Gbro Cover Design logo

Gbro Cover Design

Community
pyang5166
gbro-cover-design

公众号/小红书封面设计。固定3:4竖版,10种构图风格可选,真人出镜,生成可直接用于图片生成模型的提示词。支持多参考图:图1固定为人脸,图2起为UI截图、产品图等素材。关键词:封面设计、提示词生成、公众号封面、小红书封面。

Overview

Publisherpyang5166
Repositorygbro-cover-design
Skill namegbro-cover-design
Stars
892
Forks
96
Bundled files
19
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 19 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by pyang5166 on GitHub. Read the source before you install it.

Installation

Install the Gbro Cover Design AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/pyang5166/gbro-cover-design/tree/main
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/pyang5166/gbro-cover-design.git \
  .claude/skills/gbro-cover-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gbro Cover Design in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Gbro Cover Design on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Gbro Cover Design is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

封面设计 Skill

流程:读文章内容 → 三轮提问 → 读对应风格模板 → 生成提示词。

画幅固定为 3:4 竖版,所有提示词第一行必须是「3:4 竖版构图」。


首次使用:配置检查

每次触发本 skill 时,先检查本 skill 目录下是否存在 config.md:

  • 存在 → 读取后直接进入正常流程
  • 不存在 → 视为首次使用,先完成首次配置,再进入正常流程

首次配置(一次问完)

先向用户说明工作方式:本 skill 只产出中文提示词,不直接调用任何模型、不需要 API key;提示词需要用户自己拿去生图模型跑图。然后问两件事:

  1. 默认人脸参考图:封面为真人出镜风格,需要一张清晰的正脸照做图1。两种方式二选一:
    • 存一张到本 skill 目录 assets/my-face.png(推荐:以后生成时自动作为图1,不再每次问)
    • 选择"每次生成时上传"
  2. 常用生图模型:确认用户使用的生图模型支持多参考图输入(图1人脸 + 图2起素材图),例如即梦/Seedream 4.0、Nano Banana(Gemini 图像模型)、GPT-Image。不支持多参考图的模型无法保持人脸一致性。

问完把结果写入本 skill 目录 config.md(已被 .gitignore 排除,不会被提交):

# 配置
- 默认人脸:assets/my-face.png(或:每次上传)
- 生图模型:<模型名>
- 配置日期:<YYYY-MM-DD>

提问流程(共三轮,每轮内的问题一次列出)

第一轮:风格 + 标题

读完文章后,先给出推荐:根据内容推荐 1-2 种风格并各给一句理由,然后列出下面的完整风格表供用户挑选;同时根据文章内容提炼 1-3 个候选标题(4-8 个字)一并给出。用户一次回复选定风格和标题。

#风格适合什么
1深色渐变风人物居中,大字覆盖后方,深色渐变背景,高对比强冲击
2纯色扁平风人物抠图感,纯色背景,干净清爽
3产品主视觉风UI截图/产品占主体,人物做引导手势,适合有素材图
4对比卡片风人物手持两张对比卡片近大远小推向镜头,适合前后对比内容
5极简留白风大面积留白,文字是主视觉锤,人物轻量出镜
6海报拼贴风多张参考图叠加构图,分层有纵深,适合素材丰富的内容
7人物侧置留白风人物偏一侧占小比例,大面积留给标题,版面大气
8背影构图风人物背对镜头,制造代入感和想象空间
9局部出镜风只露手/半脸/侧脸,产品或文字是绝对主角
10正面对视风人物直视镜头,眼神接触,文字环绕脸部四周

第二轮:参考图

两个问题一起问(若 config.md 已设默认人脸且 assets/my-face.png 存在,跳过第 1 问,直接说明将使用默认人脸做图1):

  1. 图1(人脸参考图):
    • 有 → 让用户上传,提示词里写"参考图1的五官特征"
    • 没有 → 让用户描述人物(性别、大致外貌),提示词里直接描述
  2. 额外素材(图2、图3…):UI截图、产品图、其他参考图
    • 有 → 问有几张、每张是什么内容
    • 没有 → 跳过

第三轮:视觉细节

以下四项一次性列出,让用户按编号回复(如「2 / 1 / 6 / 3」);用户没提的项默认「交给模型决定」。按所选风格跳过不适用项:背影构图风跳过表情;极简留白风、人物侧置留白风默认浅色系背景,背景项可只问具体浅色色调。

