Token导航 LogoToken导航

Agent Skill · 研究检索

brand-to-design-md(品牌设计 MD)

用于辅助界面设计、视觉规范、排版、配色、布局和交互体验优化。它适合让 Agent 根据产品场景整理页面结构、生成 UI 方案、检查视觉一致性或改进组件层级。使用时需要结合现有品牌、设计系统和用户任务,不应只堆装饰元素;涉及真实页面改动时,应通过截图或浏览器预览检查文本溢出、对齐和响应式表现。

brand-to-design-md 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为操作浏览器;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 66,030。

总安装 269周安装 11GitHub Stars 31下载 87核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:brand-to-design-md(品牌设计 MD)
来源仓库:https://github.com/shaom/brand-to-design-md-skill
仓库路径:skills/brand-to-design-md
安装命令:
npx skills add https://github.com/shaom/brand-to-design-md-skill --skill brand-to-design-md
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/shaom/brand-to-design-md-skill --skill brand-to-design-md

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

brand-to-design-md 将公开品牌证据转化为编码友好的 DESIGN.md 文件,辅助 UI 开发。适用于自动生成视觉规范、配色方案与布局结构,提升前端实现一致性。支持输出 demo HTML 页面并浏览器验证,确保文本溢出与响应式表现正常。需结合具体项目上下文使用,避免脱离实际场景生成无效代码片段。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/brand-to-design-md

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/shaom/brand-to-design-md-skill --skill brand-t…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要操作浏览器,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

brand-to-design-md 怎么安装?

在终端执行 npx skills add https://github.com/shaom/brand-to-design-md-skill --skill brand-to-design-m…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

brand-to-design-md 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

brand-to-design-md 需要什么权限?

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

brand-to-design-md 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

brand-to-design-md 用的人多吗?

公开数据是累计安装 269 次,近一周安装 11 次,下载 87 次,GitHub 31 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

brand-to-design-md 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
brand-to-design-md

品牌设计 MD · 本页

26931操作浏览器未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Brand To DESIGN.md

Overview

Use this skill to turn public brand evidence into a token-ready DESIGN.md that a coding agent can use to generate consistent UI. When useful, also create a demo HTML page and verify it in a browser.

Start from the Google Labs DESIGN.md standard, not from example directories or third-party showcase pages. The output should be practical, source-aware, and executable by an agent.

Workflow

1. Confirm Scope And Standard

Clarify only if needed:

  • Target brand URL or brand name.
  • Required outputs: DESIGN.md only, or DESIGN.md plus demo HTML and screenshots.
  • Target context: website, app UI, developer docs, product page, editorial asset, or general system.

Use the Google Labs DESIGN.md format as the structural reference: metadata, design tokens, component guidance, imagery rules, logo boundaries, and Do/Don't guidance.

2. Gather Evidence

Prefer primary and high-signal sources:

  • Official homepage and product pages.
  • Official brand, press, newsroom, media kit, or legal trademark pages.
  • Public CSS, font declarations, SVG logos, favicons, images, and screenshots.
  • Design agency case studies when they explain the identity system.
  • Third-party brand databases only as secondary support.

Record evidence in four groups:

  • Direct evidence: observed CSS, SVG fills, image colors, font names, layout behavior.
  • Official prose: brand usage rules, typography descriptions, press-kit notes.
  • Design rationale: motifs, concepts, color names, type-system explanations.
  • Inference: practical agent decisions not explicitly stated by sources.

If access is blocked by a CAPTCHA, login, or security challenge, do not bypass it. Use accessible official pages, cached/search snippets, press kits, downloaded public assets, or clearly mark the limitation.

3. Extract Tokens

Translate evidence into roles, not just values.

Core token groups:

  • colors: primary, secondary, tertiary, neutral, surface, on-primary, text, border, status/accent colors.
  • typography: display, h1, h2, body, label, mono/code when present.
  • rounded: small, medium, large, special brand shapes.
  • spacing: base scale, common section gaps.
  • components: buttons, cards, inputs, links, code panels, notices, navigation.
  • imagery: photography style, illustration style, texture, gradient, motion, icon rules.

For each major token, prefer a role explanation:

  • Where it came from.
  • What it should be used for.
  • What should not use it.

4. Compile DESIGN.md

Write a concise but usable file:

---
version: alpha
name: Brand Name
description: One sentence identity summary.
sources:
  - https://...
notes:
  - Evidence and limitation notes.
colors:
  primary: "#..."
typography:
  display:
    fontFamily: ...
components:
  button-primary:
    backgroundColor: "{colors.primary}"
---

## Overview
...

## Colors
...

## Typography
...

## Layout
...

## Components
...

## Imagery
...

## Logo And Usage
...

## Do's and Don'ts
...

Keep the writing concrete. Avoid generic claims such as "modern, clean, innovative" unless the evidence supports them and they are translated into specific design actions.

5. Generate A Demo When Useful

If asked for a demo, build a single-file HTML artifact in the workspace.

The demo should prove that the DESIGN.md is usable:

  • First screen should be an actual branded product or site experience, not an explanation page.
  • Include palette, typography, buttons, cards, forms, data/code panels, and one brand-specific motif.
  • Use extracted public assets when allowed and useful.
  • Recreate the brand's behavior and hierarchy, not only its colors.
  • Keep the page responsive and readable on mobile.

For browser-based artifacts, use real browser or preview-environment verification:

  • Open the file in an available browser or preview environment.
  • Check console errors.
  • Check horizontal overflow.
  • Capture desktop and mobile screenshots.
  • Confirm critical images and fonts fall back cleanly.

6. Report Output

Return:

  • DESIGN.md path.
  • Demo HTML path if created.
  • Screenshot paths if created.
  • Source summary.
  • Verification result.
  • Any limitations or inferred choices.

Quality Bar

A good output lets a future coding agent produce a page that feels recognizably tied to the brand without needing more context.

Check for:

  • Tokens map to meaningful roles.
  • The brand has distinct visual behavior beyond color.
  • Logo and trademark boundaries are respected.
  • Demo page uses the system in several UI contexts.
  • The output distinguishes evidence from inference.

When To Read More

For a compact checklist and output templates, read references/workflow-checklist.md.

平台分布

Codex

37.05%
按下载量换算32

Claude

26.86%
按下载量换算23

Cursor

17.96%
按下载量换算16

Gemini CLI

9.03%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills