← 返回
AI智能

UI Audit

AI skill for automated UI audits. Evaluate interfaces against proven UX principles for visual hierarchy, accessibility, cognitive load, navigation, and more. Based on Making UX Decisions by Tommy Geoco.
自动化UI审计AI技能。基于Tommy Geoco的《Making UX Decisions》,根据成熟的UX原则评估界面的视觉层级、无障碍性、认知负荷和导航等方面。
tommygeoco
AI智能 clawhub v1.0.1 1 版本 99608.4 Key: 无需
★ 26
Stars
📥 14,997
下载
💾 3,967
安装
1
版本
#latest

概述

UI Audit Skill

Evaluate interfaces against proven UX principles. Based on Making UX Decisions by Tommy Geoco.

When to Use This Skill

  • Making UI/UX design decisions under time pressure
  • Evaluating design trade-offs with business context
  • Choosing appropriate UI patterns for specific problems
  • Reviewing designs for completeness and quality
  • Structuring design thinking for new interfaces

Core Philosophy

Speed ≠ Recklessness. Designing quickly is not automatically reckless. Recklessly designing quickly is reckless. The difference is intentionality.

The 3 Pillars of Warp-Speed Decisioning

  1. Scaffolding — Rules you use to automate recurring decisions
  2. Decisioning — Process you use for making new decisions
  3. Crafting — Checklists you use for executing decisions

Quick Reference Structure

Foundational Frameworks

  • references/00-core-framework.md — 3 pillars, decisioning workflow, macro bets
  • references/01-anchors.md — 7 foundational mindsets for design resilience
  • references/02-information-scaffold.md — Psychology, economics, accessibility, defaults

Checklists (Execution)

  • references/10-checklist-new-interfaces.md — 6-step process for designing new interfaces
  • references/11-checklist-fidelity.md — Component states, interactions, scalability, feedback
  • references/12-checklist-visual-style.md — Spacing, color, elevation, typography, motion
  • references/13-checklist-innovation.md — 5 levels of originality spectrum

Patterns (Reusable Solutions)

  • references/20-patterns-chunking.md — Cards, tabs, accordions, pagination, carousels
  • references/21-patterns-progressive-disclosure.md — Tooltips, popovers, drawers, modals
  • references/22-patterns-cognitive-load.md — Steppers, wizards, minimalist nav, simplified forms
  • references/23-patterns-visual-hierarchy.md — Typography, color, whitespace, size, proximity
  • references/24-patterns-social-proof.md — Testimonials, UGC, badges, social integration
  • references/25-patterns-feedback.md — Progress bars, notifications, validation, contextual help
  • references/26-patterns-error-handling.md — Form validation, undo/redo, dialogs, autosave
  • references/27-patterns-accessibility.md — Keyboard nav, ARIA, alt text, contrast, zoom
  • references/28-patterns-personalization.md — Dashboards, adaptive content, preferences, l10n
  • references/29-patterns-onboarding.md — Tours, contextual tips, tutorials, checklists
  • references/30-patterns-information.md — Breadcrumbs, sitemaps, tagging, faceted search
  • references/31-patterns-navigation.md — Priority nav, off-canvas, sticky, bottom nav

Usage Instructions

For Design Decisions

  1. Read 00-core-framework.md for the decisioning workflow
  2. Identify if this is a recurring decision (use scaffold) or new decision (use process)
  3. Apply the 3-step weighing: institutional knowledge → user familiarity → research

For New Interfaces

  1. Follow the 6-step checklist in 10-checklist-new-interfaces.md
  2. Reference relevant pattern files for specific UI components
  3. Use fidelity and visual style checklists to enhance quality

For Pattern Selection

  1. Identify the core problem (chunking, disclosure, cognitive load, etc.)
  2. Load the relevant pattern reference
  3. Evaluate benefits, use cases, psychological principles, and implementation guidelines

Decision Workflow Summary

When facing a UI decision:

1. WEIGH INFORMATION
   ├─ What does institutional knowledge say? (existing patterns, brand, tech constraints)
   ├─ What are users familiar with? (conventions, competitor patterns)
   └─ What does research say? (user testing, analytics, studies)

2. NARROW OPTIONS
   ├─ Eliminate what conflicts with constraints
   ├─ Prioritize what aligns with macro bets
   └─ Choose based on JTBD support

3. EXECUTE
   └─ Apply relevant checklist + patterns

Macro Bet Categories

Companies win through one or more of:

BetDescriptionDesign Implication
-------------------------------------
VelocityFeatures to market fasterReuse patterns, find metaphors in other markets
EfficiencyManage waste betterDesign systems, reduce WIP
AccuracyBe right more oftenStronger research, instrumentation
InnovationDiscover untapped potentialNovel patterns, cross-domain inspiration

Always align micro design bets with company macro bets.

