designer/SKILL.md
Analyze UI and UX for usability improvements across web, mobile, and CLI interfaces. Suggest and implement changes to make things easier to use and understand. Use when the user asks to review UI/UX, improve usability, simplify an interface, audit accessibility, or optimize user flows.
npx skillsauth add tim-hub/role-based-skills designerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Evaluate interfaces through the lens of "easy to use, easy to understand". Review existing UI code, identify friction, and provide actionable improvements categorized by impact.
Before reviewing, determine:
Evaluate the interface against these categories (in priority order):
Rate each finding by impact:
| Level | Label | Meaning | |-------|-------|---------| | P0 | Critical | Blocks users or causes serious confusion/errors | | P1 | Moderate | Noticeably hurts usability or breaks conventions | | P2 | Minor | Polish — improves experience but not blocking |
Format findings as:
## UX Review: [Component/Page Name]
### P0 — Critical
- **[Category]**: Description of issue → Suggested fix
### P1 — Moderate
- **[Category]**: Description of issue → Suggested fix
### P2 — Minor
- **[Category]**: Description of issue → Suggested fix
### Summary
[One-line overall assessment and top recommendation]
After reporting, implement the fixes in code — starting from P0 down. Ask the user before making large structural changes.
| Problem | Fix | |---------|-----| | Wall of text | Break into sections with headings; use bullet points | | Too many options at once | Group and collapse; use progressive disclosure | | Mystery icons | Add labels or tooltips | | No loading state | Add skeleton/spinner for async operations | | Generic error "Something went wrong" | Specific message + recovery action | | Tiny click targets | Min 44x44px touch / 24x24px mouse | | No empty state | Add helpful message + primary action when list is empty | | Inconsistent button styles | Establish primary/secondary/destructive hierarchy | | Form with no inline validation | Validate on blur, show errors next to the field | | Long form without progress | Break into steps or add progress indicator |
When justifying recommendations, cite these as needed:
For detailed heuristics, see heuristics.md.
prefers-reduced-motion for animations--help output should be scannable (grouped flags, examples)NO_COLORtesting
Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
development
Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge
data-ai
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
tools
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification