一键导入
design-elegant
Elegant design system blueprint — Google Sans (Outfit), minimal aesthetic. Strict K3 implementation guide for refined, light-weight UI in Next.js 15.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Elegant design system blueprint — Google Sans (Outfit), minimal aesthetic. Strict K3 implementation guide for refined, light-weight UI in Next.js 15.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | design-elegant |
| description | Elegant design system blueprint — Google Sans (Outfit), minimal aesthetic. Strict K3 implementation guide for refined, light-weight UI in Next.js 15. |
Architect: K3 Ecosystem (
bergsideinspired) Target: Next.js 15 + Tailwind v4 + Shadcn UI
Execute weightless, delicate interfaces. Emphasize incredible precision via extremely thin borders, subtle typography, and a deliberate absence of visual noise.
Inject these exact font definitions into app/layout.tsx. (Note: Google Sans is proprietary and unlisted in next/font, so we substitute with the closest open match: purely geometric Outfit or Plus Jakarta Sans).
import { Outfit, Anonymous_Pro } from 'next/font/google';
const outfit = Outfit({ subsets: ['latin'], variable: '--font-sans' });
const anonymousPro = Anonymous_Pro({ subsets: ['latin'], weight: ['400', '700'], variable: '--font-mono' });
// Add to body className: `${outfit.variable} ${anonymousPro.variable} font-sans antialiased text-gray-900`
@theme Overrides (globals.css)Inject these absolute value mappings to force Shadcn into the Elegant paradigm.
@theme inline {
--color-background: #FCFCFD;
--color-foreground: #09090B;
--color-primary: #18181B; /* Almost black */
--color-primary-foreground: #FAFAFA;
--color-secondary: #FAFAFA;
--color-secondary-foreground: #18181B;
--color-muted: #F4F4F5;
--color-muted-foreground: #71717A;
--color-accent: #F4F4F5;
--color-accent-foreground: #18181B;
--color-border: #E4E4E7;
--color-input: #E4E4E7;
--color-ring: #18181B;
--font-sans: var(--font-sans), ui-sans-serif, system-ui;
--font-mono: var(--font-mono), ui-monospace, SFMono-Regular;
--radius-lg: 0.375rem;
--radius-md: calc(0.375rem - 2px);
--radius-sm: calc(0.375rem - 4px);
}
@utility thin-border {
border-width: 0.5px; /* Deliberately sub-pixel for elegance on high-DPI screens! */
border-color: var(--color-border);
}
font-bold lightly; maximum weight should usually be font-medium or font-semibold unless making a massive stylistic statement.1px borders can feel heavy. Use the provided @utility thin-border on Cards and Inputs where high-DPI retina rendering is expected.#3B82F6) only for solitary, high-value primary CTAs.Surfaces risks, blind spots, and opportunities the operator didn't ask about. Runs after plans are drafted but before execution. Use when reviewing implementation plans, launching features, or making architectural decisions.
Google Agent Development Kit (ADK) for Python — verified API patterns for building production-grade multi-agent systems. Covers Workflow graphs (ADK 2.0 Beta), LlmAgent, SequentialAgent, LoopAgent, CustomAgent (BaseAgent), MCP integration via McpToolset, FunctionTool, ToolContext state, session management, context compaction, callbacks (before/after agent/model/tool), human input via RequestInput, and the App wrapper. Use when: ADK agent, workflow graph, multi-agent, MCP toolset, HITL, context compaction, session state, agent pipeline.
Craft and launch a Gemini Deep Research session via a custom Gem. Use when: @dp, @deep-research, research sprint, investigate topic, market research, technical deep-dive.
Gemini Embedding 2 — Google's natively multimodal embedding model (GA April 2026). Maps text, images, video, audio, and PDFs into a unified 3072-dim vector space with MRL support (truncate to 128-3072). Use when: embeddings, semantic search, RAG, clustering, classification, multimodal retrieval, vector database, MRL truncation, cosine similarity, narrative memory, code retrieval, cross-modal search, agentic RAG.
Autonomous HestiaCP server management with AI agents. Two-brain Orchestrator+Sentinel architecture for VPS monitoring, troubleshooting, security hardening, PHP-FPM tuning, Exim mail forensics, and post-compromise detection. Use when: HestiaCP, VPS, server monitoring, DevOps agent, Linux admin, Nginx/Apache, PHP-FPM, Exim, Fail2Ban, ClamAV, SSL, backup.
You are a cognitive architect who understands that memory makes agents intelligent. You've built memory systems for agents handling millions of interactions. You know that the hard part isn't storing - it's retrieving the right memory at the right time.