com um clique
MobiAI-Core
MobiAI-Core contém 45 skills coletadas de ArisGuimera, com cobertura ocupacional por repositório e páginas de detalhe dentro do site.
Skills neste repositório
first community fixture skill
second community fixture skill
third community fixture skill
Actualiza el binario `mobiai` a la última versión publicada en GitHub Releases. Usá esta skill cuando el banner de SessionStart muestre "MobiAI update available" o cuando el usuario pida explícitamente actualizar MobiAI.
Use when starting any conversation — establishes how to find and invoke MobiAI skills, requiring `Skill` tool invocation before ANY response including clarifying questions, git/file reads, or code exploration
test fixture
test fixture
test fixture
test fixture
test fixture
Upgrades, or migrates, an Android project to use Android Gradle Plugin (AGP) version 9. Do not use this skill for migrating Kotlin Multiplatform (KMP) projects.
Provides a structured workflow for migrating an Android XML View to Jetpack Compose. This skill details the step-by-step process, from planning and dependency setup, to theming and layout migration, validation and XML cleanup. Use this skill when you need to migrate an XML View to Jetpack Compose in an Android project. It solves the problem of converting the UI of a legacy XML View into modern, declarative Compose components while maintaining interoperability.
Learn how to install and migrate to Jetpack Navigation 3, and how to implement features and patterns such as deep links, multiple backstacks, scenes (dialogs, bottom sheets, list-detail, two-pane, supporting pane), conditional navigation (such as logged-in navigation vs anonymous), returning results from flows, integration with Hilt, ViewModel, Kotlin, and view interoperability.
Use this skill when upgrading or migrating an Android project from any legacy Google Play Billing Library (PBL) version to the latest stable version of PBL.
Use when creating features, refactoring, or navigating an Android codebase — understand project structure, find where to make changes, follow existing patterns.
Use when building an Android project, configuring flavors or variants, troubleshooting build failures, or managing Gradle dependencies.
Use when interacting with an Android device or emulator — run adb commands, automate UI, capture screenshots, read logcat, manage emulators.
Use when writing or running tests in an Android project — unit tests, UI tests, choosing the right framework and patterns.
Use when the user shares a crash from any source (stack trace, log, screenshot, error description) and wants to find the root cause and fix it.
Use when the user asks about past decisions, workarounds, bugfixes, testing patterns or integrations specific to *this* project, OR before proposing non-trivial architecture/integration changes. MobiAI Brain is per-project living memory at <repo>/.mobiai/brain/. Loads context the user already captured so suggestions respect real project conventions instead of generic best practices.
Use when the user shares a Firebase Crashlytics crash link, crash ID, or asks to investigate a Crashlytics issue in depth.
YOU MUST use this before ANY git push, branch push to remote, merge, or PR creation — regardless of phrasing or language. Covers all irreversible integration actions (committing, pushing, opening a PR, shipping finished work). Also triggers proactively after a fix when the user signals completion (still ask before pushing). Works with any git hosting provider.
You MUST use this before starting any bug fix from a ticket or issue, OR when re-opening a ticket whose previous fix attempt didn't work (user shares a commit SHA and says 'no anda' / 'didn't fix it' / 'still broken'). Fetch, understand, investigate root cause, apply the fix with tests, and verify. For small line-level fixes, runs autonomously end-to-end and gates only before push. For complex changes, gates at each phase boundary.
Use when the user asks about code impact, call graph, callers/callees, semantic exploration of the mobile codebase, or 'where is X used'. Routes the agent to query MobiAI Graph (mobiai graph search/callers/context) instead of grep/read. Pre-flight checks that .mobiai/graph/index.json exists; if not, suggests `mobiai graph init` without running it.
You MUST use this before any creative mobile work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
You MUST use this before proposing any fix for a mobile bug, test failure, crash, or unexpected behavior — AND when re-investigating a bug whose previous fix didn't work (user shares a commit SHA and questions whether it resolves the bug). Walks root-cause analysis as phased evidence gathering. For small fixes with clear evidence, runs autonomously and returns the root cause to the caller. For complex or uncertain cases, gates at known-vs-assumed and root-cause steps.
ALWAYS invoke this when a written mobile implementation plan exists and you are about to carry it out in a fresh session. Load and critique the plan before executing any task from it.
ALWAYS invoke this when executing a mobile implementation plan in the current session with subagent support available. Drives fresh-subagent-per-task execution with mandatory two-stage review; do not hand-execute plan tasks in-session when this workflow applies.
You MUST use this once mobile implementation is finished and you are about to integrate the work — merging, pushing, opening a PR, or cleaning up the branch. Do not improvise the wrap-up; this skill gates verification, presents integration options, and handles cleanup.
ALWAYS invoke this before dispatching agents for two or more independent mobile problems (unrelated failures, separate subsystems, disjoint investigations). Do not spawn parallel agents ad hoc — this skill defines how to isolate their context and scope.
You MUST use this whenever a mobile task spans multiple steps, files, or subsystems — before touching code. Produce a written plan the user approves; do not improvise multi-step work from memory.
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.
You MUST use this before declaring any mobile work done, fixed, green, or ready — and before committing, pushing, or opening a PR. No completion claim may be made without fresh verification evidence from this session.
You MUST use this before starting mobile work that needs isolation from the current workspace — new feature branches, parallel efforts, or any plan execution that should not contaminate the active tree. Do not create worktrees ad hoc; this skill enforces safe directory selection and verification.
Use when the user wants to reproduce a bug on a mobile device, emulator, or simulator using UI automation.
Use when reviewing mobile code changes — check for lifecycle issues, memory leaks, thread safety, and platform-specific pitfalls.
Use when the user asks to write tests for mobile code, or after applying a fix that needs regression tests.
Guide the user through creating a new MobiAI skill — generate SKILL.md with proper structure, frontmatter, and actionable instructions.
Use when working on a Flutter or Dart project — building, testing, debugging, understanding state management and project structure.
Use when creating features, refactoring, or navigating an iOS codebase — understand project structure, find where to make changes, follow existing patterns.