Borrowing it
Nothing to install: this file belongs to sumulige/sumulige-claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sumulige/sumulige-claude/main/.claude/skills/design-audit/SKILL.mdgit clone --depth 1 https://github.com/sumulige/sumulige-claudeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sumulige/sumulige-claude/design-audit)<a href="https://agentmods.dev/skills/sumulige/sumulige-claude/design-audit"><img src="https://agentmods.dev/badge/skills/sumulige/sumulige-claude/design-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sumulige/sumulige-claude/design-audit"><img src="https://agentmods.dev/badge/skills/sumulige/sumulige-claude/design-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.02365 |
| Opus 5 | $0.00000 | $0.01182 |
| Sonnet 5 | $0.00000 | $0.00473 |
| Haiku 4.5 | $0.00000 | $0.00236 |
Grade A, and why
design-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Audit
系统性设计审计协议 - Steve Jobs 标准
概述
这是一个完整的 UI/UX 审计工作流,基于 Steve Jobs 和 Jony Ive 的设计哲学。用于对现有应用进行系统性审计,输出分阶段改进计划。
触发条件
- 用户请求设计审计
- 用户请求 UI/UX 评估
- 用户请求设计改进建议
- 用户说 "review my design" / "审计设计"
前置要求
开始前必须读取并内化这些文件(按顺序):
DESIGN_SYSTEM.md— 现有视觉语言(令牌、颜色、排版、间距、阴影、圆角)FRONTEND_GUIDELINES.md— 组件工程方式、状态管理、文件结构APP_FLOW.md— 每个屏幕、路由、用户旅程PRD.md— 每个功能及其需求TECH_STACK.md— 技术栈能做什么和不能做什么progress.txt— 当前构建状态LESSONS.md— 之前会话的设计错误、模式和修正- 实际应用 — 按移动、平板、桌面视口顺序走查每个屏幕
必须完全理解当前系统后再提出改变。你不是从零开始。你是在提升现有的。
审计协议
Step 1: 15 维度全面审计
针对应用中的每个屏幕,检查以下维度:
1. 视觉层级
- 眼睛落在应该落的地方吗?
- 最重要的元素是最突出的吗?
- 用户能在 2 秒内理解屏幕吗?
2. 间距与节奏
- 留白一致且有意图吗?
- 元素呼吸还是拥挤?
- 垂直节奏和谐吗?
3. 排版
- 字号建立清晰层级了吗?
- 是否有太多字重或字号在竞争?
- 字体感觉平静还是混乱?
4. 颜色
- 颜色使用克制且有目的吗?
- 颜色引导注意力还是分散注意力?
- 对比度足够可访问吗?
5. 对齐与网格
- 元素在一致的网格上吗?
- 是否有任何东西偏了 1-2 像素?
- 每个元素都感觉精确锁定在布局中吗?
6. 组件
- 相似元素跨屏幕样式一致吗?
- 交互元素明显可交互吗?
- 禁用、悬停、焦点状态都考虑了吗?
7. 图标
- 图标在风格、粗细、大小上跨应用一致吗?
- 它们来自一个统一的图标集还是混合不同库?
- 它们支持含义还是只是装饰?
8. 动效与过渡
- 过渡感觉自然且有目的吗?
- 是否有无理由存在的动效?
- 应用对触摸/点击响应灵敏吗?
- 动画在当前技术栈内可行吗?
9. 空状态
- 每个屏幕没数据时看起来怎样?
- 空白屏幕感觉有意图还是坏掉了?
- 用户被引导向第一个动作了吗?
10. 加载状态
- 骨架屏、加载器、占位符一致吗?
- 等待时应用感觉活着还是冻结?
11. 错误状态
- 错误消息样式一致吗?
- 它们感觉有帮助和清晰还是敌对和技术性?
12. 暗色模式/主题
- 如果支持,它是真正设计的还是只是反转的?
- 所有令牌、阴影、对比度在主题间都保持吗?
13. 密度
- 任何东西可以移除而不丢失含义吗?
- 是否有冗余元素在说同一件事两次?
- 每个元素都在屏幕上赢得了它的位置吗?
14. 响应式
- 每个屏幕在移动、平板、桌面都工作吗?
- 触摸目标在触摸设备上是为拇指尺寸的吗?
- 布局在所有视口大小间流畅适应吗——不只是在断点处卡住?
