Close the PDCA loop on the work you just did. After implementing changes, drive the LIVE app on localhost through the Playwright browser MCP like a real end user — manually, not programmatically — exercising every page, component, and flow the current session touched. Reproduce real user journeys, hunt for pain points, and FIX them as you go (full-stack: UI/UX + backend + DB), using already-enabled MCP servers (Sentry for production errors, Supabase for schema/logs/data, Firecrawl for research). Red-team your own work, give brutally honest critique, and suggest feature/UX improvements. Generic across any repo and stack. Use after building or changing a feature, or when the user says "test this with playwright", "test my changes", "test on localhost like a user", "PDCA this", "did you actually test it", "red-team this feature", or "verify the work end-to-end".
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategoryEngineeringStars0
About this skill
Close the PDCA loop on the work you just did. After implementing changes, drive the LIVE app on localhost through the Playwright browser MCP like a real end user — manually, not programmatically — exercising every page, component, and flow the current session touched. Reproduce real user journeys, hunt for pain points, and FIX them as you go (full-stack: UI/UX + backend + DB), using already-enabled MCP servers (Sentry for production errors, Supabase for schema/logs/data, Firecrawl for research). Red-team your own work, give brutally honest critique, and suggest feature/UX improvements. Generic across any repo and stack. Use after building or changing a feature, or when the user says "test this with playwright", "test my changes", "test on localhost like a user", "PDCA this", "did you actually test it", "red-team this feature", or "verify the work end-to-end".
Quick start
Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Close the PDCA loop on the work you just did. After implementing changes, drive the LIVE app on localhost through the Playwright browser MCP like a real end user — manually, not programmatically — exercising every page, component, and flow the current session touched. Reproduce real user journeys, hunt for pain points, and FIX them as you go (full-stack: UI/UX + backend + DB), using already-enabled MCP servers (Sentry for production errors, Supabase for schema/logs/data, Firecrawl for research). Red-team your own work, give brutally honest critique, and suggest feature/UX improvements. Generic across any repo and stack. Use after building or changing a feature, or when the user says "test this with playwright", "test my changes", "test on localhost like a user", "PDCA this", "did you actually test it", "red-team this feature", or "verify the work end-to-end".
About this listing
Category
Engineering
Reported license
MIT
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLI