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 jiushiwon/wg-skills --skill frontend-ui-foundrygit clone --depth 1 https://github.com/jiushiwon/wg-skillsWrote 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/jiushiwon/wg-skills/frontend-ui-foundry)<a href="https://agentmods.dev/skills/jiushiwon/wg-skills/frontend-ui-foundry"><img src="https://agentmods.dev/badge/skills/jiushiwon/wg-skills/frontend-ui-foundry/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/jiushiwon/wg-skills/frontend-ui-foundry"><img src="https://agentmods.dev/badge/skills/jiushiwon/wg-skills/frontend-ui-foundry.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 | $0.00135 | $0.02389 |
| Opus 5 | $0.00068 | $0.01195 |
| Sonnet 5 | $0.00027 | $0.00478 |
| Haiku 4.5 | $0.00014 | $0.00239 |
Grade A, and why
frontend-ui-foundry 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.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend UI Foundry
综合性前端 UI 技能：按场景生成、一键优化、Token 统一、品牌套用、设计审查六位一体。
设计哲学
- 场景驱动：不同场景（移动端/PC/管理端/营销页/文档/金融/原生/3D）有截然不同的布局、组件、交互基线
- Token 优先：所有视觉决策沉淀为可消费的设计 Token，颜色/字体/间距/圆角/阴影/动效一应俱全
- 双模式闭环：
forge从零生成，optimize智能重构现有项目 - 复用协同：直接引用
impeccable的设计法则、ui-ux-pro-max的规则库、ui-audit的决策框架 - 多栈适配：HTML+Tailwind、React+Next、Vue+Nuxt、uniapp、RN、Svelte 六栈统一体验
子命令
| 命令 | 类别 | 用途 | 详细 |
|---|---|---|---|
forge <scenario> |
生成 | 从零按场景生成页面或项目 | commands/forge.md |
optimize [target] |
优化 | 一键智能重构现有项目 | commands/optimize.md |
tokens <action> |
Token | 提取/注入/导出设计 Token | commands/tokens.md |
unify [target] |
统一 | 多页面/多模块风格统一 | commands/unify.md |
audit [target] |
审查 | 设计 + 代码双维审查 | commands/audit.md |
brand <name> |
品牌 | 套用品牌风格到目标 | commands/brand.md |
scenario <type> |
场景 | 输出场景方案基线 | commands/scenario.md |
stack <name> |
技术栈 | 技术栈最佳实践 | commands/stack.md |
路由规则
- 无参数 → 渲染子命令菜单 + 场景选择器，引导用户选择
- 首词匹配子命令 → 加载对应
references/commands/<cmd>.md并按其流程执行 - 首词不匹配 → 视为通用设计请求，按"识别场景 → 选择风格 → 加载 Token → 实施"主流程
主流程（首词不匹配时）
1. 识别场景（mobile-responsive / pc-corporate / admin-dashboard / landing-marketing / docs-site / fintech-app / mobile-native / threejs-3d）
2. 选择风格（brand 名称 / 调色板 / 用户自描述）
3. 选择技术栈（html-tailwind / react-nextjs / vue-nuxt / uniapp / react-native / svelte）
4. 加载 references/tokens/ 对应 Token
5. 加载 references/scenarios/<scenario>.md 场景基线
6. 应用设计法则（OKLCH 调色策略、字号阶 ≥1.25、行长 65-75ch、AI slop 黑名单）
7. 输出代码 + Token 文件 + 报告
核心资源
设计 Token（6 份）
| 类别 | 文件 |
|---|---|
| 调色板 | tokens/color-palettes.md |
| 字体配对 | tokens/typography.md |
| 间距阶梯 | tokens/spacing-scale.md |
| 圆角阴影 | tokens/radius-elevation.md |
| 动效 | tokens/motion.md |
| 布局栅格 | tokens/layout-grid.md |
What ships with it
48 files 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.
- README.md 11 KB
- references/anti-patterns.md 5.8 KB
- references/brands/apple.md 2.0 KB
- references/brands/claude.md 2.2 KB
- references/brands/cursor.md 1.9 KB
- references/brands/index.md 7.4 KB
- references/brands/linear.md 2.1 KB
- references/brands/lovable.md 2.1 KB
- references/brands/mintlify.md 2.0 KB
- references/brands/revolut.md 1.9 KB
- references/brands/stripe.md 2.1 KB
- references/brands/supabase.md 2.2 KB
- references/brands/vercel.md 1.9 KB
- references/commands/audit.md 4.1 KB
- references/commands/brand.md 4.2 KB
- references/commands/forge.md 3.8 KB
- references/commands/optimize.md 5.9 KB
- references/commands/scenario.md 2.6 KB
- references/commands/stack.md 2.0 KB
- references/commands/tokens.md 4.2 KB
- references/commands/unify.md 3.3 KB
- references/scenarios/admin-dashboard.md 9.4 KB
- references/scenarios/docs-site.md 10 KB
- references/scenarios/fintech-app.md 9.2 KB
- references/scenarios/landing-marketing.md 9.1 KB
- references/scenarios/mobile-native.md 9.5 KB
- references/scenarios/mobile-responsive.md 5.7 KB
- references/scenarios/pc-corporate.md 6.5 KB
- references/scenarios/threejs-3d.md 9.4 KB
- references/stacks/html-tailwind.md 3.8 KB
- references/stacks/react-native.md 8.7 KB
- references/stacks/react-nextjs.md 6.9 KB
- references/stacks/svelte.md 5.5 KB
- references/stacks/uniapp.md 8.1 KB
- references/stacks/vue-nuxt.md 5.9 KB
- references/tokens/color-palettes.md 12 KB
- references/tokens/layout-grid.md 7.9 KB
- references/tokens/motion.md 7.2 KB
- references/tokens/radius-elevation.md 6.9 KB
- references/tokens/spacing-scale.md 5.4 KB
- references/tokens/typography.md 9.0 KB
- scripts/detect-stack.mjs 5.2 KB runs code
- scripts/extract-tokens.mjs 6.3 KB runs code
- scripts/match-profile.mjs 7.7 KB runs code
- scripts/verify-output.mjs 6.9 KB runs code
- templates/tokens.css.tpl 7.9 KB
- templates/tokens.tailwind.tpl 4.5 KB
- ui-configurator.html 109 KB
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 · 151 lines · 135 tokens per session scan A 1591fd2986a7
frontend-ui-foundry is a skill published in the GitHub repository jiushiwon/wg-skills (99 stars, last pushed yesterday), licensed Apache-2.0. It adds 135 tokens to every session and 2,389 once invoked, about $0.0007 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 $ralph 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.