Key Principle: Good Design Decisions Are Relative

A design decision is "good" when it:

  • Supports the product's jobs-to-be-done
  • Aligns with company macro bets
  • Respects constraints (time, tech, team)
  • Balances user familiarity with differentiation needs

There is no universally correct UI solution—only contextually appropriate ones.


Generating Audit Reports

When asked to audit a design, generate a comprehensive report. Always include these sections:

Required Sections (always include)

  1. Visual Hierarchy — Headings, CTAs, grouping, reading flow, type scale, color hierarchy, whitespace
  2. Visual Style — Spacing consistency, color usage, elevation/depth, typography, motion/animation
  3. Accessibility — Keyboard navigation, focus states, contrast ratios, screen reader support, touch targets

Contextual Sections (include when relevant)

  1. Navigation — For multi-page apps: wayfinding, breadcrumbs, menu structure, information architecture
  2. Usability — For interactive flows: discoverability, feedback, error handling, cognitive load
  3. Onboarding — For new user experiences: first-run, tutorials, progressive disclosure
  4. Social Proof — For landing/marketing pages: testimonials, trust signals, social integration
  5. Forms — For data entry: labels, validation, error messages, field types

Audit Output Format

{
  "title": "Design Name — Screen/Flow",
  "project": "Project Name",
  "date": "YYYY-MM-DD",
  "figma_url": "optional",
  "screenshot_url": "optional - URL to screenshot",
  
  "macro_bets": [
    { "category": "velocity|efficiency|accuracy|innovation", "description": "...", "alignment": "strong|moderate|weak" }
  ],
  
  "jtbd": [
    { "user": "User Type", "situation": "context without 'When'", "motivation": "goal without 'I want to'", "outcome": "benefit without 'so I can'" }
  ],
  
  "visual_hierarchy": {
    "title": "Visual Hierarchy",
    "checks": [
      { "label": "Check name", "status": "pass|warn|fail|na", "notes": "Details" }
    ]
  },
  "visual_style": { ... },
  "accessibility": { ... },
  
  "priority_fixes": [
    { "rank": 1, "title": "Fix title", "description": "What and why", "framework_reference": "XX-filename.md → Section Name" }
  ],
  
  "notes": "Optional overall observations"
}

Checks Per Section (aim for 6-10 each)

Visual Hierarchy: heading distinction, primary action clarity, grouping/proximity, reading flow, type scale, color hierarchy, whitespace usage, visual weight balance

Visual Style: spacing consistency, color palette adherence, elevation/shadows, typography system, border/radius consistency, icon style, motion principles

Accessibility: keyboard operability, visible focus, color contrast (4.5:1), touch targets (44px), alt text, semantic markup, reduced motion support

Navigation: clear current location, predictable menu behavior, breadcrumb presence, search accessibility, mobile navigation pattern

Usability: feature discoverability, feedback on actions, error prevention, recovery options, cognitive load management, loading states

版本历史

共 1 个版本

  • v1.0.1 当前
    2026-03-28 09:44 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

ai-intelligence

self-improving agent

pskoett
捕获经验教训、错误和纠正,以实现持续改进。使用时机:(1)命令或操作意外失败;(2)用户纠正……
★ 4,056 📥 796,118
ai-intelligence

ontology

oswalpalash
类型化知识图谱,用于结构化智能体记忆与可组合技能。支持创建/查询实体(人员、项目、任务、事件、文档)及关联...
★ 709 📥 243,539
ai-intelligence

Proactive Agent

halthelobster
将AI智能体从任务执行者升级为主动预判需求、持续优化的智能伙伴。集成WAL协议、工作缓冲区、自主定时任务及实战验证模式。Hal Stack核心组件 🦞
★ 834 📥 212,799