skills/ui-ux-design/designing-user-interfaces/SKILL.md
Design, implement, or review screens, components, navigation, workflows, forms, dashboards, and design systems for clear hierarchy, low cognitive load, accessibility, and preserved capability, using Apple-derived philosophy adapted to the target platform. Use especially for visibility, progressive-disclosure, clutter, or over-simplification decisions.
npx skillsauth add narumiruna/agent-skills designing-user-interfacesInstall 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.
Minimize cognitive load without sacrificing capability, agency, context, or recovery. Apply Apple-derived principles through the target platform's conventions; do not copy platform-specific components or metrics blindly.
Identify the primary user, task, context, platform, inputs, constraints, and product conventions from available evidence. Do not invent research, business rules, capabilities, defaults, success claims, or destructive consequences. Preserve behavior, content meaning, data semantics, permissions, persistence, and recovery unless authorized evidence requires a change. Ask one question only when a missing product decision blocks safe work; otherwise leave uncertain behavior unchanged and label the unknown.
| Class | Presentation | | --- | --- | | Primary | Direct, labeled, prominent | | Supporting | Visible with lower emphasis near its object | | Contextual | Revealed for the relevant item, role, state, or step | | Advanced | Labeled progressive disclosure or dedicated view | | Safety/status | Visible at the relevant time; interrupt only when needed | | Redundant/irrelevant | Remove only after proving no capability, cue, status, or recovery path is lost |
Classify by task necessity, audience/frequency evidence, consequence if missed, lifecycle state, and the search, memory, navigation, or recovery cost of hiding it. Never hide location, consequential state, required input, destructive consequences, permission boundaries, unsaved-work risk, error recovery, or the only accessible route to a core action.
Use references/apple-hig.md for deeper HIG-derived or Apple-platform decisions, references/preferences.md for adjustable visual defaults, and references/cases.md for comparable patterns. Product evidence, platform conventions, and accessibility override preferences.
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.