mobile-browser-workflow-executor
Mobile Browser Workflow Executor
This skill executes mobile browser workflows defined in /workflows/mobile-browser-workflows.md using Playwright MCP as the primary engine, with Claude-in-Chrome as an optional alternative. It emulates a mobile viewport (393x852 - iPhone 14 Pro dimensions), validates workflows step-by-step, audits for iOS Human Interface Guidelines (HIG) anti-patterns, captures visual evidence with device frame mockups, and generates comprehensive reports.
Execution Modes
- Audit Mode (Default): Execute workflows, capture findings, generate reports. Does not modify code.
- Fix Mode: Execute audit, then automatically remediate identified issues with user approval.
Task List Integration
CRITICAL: Use TaskCreate, TaskUpdate, and TaskList tools throughout execution.
| Task | Purpose |
|---|---|
| Master task | mobile-browser-workflow-execution - tracks overall session |
| Per-workflow tasks | One task per workflow with step progress |
| Agent tasks | UX evaluation, fix agents, verification, report generation |
More from neonwatty/claude-skills
think-through
A Socratic interview skill for thinking through technical ideas like apps, products, tools, and projects. Use this when the user says "think through [idea]", "help me think about [app/product]", "let's explore [project idea]", or wants to iterate on a technical concept before building. Asks probing questions about the problem, target users, market, technical approach, tradeoffs, and viability. Continues until the idea is well-explored, then produces a written summary and proposes directions.
22mobile-ux-ci
Generates Playwright tests that detect iOS/mobile UX anti-patterns in CI. Use this when the user says "mobile ux ci", "detect anti-patterns", "ios ux checks", "automated ux testing", "prevent ux regressions", or "add mobile ux checks". Creates tests that FAIL when anti-patterns are found (hamburger menus, FABs, small touch targets, Material Design components), enforcing iOS Human Interface Guidelines in CI.
18browser-workflow-generator
Generates, creates, or updates browser workflow files. Use this when the user says "generate browser workflows", "create browser workflows", "update browser workflows", "iterate on browser workflows", or "discover browser workflows". Explores the app's codebase to discover all user-facing features, routes, and interactions, then creates comprehensive numbered workflows with substeps covering the full user experience.
18ios-workflow-executor
Executes web app workflows in Safari on the iOS Simulator from /workflows/ios-workflows.md. Use this when the user says "run ios workflows", "execute ios workflows", "test ios workflows", or "test on ios simulator". Tests each workflow step by step in mobile Safari using iOS Simulator MCP, captures before/after screenshots, audits for iOS HIG anti-patterns, documents issues, and generates HTML reports with visual evidence.
17pr-creator
Creates a pull request from current changes, monitors GitHub CI, and debugs any failures until CI passes. Use this when the user says "create pr", "make a pr", "open pull request", "submit pr", or "pr for these changes". Does NOT merge - stops when CI passes and provides the PR link.
15feature-interview
Deeply interviews the user about a feature idea before implementation. Use this when the user says "interview me about [feature]", "I want to create a new feature", "let's create a new feature", "new feature", "plan a feature", or describes a feature they want to build. Asks probing, non-obvious questions about technical implementation, UI/UX decisions, edge cases, concerns, tradeoffs, and constraints. Continues interviewing until the feature is fully understood, then writes a detailed implementation plan.
15