MockDonalds

Convert acceptance criteria, Jira tickets, Gherkin scenarios, PRDs, or any product requirements into a structured spec template. Use when translating PM artifacts into actionable specs for add-*, update, migrate, or remove skills.

Scaffold a complete new feature module with all 6 submodules, source files, tests, fakes, and AGENTS.md. Use when adding an entirely new feature to the app.

Execute cross-cutting migrations — library swaps, pattern changes, API version upgrades, or architecture refactors. Handles phased rollout, coexistence, and rollback planning.

Reverse-engineer a spec from existing code — reconstructs presumed acceptance criteria, data flow, API contracts, UI states, and business rules by reading source, tests, and git history. Use when inheriting undocumented features, onboarding onto unfamiliar code, or preparing for a refactor.

Modify existing feature code across all affected layers — domain models, data, presentation, tests, and fakes. Use when changing behavior, adding fields, or enhancing existing features.

Verification pipeline with three scopes — diff (default, changed modules only), full (whole project lint + unit + arch + builds), and all (every test level + every variant + full assemble). Use after any code change.

Add, run, and analyze macrobenchmarks — Android Macrobenchmark (Perfetto) and iOS XCTest performance metrics. Scoped to authored, repeatable performance measurements against production-representative builds. Use when startup, scroll, or frame-timing regressions need regression-gated coverage.

Run the full test pipeline (lint + all 5 test levels on both platforms). Mirrors the CI pipeline in verification.md minus the final `./gradlew assemble` step. Device/simulator/emulator required for steps 4+.

Run Android and iOS end-to-end journey tests. Android uses `:testing:e2e-tests` against the debug target with UI Automator. iOS uses the E2ETests test plan via xcodebuild. Requires a connected device/emulator (Android) or simulator (iOS). Use after modifying navigation, deep links, auth gating, or full-flow behavior.

Run Android and iOS UI tests for a specific feature. Requires a connected device/emulator (Android) or simulator (iOS). Use after modifying UI code.

Run pure-logic unit tests — Kotlin (Kotest on JVM host) and Swift (Swift Testing in iosAppTests/Unit/). Use to validate non-UI logic changes. For iOS view tests, use run-ui-tests instead.

Scaffold a new core module with api/impl split, optional test module, source files, and AGENTS.md. Use when adding shared infrastructure to the app.

Add a feature flag to gate behavior — flag definition, presenter observation, and domain/data checks. Use when adding runtime toggles for features or experiments. Production binding is Harness (iOS via Swift bridge, Android via direct SDK).

Scaffold a new market across both platforms — 3 .properties files in core/build-config/markets/{market}/, a new AGP market flavor in androidApp/build.gradle.kts, a single regex extension in build-logic/convention/.../BuildVariantResolver.kt, 6 xcconfigs in iosApp/Configuration/{market}/, YAML edits to iosApp/project.yml for 30 new target-config bindings, xcodegen regeneration, and cross-platform smoke builds. Use when launching the app in a new country/region or adding a synthetic sandbox market.

Interview the user one question at a time to resolve every unfilled marker in a spec file (`<!-- TODO -->`, empty `- [ ]` AC items, missing required fields, raw template placeholders, unconfirmed reverse-spec presumptions). Use on hand-authored specs, stale specs, or when the user explicitly says "grill me" or "stress-test this plan". The conversion skills (`/ac-to-spec`, `/reverse-spec`) embed this same logic inline, so freshly-converted specs do not need a separate grill pass. Walks the decision tree branch-by-branch, recommends an answer for each question, explores the codebase instead of asking when it can, and writes resolved answers back into the spec with a Decisions log appended.

Publish project markdown docs as derived Obsidian-style notes organized into a Confluence-style nested taxonomy (Home / Orientation / Standards / Modules / Skills & Tooling) with wikilinks and auto-generated index notes. Walks the current working directory, detects known doc conventions (AGENTS.md, CLAUDE.md, .agents/, docs/, README.md, ARCHITECTURE.md, CONTRIBUTING.md), and writes per-file derived notes (condensed / expanded / reframed depending on source type) to a configured Obsidian vault path. Idempotent via content-hash manifest — only re-derives changed sources on re-run. Use when you want a navigable Obsidian knowledge base for a project, or to refresh an existing vault after docs change. Personal-machine skill — vault path is configured locally.

Add analytics event tracking to a feature — event definitions, presenter wiring, and domain/data dispatch. Use when adding user behavior tracking. NOTE: core:analytics exists with AnalyticsEvent interface, TrackAnalyticsEvent interactor, and LoggingAnalyticsDispatcher — production SDK integration is not yet finalized.

Add a new API endpoint to a feature — data source interface, implementation, DTO, mapper, and HttpClient config. Use when connecting a feature to a backend service. NOTE: core:network infrastructure exists but not all features have real API integrations yet — this skill scaffolds the wiring; actual endpoint details depend on backend readiness.

Add observability instrumentation to a feature — logging, performance markers, health checks, and crash context. Use when adding production monitoring to a feature. NOTE: core:monitoring module is planned but not yet implemented — this skill documents the target patterns and scaffolds what's possible today.

Add a new repository with interface, implementation, and test. Use when adding a new data source to a feature.

Add a new screen to an existing feature module. Creates Screen object, TestTags, Presenter, UiState, Events, Ui composable, and full test suite (9+ files).

Add a new use case interactor with abstraction, implementation, fake, and test. Use when adding new business logic to a feature.

Clean removal of features, screens, use cases, repositories, or other code across all layers. Handles dependency analysis, file deletion, reference cleanup, and test updates.

Add a new field to core:build-config — updates Defaults.properties, every markets/*.properties, the AppBuildConfig facade, and the Phase 1 smoke test. Use when adding compile-time market/env configuration (NOT runtime feature flags — those go to Harness).

Combined unit + UI test gap-filling for all changed code. Analyzes the branch diff and creates missing tests for domain logic, data access, presenters, and UI screens.

Identify and fill unit test gaps for changed code by analyzing the branch diff. Creates test files following Kotest BehaviorSpec patterns with fakes.

Parse every core/build-config/impl/markets/*.properties against Defaults.properties and enforce build-config invariants (required keys, no unknown keys, format rules for market/env/locale/currency/URLs). Gradle task on :core:build-config:impl — sub-second warm, configuration-cache compatible. Run before any market-scoped build and as part of `verify`.

Identify and fill UI test gaps for changed screens by analyzing the branch diff. Creates UiTest, UiRobot, and StateRobot following the Robot pattern.

Surface unused Kotlin declarations (imports, private members, parameters) across ALL source sets via full Detekt, plus targeted greps for dead TestTags, Screen objects with no navigation, and Fake classes with no test references. Reports findings — does not auto-delete. Run periodically to stop dead code accumulating.

Fast pre-commit lint check — runs Detekt on commonMain Kotlin and SwiftLint on changed Swift files only. Targets the ~5s inner loop you run 20× a day. For thorough diff-scoped verification (lint + unit + architecture), use verify.

Generate a structured overview of the project, a feature, or a core module. Supports android/ios scope for platform-specific focus. Use for onboarding, context-switching, or reviewing unfamiliar code.

Review code changes against the default branch, checking architecture rules, naming conventions, test coverage, and forbidden patterns. Use before merging or to validate work.

Run Konsist architecture tests and Harmonize iOS architecture tests. Use to verify code follows project conventions after structural changes.