DrSmile444
User👁️ Evidence-driven UX review skills for AI coding agents (Claude Code, Codex) — usability, psychology, accessibility, product, and trust, graded by evidence and severity instead of an opaque score.
Categories
Indexed Skills (19)
openspec-apply-change
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
openspec-propose
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
openspec-sync-specs
Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.
openspec-update-change
Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Never edits code.
openspec-verify-change
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
psychology
Use when the user wants analysis of attention, cognitive load, motivation, emotion, behavioral economics (defaults, anchoring, loss aversion, scarcity, urgency), social proof, habit formation, or persuasive/dark-pattern ethics in a UI or feature — including questions like "is this manipulative" or "why would this motivate users". Not for general task-flow/navigation review (use `usability`) or accessibility (use `accessibility`).
review
Use when the user asks for a broad, comprehensive, general, or end-to-end UX review of a feature, screen, flow, app, or implementation — across multiple dimensions (usability, accessibility, psychology, product, trust) rather than one specific angle. If the request already narrows to one angle (e.g. "check accessibility", "is this manipulative"), prefer the matching domain skill instead.
trust
Use when the user wants review of permission-request timing, onboarding necessity, destructive-action safety (undo vs. confirmation), notification honesty, or other trust/safety signals in a flow. Not for general task-flow review (use `usability`) or persuasive-mechanism ethics unrelated to trust/permissions (use `psychology`).
usability
Use when the user wants to review task flow, interaction friction/efficiency, navigation, forms, system status/feedback, or error handling in a UI or feature — not a full multi-lens review, and not primarily an accessibility, psychology, product-goal, or trust/permissions concern (use the matching sibling skill for those instead).
ux-crux-psychology
Use when the user wants analysis of attention, cognitive load, motivation, emotion, behavioral economics (defaults, anchoring, loss aversion, scarcity, urgency), social proof, habit formation, or persuasive/dark-pattern ethics in a UI or feature — including questions like "is this manipulative" or "why would this motivate users". Not for general task-flow/navigation review (use `usability`) or accessibility (use `accessibility`).
ux-crux-review
Use when the user asks for a broad, comprehensive, general, or end-to-end UX review of a feature, screen, flow, app, or implementation — across multiple dimensions (usability, accessibility, psychology, product, trust) rather than one specific angle. If the request already narrows to one angle (e.g. "check accessibility", "is this manipulative"), prefer the matching domain skill instead.
ux-crux-trust
Use when the user wants review of permission-request timing, onboarding necessity, destructive-action safety (undo vs. confirmation), notification honesty, or other trust/safety signals in a flow. Not for general task-flow review (use `usability`) or persuasive-mechanism ethics unrelated to trust/permissions (use `psychology`).
ux-crux-usability
Use when the user wants to review task flow, interaction friction/efficiency, navigation, forms, system status/feedback, or error handling in a UI or feature — not a full multi-lens review, and not primarily an accessibility, psychology, product-goal, or trust/permissions concern (use the matching sibling skill for those instead).
accessibility
Use when accessibility, WCAG conformance, screen readers (VoiceOver/TalkBack), keyboard/switch access, color contrast, touch target size, text scaling, or gesture alternatives are the primary concern. Not for general task-flow review (use `usability`) or persuasive-mechanism ethics (use `psychology`).
product
Use when the user wants review of a screen or flow's primary goal clarity, information hierarchy, content/UX writing, or whether onboarding/registration is justified before value is shown — whether the design serves user intent vs. internal product structure. Not for interaction mechanics (use `usability`) or persuasive-mechanism ethics (use `psychology`).
ux-crux-accessibility
Use when accessibility, WCAG conformance, screen readers (VoiceOver/TalkBack), keyboard/switch access, color contrast, touch target size, text scaling, or gesture alternatives are the primary concern. Not for general task-flow review (use `usability`) or persuasive-mechanism ethics (use `psychology`).
ux-crux-product
Use when the user wants review of a screen or flow's primary goal clarity, information hierarchy, content/UX writing, or whether onboarding/registration is justified before value is shown — whether the design serves user intent vs. internal product structure. Not for interaction mechanics (use `usability`) or persuasive-mechanism ethics (use `psychology`).
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.