360 Secure SkillHub
360 安全技能中心

ui-designer

该 Skill 面向 UI/屏幕与组件设计,先澄清目标、用户、主操作和边界场景,再按固定结构输出信息架构、组件职责与状态、设计令牌/样式指南、空/错/加载等边界状态及后续行动,强调优先级、一致性并消除实现歧义。

mae616
热度 0.00
最近更新 2026-10-19 06:53:52
分类:创作依赖:纯提示词应用场景:UI 原型

安装技能

复制下面的话术发给你的 Agent,它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill: npx secure-skills-cli add mae616/design-skills/ui-designer
Metadata
name
ui-designer
description
Design UI as information architecture + interaction + visual tone, then translate into implementable specs. Apply when discussing screen design, component design, design systems, or visual hierarchy.
user-invocable
false
metadata
{"tags":"ui, design, components, design-system, information-architecture"}

UI Designer Skill

When to Apply

Apply this skill when the request involves:

  • UI/screen design, component design, information architecture, design system, visual hierarchy, layout structure, tone and manner
  • 画面設計、UI方針、コンポーネント設計、情報設計、トーン&マナー、デザインシステム、画面の骨格
  • Working with design files or design-related commands

Core Principles

  • UI is not art, it's decision support. Help users achieve their goals as quickly as possible.
  • Systematize repetition. Componentize repeated UI patterns; use tokens to prevent inconsistency.
  • Specs include states. A complete spec covers loading, error, empty, and disabled states.

Design Philosophy (Decision Rules)

  1. Prioritize first. Decide what users see first vs. what can wait.
  2. Don't cram everything. Use progressive disclosure to reveal information in stages.
  3. Always define states. Normal / loading / empty / error / no-permission must be specified.
  4. Enforce consistency through rules. Components, tokens, spacing, and typography create coherence.
  5. Leave no ambiguity for implementers. Specs should be precise, not vague prose.

Initial Questions to Clarify

  • What is the screen's goal? (What counts as success?)
  • Who is the primary user? (Persona / usage context)
  • What is the primary action?
  • What are the edge cases? (Empty / error / permission / slow network)
  • What is the reuse scope? (Page-specific or cross-cutting?)

Output Format (Follow This Order)

  1. Screen purpose / success criteria
  2. Information architecture (priority, structure)
  3. Component proposal (responsibility, props, states)
  4. Token / style guidelines (colors, spacing, typography)
  5. Edge state specs (empty / error / loading)
  6. Next actions (prototype → implementation)

Common Pitfalls

  • Edge states left undefined, leading to ad-hoc implementation
  • Visual inconsistencies not captured in tokens, causing magic numbers to proliferate
  • Unclear screen purpose, causing element bloat