Systematic visual QA sweep of the live metagraphed frontend (apps/ui, served at metagraph.sh) — actually browsing pages at real viewports and looking for defects only visible on inspection (crowding, overflow, truncation, misalignment), not catchable by reading code or trusting a PR's own screenshot table. Produces precise, root-caused GitHub issues a contributor's AI coding agent can act on correctly without needing design judgment of its own. Invoke for "run a visual QA sweep", "find real UI/UX bugs", "check the site for mobile/tablet crowding issues", or any request to audit the live frontend for visual defects. Distinct from the metagraphed skill (which covers writing a contribution) and code-review (which reviews a diff, not live rendered output) — this skill's whole point is that a defect can look completely correct in code and still be visually broken.
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategoryEngineeringStars0
About this skill
Systematic visual QA sweep of the live metagraphed frontend (apps/ui, served at metagraph.sh) — actually browsing pages at real viewports and looking for defects only visible on inspection (crowding, overflow, truncation, misalignment), not catchable by reading code or trusting a PR's own screenshot table. Produces precise, root-caused GitHub issues a contributor's AI coding agent can act on correctly without needing design judgment of its own. Invoke for "run a visual QA sweep", "find real UI/UX bugs", "check the site for mobile/tablet crowding issues", or any request to audit the live frontend for visual defects. Distinct from the metagraphed skill (which covers writing a contribution) and code-review (which reviews a diff, not live rendered output) — this skill's whole point is that a defect can look completely correct in code and still be visually broken.
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.
Systematic visual QA sweep of the live metagraphed frontend (apps/ui, served at metagraph.sh) — actually browsing pages at real viewports and looking for defects only visible on inspection (crowding, overflow, truncation, misalignment), not catchable by reading code or trusting a PR's own screenshot table. Produces precise, root-caused GitHub issues a contributor's AI coding agent can act on correctly without needing design judgment of its own. Invoke for "run a visual QA sweep", "find real UI/UX bugs", "check the site for mobile/tablet crowding issues", or any request to audit the live frontend for visual defects. Distinct from the metagraphed skill (which covers writing a contribution) and code-review (which reviews a diff, not live rendered output) — this skill's whole point is that a defect can look completely correct in code and still be visually broken.
About this listing
Category
Engineering
Reported license
AGPL-3.0
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