Audit live UI to detect visual inconsistencies and fix them atomically.
npx skills add https://github.com/lyh2/gstack-deepseek --skill design-review-lyh2
Please help me install this Agent Skill. Skill: design-review Source: https://github.com/lyh2/gstack-deepseek/tree/main/design-review Command: npx skills add https://github.com/lyh2/gstack-deepseek --skill design-review-lyh2
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use /plan-design-review. Use when asked to "audit the design", "visual QA", "check if it looks good", or "design polish". Proactively suggest when the user mentions visual inconsistencies or wants to polish the look of a live site.
Describe the target site and run the design-review workflow to start a visual QA pass.
High-intent search queries and answers about installing and using this skill.
Visual QA audits live UI across sites to detect visual inconsistencies, spacing issues, hierarchy problems, and AI slop. You describe the target site and run the design-review workflow to start a visual QA pass that iteratively fixes issues in source code.
Plan-mode design review supports pre-implementation audits and proactive design polish suggestions. Use the /plan-design-review workflow to audit designs before writing code, ensuring visual hierarchy and spacing issues are caught early.
Fixing AI slop and spacing issues requires iteratively correcting source code and committing each fix atomically. The process re-verifies changes with before and after screenshots to ensure traceability and confirm the visual inconsistency is resolved.
Yes, design review applies to live frontend sites to detect inconsistencies in typography, hierarchy, and interaction latency. It audits the rendered UI directly, so it works with any design system as long as the site is accessible.
Automated visual QA is not suited for purely aesthetic or subjective design explorations. It focuses on detecting specific visual inconsistencies, spacing problems, hierarchy issues, and slow interactions rather than evaluating creative design direction.
Before and after verification works by capturing screenshots before a fix is applied and after the source code change is committed atomically. This ensures each visual inconsistency fix is traceable and confirmed visually before moving to the next issue.
Ronin15Compare SDL3 HammerEngine metrics against baselines to flag performance regressions.
CarbeneAIDetect visual QA issues in live UI and document atomic fixes.
robertzengcnAudit UI visual consistency and fix spacing, hierarchy, and interaction issues.
romiluz13Design UI layouts with visual hierarchy, spacing, color, and state design.
