跳到正文
cccskills
免费在 GitHub 公开

design-md

Use DESIGN.md files to give AI agents a complete design system in plain text. Drop a DESIGN.md into your project root and any AI coding agent generates consistent, pixel-perfect UI matching that design. Use when: building UI with AI agents, maintaining design consistency across AI-generated components, recreating the look of existing websites.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(2)

  • SKILL.md4.4 KB
  • _scores.json1.7 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

DESIGN.md

Overview

DESIGN.md is a plain-text design system document that AI agents read to generate consistent UI. Introduced by Google Stitch, it captures colors, typography, components, spacing, and design philosophy in markdown — the format LLMs read best.

Think of it as AGENTS.md for design: AGENTS.md tells agents how to build, DESIGN.md tells agents how things should look.

Instructions

Using a DESIGN.md

  1. Copy a DESIGN.md into your project root
  2. Tell your AI agent: "Build a landing page following DESIGN.md"
  3. The agent reads colors, typography, components, and layout rules
  4. Generated UI matches the design system consistently

Structure of a DESIGN.md

Every DESIGN.md follows this structure:

# DESIGN.md

## Visual Theme & Atmosphere
Mood, density, design philosophy (e.g., "dark cinematic", "clean editorial")

## Color Palette & Roles
| Name | Hex | Role |
|------|-----|------|
| Primary | #6366f1 | Interactive elements, CTAs |
| Background | #0a0a0b | Page background |
| Surface | #18181b | Cards, elevated content |
| Text Primary | #fafafa | Main content |
| Accent | #f97316 | Highlights, alerts |

## Typography Rules
Font families, size hierarchy (h1-h6, body, caption), weights, line heights

## Component Stylings
Buttons (primary, secondary, ghost), cards, inputs, navigation — with hover/active states

## Layout Principles
Spacing scale (4px base), max-width, grid columns, whitespace philosophy

## Depth & Elevation
Shadow system, border treatments, surface hierarchy

## Do's and Don'ts
Design guardrails: what to do and what to avoid

## Responsive Behavior
Breakpoints, touch targets, mobile adaptations

Finding Pre-Made DESIGN.md Files

The awesome-design-md collection has 58+ ready-to-use files extracted from real websites:

  • AI: Claude, Cohere, ElevenLabs, Mistral, Ollama, Replicate, RunwayML
  • Dev Tools: GitHub, Vercel, Supabase, Railway, Linear, Cursor
  • SaaS: Stripe, Notion, Figma, Slack, Cal.com
  • Marketing: Tailwind, shadcn/ui, Framer

Creating Your Own DESIGN.md

Inspect the target website and extract:

  1. Colors: Use browser DevTools → Computed styles → capture all colors used
  2. Typography: Font families from CSS, size scale from headings
  3. Spacing: Measure padding/margins, identify the base unit (usually 4px or 8px)
  4. Components: Screenshot buttons, cards, inputs in all states
  5. Layout: Note max-width, grid columns, responsive breakpoints

Write it all in markdown following the structure above.

Examples

Example 1: Build a SaaS landing page

Drop Linear's DESIGN.md into your project:

curl -O https://raw.githubusercontent.com/VoltAgent/awesome-design-md/main/design-md/linear/DESIGN.md

Then tell the agent:

Build a landing page for a project management tool following DESIGN.md.
Include: hero with gradient, feature grid, pricing table, CTA section.

Result: The agent generates UI with Linear's exact color palette, typography, spacing, and component styles.

Example 2: Consistent component library

With DESIGN.md in place, every component the agent generates follows the same system:

Create a notification dropdown component following DESIGN.md.

The agent uses the correct surface color, border radius, shadow level, and typography from the design system — no manual correction needed.

Guidelines

  • Place DESIGN.md in project root alongside AGENTS.md and CLAUDE.md
  • One DESIGN.md per project — it defines the entire visual language
  • Update it when your design evolves (it's version-controlled markdown)
  • For dark/light themes, include both color sets in the palette section
  • Test with a simple component first to verify the agent reads it correctly
  • Combine with impeccable skill for additional design quality rules

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Scripts and configures production rendering in Autodesk 3ds Max with the V-Ray and Corona renderers: output size and files, render elements, denoising, light mix, batch and command-line rendering, and network rendering. Use when a user asks to set up a production render, render several cameras in one batch, render from the command line or on a render farm, add render passes for compositing, or cut render time for archviz and product shots.

中文简介正在准备中。当前显示原文说明。

TerminalSkills/skills1722026年10月14日 更新

Covers scripting Autodesk 3ds Max, the 3D modeling and rendering application, with MAXScript and Python (pymxs): scene manipulation, object creation, material assignment, camera and light setup, batch operations, and file I/O. Use when tasks involve automating repetitive 3ds Max workflows, batch processing scenes, running scripts headless with 3dsmaxbatch, creating custom tools, or scripting scene setup for archviz, product visualization, or VFX.

中文简介正在准备中。当前显示原文说明。

TerminalSkills/skills1722026年10月14日 更新

3proxy

免费

3proxy is a small open-source proxy server that runs HTTP/HTTPS, SOCKS4/5, SNI and TCP/UDP port-mapping proxies from one config file. Use when a user asks to set up an HTTP or SOCKS5 proxy, add proxy users and passwords, write 3proxy access rules, chain or rotate upstream (parent) proxies, limit bandwidth, connections or monthly traffic per user, run 3proxy in Docker, or fix a 3proxy.cfg that will not start.

中文简介正在准备中。当前显示原文说明。

TerminalSkills/skills1722026年10月14日 更新

Builds Agent2Agent (A2A) servers and clients, the open protocol (originally from Google, now under the Linux Foundation) that lets AI agents from different frameworks call each other. Use when the user wants to create an A2A-compliant agent, build an Agent Card, implement task management, connect agents across frameworks, set up agent discovery, handle streaming responses, implement push notifications, or orchestrate multi-agent workflows. Trigger words: a2a, agent to agent, agent2agent, a2a protocol, a2a server, a2a client, agent card, agent interoperability, agent collaboration, multi-agent, agent discovery, a2a sdk, a2a task.

中文简介正在准备中。当前显示原文说明。

TerminalSkills/skills1722026年10月14日 更新

Plans a controlled experiment (A/B test) so its result can be trusted: writes the hypothesis, picks one primary metric and the guardrails, computes sample size and run time, specifies how visitors are assigned and when exposure is logged, and reads out the result with a confidence interval. Use when someone says "set up an A/B test", "split test this page", "how many visitors do I need", "how long should the experiment run", "is this result significant", "can I stop the test early", or wants to test a headline, price, layout or onboarding change against the current version.

中文简介正在准备中。当前显示原文说明。

TerminalSkills/skills1722026年10月14日 更新

ably

免费

Ably is a hosted realtime messaging service: clients publish and subscribe to named channels over WebSockets, see who is present, replay message history, and resume after a dropped connection. Use when a user asks to "add realtime updates", "push live notifications to the browser", "show who is online", "add a chat room with typing indicators", "publish from a serverless function", or "authenticate Ably clients without exposing the API key". Covers the ably 2.x JavaScript SDK (Realtime and REST), JWT token authentication, presence, history and rewind, batch publishing, and the @ably/chat 1.x SDK.

中文简介正在准备中。当前显示原文说明。

TerminalSkills/skills1722026年10月14日 更新

查看 TerminalSkills 的全部技能

报告此技能的问题