Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add yunshu0909/yunshu_skillshub --skill ui-designgit clone --depth 1 https://github.com/yunshu0909/yunshu_skillshubWrote 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/yunshu0909/yunshu_skillshub/ui-design)<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/ui-design"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/ui-design/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/yunshu0909/yunshu_skillshub/ui-design"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/ui-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00222 | $0.01130 |
| Opus 5 | $0.00111 | $0.00565 |
| Sonnet 5 | $0.00044 | $0.00226 |
| Haiku 4.5 | $0.00022 | $0.00113 |
Grade A, and why
ui-design 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 12d 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.
What it actually says
用户要求修改页面的 UI 样式(布局、间距、颜色、组件搭配等视觉层面的调整)。通过结构化的协作流程完成修改,确保每一步都对齐目标,不做无效猜测。
核心原则
- 不猜,不抢跑 — 没有对齐目标之前,绝不动代码
- 截图是第一语言 — 主动要求用户提供截图,用截图定位问题
- ASCII 画方案 — 布局方案用 ASCII 画出来,文字描述容易产生歧义
- 每次只改一个点 — 不要一次改多个地方,逐步逼近目标
工作流程
第 1 步:定位问题
用户说想改某个地方时,先做两件事:
- 读代码 — 读取相关文件,理解当前实现
- 描述现状 — 用 ASCII 画出当前布局,向用户确认:"我看到的是这样,对吗?"
示例:
┌─────────────────────────────────────────────┐
│ 📈 标题 [🔄] │
│ 副标题说明文字 │
│ 🔍 [搜索框... ] │
├─────────────────────────────────────────────┤
禁止:跳过这一步直接问"你想改成什么样"。必须先让用户确认你理解了现状。
第 2 步:给出方案
提供 2-3 个方案,每个方案包含:
- ASCII 布局图 — 画出改完的样子
- 一句话说明 — 这个方案的核心思路是什么
示例:
方案 A:搜索和刷新放同一行
┌──────────────────────────────────────────┐
│ 🔍 [搜索框... ] [🔄] │
└──────────────────────────────────────────┘
方案 B:刷新挪到标题行
┌──────────────────────────────────────────┐
│ 📈 标题 [🔄] │
│ 🔍 [搜索框... ] │
└──────────────────────────────────────────┘
禁止:
- 只给一个方案(用户没有选择余地)
- 给超过 3 个方案(选择困难)
- 方案只有文字没有 ASCII 图
第 3 步:等用户选择
用户选完方案后,才开始写代码。
禁止:用户还没选就开始改代码。
第 4 步:改代码
执行最小改动,只改用户选定方案涉及的部分。
禁止:顺手改其他地方、优化代码结构、加注释。
第 5 步:微调
改完后让用户看效果。用户可能会提出微调:
- "加个边框"
- "颜色太深"
- "间距再大一点"
微调是具体的、小的修改,直接执行,不需要再走方案选择流程。
如果用户的反馈不够具体(比如"感觉不对"),主动追问:
- "是大小的问题、颜色的问题、还是位置的问题?"
- "和旁边哪个元素搭配起来不协调?"
沟通规范
用户应该提供的
| 信息 | 说明 |
|---|---|
| 截图 | 标注出想改的区域 |
| 问题描述 | "这两个元素搭配不协调"、"间距太大" |
| 选择方案 | 从给出的方案中选一个 |
AI 应该做的
| 阶段 | 输出 |
|---|---|
| 定位 | ASCII 现状图 |
| 方案 | 2-3 个 ASCII 方案图 + 一句话说明 |
| 改码 | 最小改动,只改选定方案 |
| 微调 | 直接执行具体调整 |
AI 绝不应该做的
- 用户说"改布局"就直接猜想法然后改代码
- 一次给出大段代码重构
- 微调阶段还在给多个方案让用户选
- 顺手改用户没提到的地方
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.
- 12d ago First seen · 110 lines · 222 tokens per session scan A d70108ceec47
ui-design is a skill published in the GitHub repository yunshu0909/yunshu_skillshub (757 stars, last pushed 1mo ago), licensed MIT. It adds 222 tokens to every session and 1,130 once invoked, about $0.0011 per session on Opus 5. 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 2026-08-30.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.