Mobile

Consult Google Gemini CLI for second opinions on architecture, debugging, and security audits. Use Gemini's 1M+ context window for comprehensive code analysis. Compare Flash (fast) vs Pro (thorough) vs 3-Pro-Preview (cutting-edge). Use when: need second opinion on architectural decisions, stuck debugging after 2+ attempts, writing security- sensitive code, planning refactors (5+ files), approaching 70%+ context capacity, unfamiliar with tech stack, need peer review, or want Flash vs Pro vs 3-Pro-Preview comparison. Keywords: gemini-cli, google gemini, gemini command line, second opinion, model comparison, gemini-2.5-flash, gemini-2.5-pro, gemini-3-pro-preview, architectural decisions, debugging assistant, code review gemini, security audit gemini, 1M context window, AI pair programming, gemini consultation, flash vs pro, AI-to-AI prompting, peer review, codebase analysis, gemini CLI tool, shell gemini, command line AI assistant, gemini architecture advice, gemini debug help, gemini security scan, gemini code compare

Critically reviews specifications, generates clarifying questions and improvement suggestions, and applies refinements based on user feedback

Flight Levels methodology for project and work management. Use when planning projects, decomposing work into tasks, deciding document types, managing phases, or coordinating initiatives. Applies Kanban-based pull systems and hierarchical work alignment (Vision -> Strategy -> Initiative -> Task). Teaches when and why to use Metis tools.

Plan work before coding: do repo research, analyze options/risks, and ask clarifying questions before proposing an implementation plan. Use when the user asks for a plan, design/approach, scope breakdown, or implementation steps.

Token-efficient codebase exploration using MCP-first approach. Locates functions, classes, patterns, and traces dependencies with 80-90% token savings. Use when searching code, finding implementations, or tracing call chains.

Manage Glide app access, privacy, authentication, and publishing. Use when configuring who can access an app, setting up sign-in methods, publishing apps, inviting users, or configuring Row Owners for data security.

Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation with Shannon quantitative validation by testing with subagents before writing, iterating until bulletproof against rationalization

Natural language wrapper for testing commands - automatically triggers /testing:run when users request test execution

Master OPAL window functions for row-relative calculations, rankings, and moving aggregates. Covers lag(), lead(), row_number(), rank(), dense_rank(), moving averages, first(), and last(). Use when comparing rows to neighbors, ranking within partitions, calculating rate of change, or computing time-based moving windows. CRITICAL - OPAL uses window() function wrapper, NOT SQL OVER clause.

Provides Android coding patterns for Kotlin 2.0 and Jetpack Compose projects. Includes MVI architecture, Clean Architecture layers, Compose best practices, and Coroutines/Flow patterns. Use when writing Android code, implementing features, reviewing code, or learning patterns. Use when user mentions: MVI 패턴, 클린 아키텍처, 컴포즈 패턴, 코루틴, Flow, 상태 관리, 아키텍처, ViewModel 패턴, 레이어 구조, 패턴 설명.

Validate completed implementation against plan tasks and acceptance criteria. Sixth phase of research-discussion-specification-plan-implement-review workflow. Use when: (1) Implementation phase is complete, (2) User wants validation before merging/shipping, (3) Quality gate check needed after implementation. Reviews ALL plan tasks for implementation correctness, test adequacy, and code quality. Produces structured feedback (approve, request changes, or comments) - does NOT fix code.

Apply London (mock-based) and Chicago (state-based) TDD schools. Use when practicing test-driven development or choosing testing style for your context.

Use this skill AFTER a terraform plan has been generated. This skill audits a terraform plan file for security vulnerabilities (using tfsec/checkov) and company compliance policies. It either APPROVES or REJECTS the plan.

Generate and compare multiple architecture options (minimal, moderate, full modernization) with comprehensive trade-offs analysis across cost, timeline, risk, performance, and maintainability dimensions. Use when evaluating multiple architectural approaches or deciding between modernization strategies with different cost/risk trade-offs.

This skill should be used after productive sessions to extract learnings and route them to appropriate Reusable Intelligence Infrastructure (RII) components. Use when corrections were made, format drift was fixed, new patterns emerged, or the user explicitly asks to "harvest learnings" or "capture session intelligence". Transforms one-time fixes into permanent organizational knowledge by implementing updates across multiple files.

Follow data movement through specific execution paths tracking transformations, state changes, and control decisions to verify runtime behavior. Use when: (1) claims about runtime behavior are based on static reading without tracing actual execution, (2) debugging specific input cases where knowing what happens with particular data differs from general code structure understanding, (3) code that looks simple has non-obvious runtime behavior due to side effects, closure captures, or async timing, (4) multiple transformation paths or conditional branches make mental simulation likely incomplete.

Generate test file scaffolds from source analysis with language-appropriate templates.

1600+ lines of performance optimization mastery - profiling, rendering, memory, network, battery, APK size with production-ready code examples.

Generate QR codes with URLs and UTM tracking. Exports PNG/SVG with captions. Use for single codes, batch generation, or marketing campaigns with tracking parameters.

Write Kotlin code for Android following best practices. Use when developing with Jetpack Compose, Android SDK, or Kotlin projects. Covers coroutines, state management, and tooling.