claude-utilities

Investigate the Apollo repository **$ARGUMENTS** and produce a detailed investigation for migration.

Migrate the Apollo repository **$ARGUMENTS** to the new `GraphQLClientProtocol` pattern.

Review the completed migration for **$ARGUMENTS** against the original investigation and produce a detailed report.

Show the current feature flag cleanup progress.

Show the current Apollo removal migration progress.

Use this agent when you need to review Swift/iOS code for quality, best practices, and potential issues. This agent should be invoked: **Proactive Usage Examples:** - After implementing a new feature or component - After refactoring existing code - Before submitting a pull request - After making architectural changes **Example Interactions:** <example> Context: User has just written a new SwiftUI view with view model user: "I've just finished implementing the UserProfileView and its view model. Here's the code:" [code provided] assistant: "Let me use the ios-code-reviewer agent to review this implementation for best practices, potential issues, and improvements." [Uses Task tool to launch ios-code-reviewer agent] </example> <example> Context: User has completed a refactoring of a view controller user: "I've refactored the legacy UIKit view controller to use modern async/await. Can you check if I did it correctly?" assistant: "I'll use the ios-code-reviewer agent to analyze your refactoring for proper async/await usage, memory management, and iOS best practices." [Uses Task tool to launch ios-code-reviewer agent] </example> <example> Context: User mentions completing work on a feature user: "Done with the authentication flow implementation" assistant: "Great! Let me use the ios-code-reviewer agent to review the authentication implementation for security best practices, memory leaks, and code quality." [Uses Task tool to launch ios-code-reviewer agent] </example> <example> Context: User asks for general code review user: "Can you review my recent changes?" assistant: "I'll use the ios-code-reviewer agent to perform a comprehensive review of your recent code changes." [Uses Task tool to launch ios-code-reviewer agent] </example>

Use this agent when the user requests test creation, improvement, or generation for iOS code. Trigger this agent when: - User explicitly asks to "write tests", "create tests", "generate tests", or "add test coverage" - User mentions testing-related keywords: "XCTest", "unit test", "test suite", "test coverage", "mock", "test doubles" - User wants to improve or expand existing tests - User needs help with testing patterns or mocking strategies - After implementing new features or fixing bugs where tests should be added EXAMPLES: <example> Context: User just implemented a new ViewModel method user: "I just added a new method to handle user login in AuthenticationViewModel. Here's the code: [code snippet]" assistant: "Great! Now let me use the ios-test-writer agent to create comprehensive tests for this new login method." <uses Task tool to launch ios-test-writer agent> </example> <example> Context: User explicitly requests test creation user: "Can you write unit tests for the AdViewViewModel class?" assistant: "I'll use the ios-test-writer agent to analyze the AdViewViewModel and create a comprehensive XCTest suite with proper mocking and coverage." <uses Task tool to launch ios-test-writer agent> </example> <example> Context: User mentions improving test coverage user: "Our test coverage is low for the Listing module. Can you help?" assistant: "Let me use the ios-test-writer agent to analyze the Listing module and generate missing tests to improve coverage." <uses Task tool to launch ios-test-writer agent> </example> <example> Context: User asks about mocking dependencies user: "How do I mock the NetworkService in my tests?" assistant: "I'll use the ios-test-writer agent to show you proper mocking patterns and create example tests with mocked dependencies." <uses Task tool to launch ios-test-writer agent> </example>

Use this agent when you need to check and fix Swift code style issues according to SwiftLint rules. Examples: <example> Context: User has just written or modified Swift code and wants to ensure it follows project style guidelines. user: "I just updated the AdViewViewModel.swift file. Can you check if it follows our coding standards?" assistant: "I'll use the swiftlint-fixer agent to check and fix any style issues in that file." <uses Task tool to launch swiftlint-fixer agent> </example> <example> Context: User is preparing code for a pull request and wants to ensure all style issues are resolved. user: "I'm about to create a PR for the Authentication module. Can you make sure all the Swift files are properly formatted?" assistant: "Let me use the swiftlint-fixer agent to check and fix any SwiftLint violations in the Authentication module." <uses Task tool to launch swiftlint-fixer agent> </example> <example> Context: CI/CD pipeline failed due to SwiftLint violations. user: "The build is failing with SwiftLint errors. Can you fix them?" assistant: "I'll use the swiftlint-fixer agent to identify and resolve the SwiftLint violations causing the build failure." <uses Task tool to launch swiftlint-fixer agent> </example> <example> Context: Proactive code quality check after completing a feature. user: "I've finished implementing the new listing detail screen." assistant: "Great! Let me use the swiftlint-fixer agent to ensure the new code follows our style guidelines before we proceed." <uses Task tool to launch swiftlint-fixer agent> </example>

Indexa, busca e sugere docs .md espalhados por ~/Desktop/knowledge/, pelo repo do projeto atual, e pelo dir de memory do Claude. Use quando o usuario perguntar "o que eu tinha doc sobre X?", "tem alguma ideia stale?", ou quando voce (Claude) terminar uma sessao tecnica e quiser sugerir docs relacionados pra atualizar/conectar. Tambem usado pra criar novos docs com frontmatter padronizado nos lugares certos. Aceita subcomandos: stale, drafts, related, suggest, new, index.

Use o executor local rápido (Qwen3.5 35B A3B) para tarefas de baixo risco e baixo custo

Use o executor local inteligente (dots.llm1) para tarefas que exigem reasoning mais forte

Analyze Swift Package Manager dependencies, package plugins, module variants, and CI-oriented build overhead that slow Xcode builds. Use when a developer suspects packages, plugins, or dependency graph shape are hurting clean or incremental build performance, mentions SPM slowness, package resolution time, build plugin overhead, duplicate module builds from configuration drift, circular dependencies between modules, oversized modules needing splitting, or modularization best practices.

Benchmark Xcode clean and incremental builds with repeatable inputs, timing summaries, and timestamped `.build-benchmark/` artifacts. Use when a developer wants a baseline, wants to compare before and after changes, asks to measure build performance, mentions build times, build duration, how long builds take, or wants to know if builds got faster or slower.