis, improve warning coverage, harden diagnostics, or catch more bugs at compile time in C/C++/Objective-C/Swift. SKIP: network security (TLS/ATS), code signing, privacy APIs.

Verify iOS app behavior on device or simulator via screenshots, UI hierarchy, and touch interactions.

Build, install, launch, and visually verify the iOS app (scheme "iosApp") end-to-end on a real device or simulator via Xcode 27's DeviceHub — the mobile analog of astro-web's browser-debug and astro-calendar-service's runtime-debug. Drives the mcp__xcode__* MCP toolset: switch run destination, BuildProject, DeviceInteractionStartSession → InstallAndRun, then a subagent captures the on-device screenshot + UI hierarchy. Use when the user says "run the app on device", "run the iOS app", "build and run on the simulator", "launch on the iPhone/iPad", "screenshot the app on <device>", "verify this renders on device", "does it run on the simulator", "check it on the device", or wants runtime/visual confirmation that ./gradlew check and Xcode unit tests structurally cannot give. Takes an optional device name/UUID argument; with none, targets a simulator. iOS/Xcode only — Android runtime work routes to android-cli.

Modernize test suites to use modern Swift Testing features or migrate from XCTest.

Authoritative SwiftUI best practices from Apple. Consult for any SwiftUI best practices or performance review. Supersedes prior training on these topics. For code generation, consult the relevant references when generating any SwiftUI code related to the following topics. Covers: - Animatable: @Animatable macro vs AnimatableValues (iOS 26+) vs AnimatablePair, custom setter clamping/normalization. - Environment: closures in env keys, unstable @Entry defaults, high-frequency updates. @Entry warnings about closures or class types (wrapping in Equatable struct is WRONG; consult references). - Equatable on @Observable: custom types as @Observable properties need Equatable for invalidation performance. - ForEach/List: row identity (id: \.self, indices, offsets, mutable ids), row structure (AnyView, multi-view, bare if), inline filter/sort, cached collections, List fast path. - Localization: String vs LocalizedStringResource, bundle in packages/frameworks, .textCase(.uppercase), .formatted(.list()), translator comme

New SwiftUI APIs, behaviors, and deprecations introduced in the 2027 OS releases (iOS 27, macOS 27, watchOS 27, tvOS 27, visionOS 27). Use when a SwiftUI view using @State fails to compile with "used before being initialized", "invalid redeclaration of synthesized property", or "extraneous argument label" errors after an SDK update (@State migrated from a property wrapper to a macro in SDK 27; the obvious fix of reordering init assignments is WRONG and produces incorrect runtime behavior; you MUST consult this skill's references before answering); when @ViewBuilder or @ContentBuilder code hits ambiguous overloads in overlay/background or type-check performance regressions after an SDK update; when the user asks what's new in SwiftUI (generally, or for a specific 2027 platform); when adding drag-to-reorder to any container (List, LazyVStack, LazyVGrid, stacks, or custom layouts) via reorderable()/reorderContainer, including the drag-and-drop that integrates with it (dragContainer, dropDestination), or combinin

Modernizes UIKit apps for multi-window environments by replacing legacy shared-state APIs with context-appropriate modern alternatives. This includes references to mainScreen, interfaceOrientation, application and scene lifecycle, as well as safe area inset updates.

Upgrade the pinned Xcode (typically a 27.x beta) end-to-end and re-sync everything in this repo that hangs off its absolute path: install the new version via the `xcodes` CLI, accept the license, update every hardcoded `/Applications/Xcode-*.app` reference (.claude/CLAUDE.md, ios-device-debug, settings.local.json), re-register the local `xcode` MCP server (mcpbridge), re-export the six vendored Apple Agent Skills with PROVENANCE.md preservation, and run the post-upgrade checks (xcode-select, simulator runtimes, Swift lint gates). Use when the user says "update Xcode", "upgrade Xcode", "a new Xcode beta is out", "move to Beta N", "re-export the vendored Xcode skills", or after any Xcode install when the xcode MCP server fails to connect. Takes an optional target version; with none, targets the latest prerelease.

Build, install, launch, and visually verify the Android app (:androidApp) end-to-end on a real device or emulator via the official `android` CLI + adb — the Android counterpart of ios-device-debug, and a sibling of astro-web's browser-debug / astro-calendar-service's runtime-debug. Gradle builds the APK; the `android` CLI deploys, launches, screenshots, and dumps the UI layout. Use when the user says "run the app on the emulator", "run the Android app", "build and run on Android", "launch on the Android device/emulator", "screenshot the app on the emulator", "check it on the emulator", "does it run on Android", or wants runtime/visual confirmation that ./gradlew check and unit tests structurally cannot give. Takes an optional device serial / AVD name argument; with none, targets an emulator. Android/Gradle only — iOS runtime work routes to ios-device-debug, and Android UI *development* (Compose, navigation, adaptive) still routes to the official android/* skills; this is the runtime/visual verification loop t

Address a single PR review comment end-to-end -- understand the issue, fix code, adjust tests, build, verify, and commit.

