Mcgrass-ops
UserA full stack for anyone with an idea to be able to build a fully functioning app.
Categories
Indexed Skills (5)
android-compose-design
Android-specific UI/UX and engineering system for Jetpack Compose apps. Use this skill whenever building, modifying, reviewing, or designing any Android app screen, component, or layout - even if the user doesn't explicitly mention design, Compose, or Material. Routes between five distinct visual styles (m3-expressive-default, dark-product-minimal, playful-warm, data-dense, trust-signaling) based on the app's purpose, then applies an engineering track covering architecture, state, platform integration (edge-to-edge, splash, predictive back, permissions), accessibility, performance, and build defaults. Use this proactively for any Android development work, not just when "design" is named in the prompt.
android-market-research
Market and competitor research for an Android app idea. Use FIRST in the pipeline - before android-product-planning - whenever the user has an app idea, wants to build an app, or asks whether there's a market for something. Fans out web searches across the app's category, names 3-7 real competitor apps with what each does well and where it's weak, mines user-review complaints for unmet needs, surveys monetization norms and the ASO/keyword landscape, and flags market and feasibility risks. Produces a research brief that feeds the planning skill. Trigger proactively on "build me an app", "I have an app idea", "research the market for X", "is there demand for".
android-monetization
Monetization strategy for an Android app. Use AFTER android-product-planning and BEFORE android-compose-design. Takes the planning spec's monetization field and deepens it into a concrete model (free+ads, one-time purchase, freemium subscription, IAP, or B2B/strategic-free), pricing with regional/PPP notes, paywall placement and copy, free-tier scoping, the funnel and activation events to instrument, billing SDK choice (Play Billing, RevenueCat), Play Store subscription compliance, and an experimentation plan. Enforces a replan loop back to planning if the model changes the product. Trigger on "how should this app make money", "add a paywall", "pricing", "monetization", "subscription", or automatically once a planning spec exists.
android-polish
Final polish + ship-readiness gate for a built Android app. Use LAST in the pipeline - after the MCP has written the code and the app builds - to take it from "works" to "passes Google Play review and feels finished." Runs a severity-ordered checklist (P0 ship-blockers first - target-API gate, AAB + Play App Signing, 16 KB page size, themed-icon monochrome layer, release crashes/ANRs; then P1 quality - states, accessibility, performance, tests, static analysis, localization, process-death; then P2 spit-shine) and attaches a concrete verification method (a command, tool, or snapshot) to every item. Pulls store/icon assets from the asset library when one is available, with a manual fallback when it is not. Trigger on "polish my app", "is this ready to ship", "final pass", "prep for release", "store assets", "code cleanup", "make it feel finished".
android-product-planning
Product planning, retention, and Android-platform discovery. Use BEFORE the android-compose-design skill - whenever the user wants to build a new app, add a major feature, or scope a product from a one-sentence prompt. Asks 5-11 questions covering loop, Jobs-to-be-Done, win/lose state, retention targets, primary screen, monetization, activation event, and (conditional) hook and pre-mortem. Detects product, retention, and platform contradictions (viral-vs-accountability, weak Investment phase, monetization mismatched with retention curve, notification timing, missing offline fallback). Surfaces the 11 Android-platform decisions (notifications, permissions, deep links, widgets, offline, form factors, AI cost, Vitals, Material 3 Expressive, Data Safety, ASO) that anchor what the design skill builds. Produces a one-page spec the design skill consumes. Use proactively - most one-sentence prompts hide product incoherence the user hasn't noticed yet.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.