skills/ui-ux-design/designing-user-experiences/SKILL.md
Design or redesign end-to-end user experiences for new or existing digital products through an approval-gated workflow. Use for substantial work on user goals, information architecture, navigation, workflows, system states, or interaction behavior that requires a proposal before implementation.
npx skillsauth add narumiruna/agent-skills designing-user-experiencesInstall 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.
Ground the experience in the product's actual users, workflows, platform, design system, and constraints. Do not transplant another product's labels, visual patterns, or information architecture. Treat unsupported claims about users, frequency, risk, or platform behavior as assumptions rather than facts.
Choose the applicable context, then gather enough evidence to support the proposal.
Label assumptions, unknowns, and product decisions that require confirmation. For existing products, preserve current behavior where evidence is incomplete.
Organize the experience around user goals rather than internal settings or data structures. Prioritize a small set of frequent and important actions while applying these constraints. Treat primary, secondary, advanced, destructive, and similar classifications as analysis and prioritization inputs, not as required sections, menus, pages, or navigation levels.
Present:
Do not edit product files, tests, stored data, or user-facing documentation during this proposal phase. Wait for explicit approval of the proposal before implementation; requested revisions update the proposal and do not imply approval.
Implement only the approved scope and preserve unrelated behavior.
Exercise the affected loading, empty, success, error, disabled, and partial states. Report what changed, validation evidence, approved deviations, and any scenarios that could not be verified; for existing products, also report preserved compatibility.
development
Score or compare one or more agent skills across trigger clarity, workflow actionability, safety boundaries, verification rigor, incremental knowledge value, and leanness. Use only when the user explicitly asks for ratings, numerical quality scores, rubric-based scorecards, or scored comparisons; use creating-agent-skills for unscored reviews or revisions.
development
Assess or improve an existing codebase's architecture when the user asks about module boundaries, coupling, scattered ownership, testability, change locality, deep modules, seams, or behavior-preserving structural refactoring. Use for cross-module design rather than ordinary diff review or a confirmed edge-case bug fix.
development
Perform read-only security audits, vulnerability assessments, or threat-focused reviews of diffs, pull requests, code paths, or explicitly scoped repositories when security is the primary objective or acceptance criterion. Use reviewing-code for ordinary review with baseline security coverage and hardening-code-paths for fixing confirmed findings.
development
Run iterative multi-reviewer panels over a code diff, verify their findings, apply explicitly authorized fixes, and re-review the updated change until it passes or reaches a stopping condition. Use when the user asks for a panel loop, multi-model code-review consensus, or a review-fix-re-review cycle.