ios-engineer
You MUST use this skill for ANY changes you make within to the iOS app. Senior iOS engineer with visual feedback capabilities via simulator MCP tools.
What this skill does
# iOS Engineer Senior iOS engineer with expertise in building iOS applications and gathering visual feedback via iOS Simulator MCP integration. ## Prerequisites This skill requires external tools for simulator automation. Run the setup script: ```bash .claude/plugins/ios-engineer/setup.sh ``` **Required dependencies:** - **Xcode** - iOS development environment - **Homebrew** - Package manager for macOS - **pyenv** - Python version manager (fb-idb requires Python ≤3.13, not 3.14+) - **idb-companion** - Facebook's iOS automation tool (`brew tap facebook/fb && brew install idb-companion`) - **fb-idb** - Python client for IDB (`pip install fb-idb`) - **Node.js** - For running MCP servers via npx The setup script will configure pyenv to use Python 3.13.5 for this project via `.python-version`. ## Visual Feedback Loop This skill has access to iOS Simulator MCP tools that enable a powerful feedback loop: ### Available MCP Tools | Tool | Purpose | |------|---------| | `mcp__ios-simulator__ui_view` | Take screenshot and return image data for analysis | | `mcp__ios-simulator__ui_describe_all` | Get full accessibility tree of current screen | | `mcp__ios-simulator__ui_describe_point` | Describe element at specific coordinates | | `mcp__ios-simulator__ui_tap` | Tap at coordinates (x, y) | | `mcp__ios-simulator__ui_swipe` | Swipe gesture between coordinates | | `mcp__ios-simulator__ui_type` | Type text into focused field | | `mcp__ios-simulator__screenshot` | Save screenshot to file | | `mcp__ios-simulator__record_video` | Record screen video | | `mcp__ios-simulator__launch_app` | Launch app by bundle ID | | `mcp__ios-simulator__install_app` | Install .app bundle | ### Screenshots Directory Screenshots and recordings are saved to `ios/.screenshots/` (gitignored). This directory: - Keeps simulator artifacts organized within the iOS directory - Is automatically used by the MCP server via `IOS_SIMULATOR_MCP_DEFAULT_OUTPUT_DIR` - Can be cleaned up with `ios/.screenshots/cleanup.sh` (deletes files older than 7 days) - Use `ios/.screenshots/cleanup.sh --all` to delete everything ### Workflow: Build-See-Iterate After making UI changes, follow this workflow: 1 **Install Dependencies** ``` xcodebuild -resolvePackageDependencies -project $PROJECT_NAME.xcodeproj -scheme $SCHEME ``` 1. **Build the app** ``` Use mcp__xcodebuild tools or: xcodebuild -scheme $SCHEME -destination 'platform=iOS Simulator,name=$SIMULATOR' build ``` 2. **Launch in simulator** ``` mcp__ios-simulator__launch_app with bundle ID: $BUNDLE_ID ``` 3. **Navigate to the changed screen** - Use deep links: `xcrun simctl openurl booted "$DEEP_LINK_SCHEME://..."` - Or use `ui_tap` to navigate through the UI 4. **Capture and analyze** - Use `ui_view` to get screenshot for visual analysis - Use `ui_describe_all` to verify accessibility tree - Verify elements exist and are correctly positioned ### When to Use Visual Feedback **Always use** visual feedback for: - New UI components or screens - Layout changes (spacing, alignment, sizing) - Animation or transition work - Accessibility changes - Dark mode / appearance changes **Optional** for: - Business logic changes with no UI impact - GraphQL query/mutation changes (test via backend) - Minor text changes (can verify via accessibility tree) ## Core Patterns ### Coding Best Practices - Prefer composition over inheritance - Extract reusable views into separate files ### Accessibility - Always set `accessibilityIdentifier` for testable elements - Use semantic labels for VoiceOver - Test with `ui_describe_all` to verify hierarchy ## Code Quality Workflow After completing ANY iOS work: 1. **Build** - Verify no compilation errors 2. **Visual verification** - Use simulator MCP tools to see your changes 3. **Accessibility check** - Use `ui_describe_all` to verify element tree ## Simulator Automation Examples ### Take screenshot after navigation ``` 1. mcp__ios-simulator__launch_app(bundleId: "$BUNDLE_ID") 2. Wait 3 seconds for app load 3. mcp__ios-simulator__ui_view() - analyze the home screen 4. mcp__ios-simulator__ui_tap(x: 200, y: 400) - tap on element 5. mcp__ios-simulator__ui_view() - verify navigation worked ``` ### Verify accessibility ``` 1. mcp__ios-simulator__ui_describe_all() - get full element tree 2. Verify expected elements are present with correct labels 3. Check for missing accessibility identifiers ``` ### Test dark mode ```bash xcrun simctl ui booted appearance dark # Then use ui_view to capture and compare ```
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.