- 没有屏幕尺寸应该感觉像事后想法。
15. 可访问性
- 键盘导航
- 焦点状态
- ARIA 标签
- 颜色对比度
- 屏幕阅读器流程
Step 2: 应用 Jobs 过滤器
对每个屏幕上的每个元素:
"用户需要被告知这个存在吗?"
→ 如果是,重新设计直到显而易见
"这个可以移除而不丢失含义吗?"
→ 如果是,移除它
"这感觉 inevitable 吗,仿佛没有其他设计方案?"
→ 如果否,它没完成
"这个细节像用户永远看不到的细节一样精致吗?"
→ 围栏背面也要上漆
"Say no to 1,000 things"
→ 砍掉好想法保留伟大的想法。Less but better。
Step 3: 编制设计计划
审计后,将所有发现组织成分阶段计划。不要做更改。呈现计划。
输出格式
# 设计审计结果
**总体评估**: [1-2 句话描述设计当前状态]
---
## PHASE 1 — 关键问题
> 视觉层级、可用性、响应式或一致性问题,正在积极伤害体验
| 屏幕/组件 | 问题 | 应该是 | 为什么重要 |
|-----------|------|--------|------------|
| [名称] | [问题描述] | [解决方案] | [理由] |
**Phase 1 优先级说明**: [为什么这些是最高优先级]
---
## PHASE 2 — 精化
> 间距、排版、颜色、对齐、图标调整,提升体验
| 屏幕/组件 | 问题 | 应该是 | 为什么重要 |
|-----------|------|--------|------------|
| [名称] | [问题描述] | [解决方案] | [理由] |
**Phase 2 排序说明**: [为什么这个顺序]
---
## PHASE 3 — 打磨
> 微交互、过渡、空状态、加载状态、错误状态、暗色模式、让它感觉 premium 的细微细节
| 屏幕/组件 | 问题 | 应该是 | 为什么重要 |
|-----------|------|--------|------------|
| [名称] | [问题描述] | [解决方案] | [理由] |
**Phase 3 说明**: [这些项目和预期累积影响]
---
## 需要的 DESIGN_SYSTEM 更新
- [任何需要的新令牌、颜色、间距值、排版变更或组件添加]
- 这些必须在实施开始前被批准并添加到 DESIGN_SYSTEM.md
---
## 给构建 Agent 的实施说明
- [确切文件, 确切组件, 确切属性, 确切旧值 → 确切新值]
- 写成构建 agent 可以无需设计解读就能执行的方式
- 没有歧义。"让卡片感觉更柔和"不是指令。
"CardComponent border-radius: 8px → 12px 按更新的 DESIGN_SYSTEM token"才是。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 276 lines · 0 tokens per session scan A 0d2cf05c6b44
design-audit is a skill published in the GitHub repository sumulige/sumulige-claude (2 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,365 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
codex-build
Orchestrate Codex to BUILD code in the background while this Claude Code session (typically Opus) plans and reviews — never babysitting. The session composes the implementation plan, kicks the dev-review runner detached via a background Bash task with --preset codex-build, ENDS ITS TURN, and is woken on exit to run a…
co-evolution
General-purpose co-evolution for questions, ideas, drafts, plans, specs, arguments, and markdown documents. Composes or bounces content between agents using [CONTESTED]/[CLARIFY] markers until it converges. Triggers on "co-evolution", "co-evolve", "co evolve", "bounce", "bounce document", "agent bouncer", "refine with…
recursive-task-optimizer
Build, configure, run, inspect, or troubleshoot agent-agnostic recursive improvement loops for a repository or artifact. Use when a task should be attempted repeatedly by Claude Code, Codex CLI, Hermes, or another CLI agent; when candidates must inherit mutable task instructions, a self-improving meta-procedure, and…
dev-review
Code-focused plan-bounce-execute workflow between Claude Code (Opus) and Codex CLI. Use when the user wants repo files changed, a bug fixed, a feature implemented, or a code plan verified before execution. One AI composes a plan, it bounces between agents with [CONTESTED]/[CLARIFY] markers until refined, then the…
design-harvest
Harvests a DESIGN.md from an existing codebase, critiques it against the actual code, and applies safe quick-win fixes. Three modes harvest / critique / fix. Shells out to npx @google/design.md lint for structural validation; never reimplements Google's linter. The on-ramp that makes DESIGN.md adoptable for every…
design-bridge
Continuously bridges DESIGN.md into the active planning phase. When the user is working on a UI phase, reads the project's DESIGN.md, extracts the relevant token slice, and appends it to findings.md under "## Design Context" so the agent sees design constraints in its attention window. Never edits DESIGN.md, never…