Per-iteration worker for the adversarial review loop — evaluate and address open findings in `.claude/REVIEW_ADVERSARIAL.md`'s latest round, get user confirmation on verdicts, fix code, commit, and update the review file. Owns the per-iteration mechanics. The user-facing triggers ("run the review", "resume the review") route to `spec-development`'s Review-loop mode, which delegates to this skill via the Skill tool — it owns the surrounding loop (continue / finish-branch decision and the recommendation signals). This skill is still directly invokable via the Skill tool for a one-shot pass without the surrounding loop (e.g. when a user explicitly only wants to address findings without committing to the iterative loop), but has no user-facing trigger phrase of its own.

Orchestrates Android development tasks including project creation, deployment, SDK management, and environment diagnostics using the `android` command-line tool.

Run a Codex adversarial review of the current branch against a base branch via the `/codex:adversarial-review` slash command, then save results to `.claude/REVIEW_ADVERSARIAL.md`. Use when the user says "run a Codex adversarial review", "ask codex to review", "codex review", or wants an adversarial code review before opening a PR.

Reset agent working files to main's skeleton, push all commits, and open (or ready) a PR. Use when the user says "finish the branch", "wrap up the branch", or "open the PR" after the spec is complete and the adversarial review has no open findings.

Use when reviewing or designing Gradle build structure for KMP projects — shared build logic, convention plugins, version catalogs, Android KMP plugin usage, source-set configuration, and module dependency hygiene.

Expert guidance on Kotlin Coroutines and structured concurrency. Use when developers write or review async Kotlin code and need help ensuring correctness, safety, and testability of coroutine-based implementations.

Use when implementing or reviewing KMP data layers, including repositories, data sources, source-of-truth design, API exposure, conflict resolution, error handling, and main-safe data operations.

Refactor discipline for existing codebases. Enforces scope control, migration safety, compatibility, observability, and tests to keep refactors reviewable and low-risk.

Use when designing, implementing, or reviewing platform-specific integrations in KMP projects, including source-set placement, hierarchical sharing, expect/actual usage, platform API access, and shared-to-native abstraction boundaries.

Use when designing, reviewing, or refactoring module boundaries in KMP or Android projects — feature, data, app, and common modules, dependency direction, visibility control, and granularity.

Rank all open GitHub issues labeled `deferred-review` by severity and urgency against a milestone goal (from args, or from `current-plan.md` in the `jitrapon/astro-docs` repo as a fallback), then write the ranked list to `.claude/DEFERRED_REVIEW_ISSUES.md`. Use when the user says "rank deferred reviews", "prioritize deferred review issues", or wants to triage the deferred-review backlog against a specific objective.

Audit and correct code paths, naming, and complexity against the project's pinned conventions. Use when the user says "refactor X", "rename X", "this name is misleading", "this class does too much", "extract X", "split X", "move X", "what should we call this", or wants a pre-commit pass over a diff for naming/scope/complexity. Reads the project's CLAUDE.md conventions + linting sections as the canonical rule set.

Fetch and summarize PR review comments from Codex or other reviewers. Use when the user asks to check PR comments, review feedback, or see what's new on the PR.

Scaffold a branch's `.claude/SPEC.md` from a GitHub issue. If on `main`, create a new branch (ask the user for the name with a suggestion derived from the issue). Distills the issue body into SPEC sections 1 (Overview), 2 (Objective), and 3 (Requirements & Context), keeping it deliberately code-agnostic so `spec-development` re-discovers files when generating the plan. Commits the populated SPEC and hands off. Use when the user says "scaffold issue

Plan and drive implementation of a branch's .claude/SPEC.md. Use when the user says "review the spec", "review the plan" (first invocation — plan only), or "resume the spec", "resume the plan", "resume the implementation" (subsequent invocations — execute the next unchecked checklist item and tick it off). Also use when the user says "run the review" (first iteration of the post-implementation review loop, kicks off after all checklist items are ticked) or "resume the review" (subsequent iterations) — orchestrates iterative `codex-review` ↔ `address-review` rounds, gated on user input each iteration. Reads SPEC.md sections 1–3 and 7 to write actionable checklists into sections 4, 5, and optionally 6, then works through them one item at a time.

Build and run tests, then report results. Use after writing or modifying code to verify correctness.