A. 人物表情

  1. 捂嘴惊讶 — 双手捂嘴,眼睛睁大,震惊感
  2. 张嘴震惊 — 嘴巴微张,眼神放大,强烈惊讶
  3. 开心大笑 — 嘴角上扬,眼睛弯起,真实喜悦
  4. 兴奋雀跃 — 眉飞色舞,身体前倾,藏不住的激动
  5. 自信得意 — 嘴角微扬,眼神笃定,"就这么简单"的感觉
  6. 托腮思考 — 单手托腮,眼神若有所思
  7. 推荐种草感 — 微笑点头,眼神看向镜头,"你一定要试试"
  8. 交给模型决定

B. 背景色调

  1. 浅色系 — 白/米白/浅灰,干净清爽
  2. 深色系 — 深灰/墨黑,沉稳有力
  3. 暖色调 — 米黄/暖棕/柔橙系,温暖感
  4. 冷色调 — 浅蓝灰/青灰系,冷静专业
  5. 高饱和撞色 — 模型根据选题选一对高对比色,活力感
  6. 交给模型决定

C. 字体风格

  1. 超粗黑体 — 粗壮有力,干货/科技类首选
  2. 柔和圆体 — 圆角笔画,温暖亲切
  3. 手写涂鸦体 — 笔触自然,个性感强
  4. 极简无衬线 — 笔画均匀,国际范,设计感
  5. 复古宋体 — 有衬线,古典怀旧感
  6. 狗哥风格字体 — 短视频爆款标题风格,超粗方正中文黑体,黄底黑字标签突出关键词(具体写法见文末补充说明)
  7. 交给模型决定

D. 字体颜色效果

  1. 纯白 — 深色背景首选,干净清晰
  2. 纯黑 — 浅色背景首选,沉稳有力
  3. 渐变色 — 模型根据背景色调自行搭配
  4. 描边效果 — 字体加轮廓,增加层次感
  5. 交给模型决定

生成提示词

三轮问完后:

  1. 读选定风格的模板文件:references/style-XX-风格名.md(XX 为 01-10)
  2. 读 references/examples.md,找同风格或构图最接近的成品示例做 few-shot 参照,学它的具体程度
  3. 按模板填空生成提示词

核心要求

  • 人物姿势具体:说清楚身体位置、手在哪、动作细节,不要"她做了一个动作"这种模糊描述
  • 主体元素详细:主视觉元素长什么样、上面有什么内容、大小比例、动态或静态
  • 空间关系清晰:前景/中景/后景各是什么,哪个遮挡哪个
  • 背景和字体各风格不同:不要把同一套颜色字体套到所有风格上

通用规范

  1. 画幅:固定 3:4 竖版,提示词第一行必须写「3:4 竖版构图」
  2. 安全区:所有关键元素(人脸、标题文字、主体道具)距画面四边至少保留约 10% 边距,模板中的安全区均指此定义
  3. 中文文字准确:标题文字在提示词中用引号明确圈出;生成后提醒用户逐字核对画面文字,图片模型常写错中文字,出现错字/多笔少笔就重新生成
  4. 具象隐喻:抽象概念优先找日常可识别的实物
  5. 不要发光特效:全息投影、数据流、粒子效果容易让画面廉价
  6. 正向描述:只写画面里应该出现什么
  7. 参考图指代:直接写"图1/图2/图3",不复述图里所有细节
  8. 每种风格有自己的背景和字体逻辑:不要把同一套颜色字体套到所有风格

字体风格补充说明

狗哥风格字体

当用户选择"狗哥风格字体"时,提示词里的字体风格必须具体写成:

短视频爆款标题风格:超粗中文黑体,无衬线字体,字体方正硬朗,类似思源黑体 Heavy / 站酷酷黑 / 优设标题黑。文字排版占据画面上半部分,字号巨大,行距紧凑,字距略微拉开,形成强烈压迫感和高点击率视觉冲击。

重点关键词使用高饱和亮黄色矩形色块作为背景,黑色超粗字体,重点信息放在黄色标签里,像警示牌一样醒目。

其他主标题使用纯白色超粗大字,添加轻微黑色投影或暗色描边,确保在深色背景上清晰可读。整体文字风格像小红书 / B站 / 抖音知识类爆款封面,强对比、强识别、一眼看懂。不要文艺字体,不要细字体,不要花哨渐变。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Gbro Cover Design AI skill do?

公众号/小红书封面设计。固定3:4竖版,10种构图风格可选,真人出镜,生成可直接用于图片生成模型的提示词。支持多参考图:图1固定为人脸,图2起为UI截图、产品图等素材。关键词:封面设计、提示词生成、公众号封面、小红书封面。

Why use Gbro Cover Design on TypingMind?

Because you install it once and use it with any model. Gbro Cover Design is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Gbro Cover Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pyang5166/gbro-cover-design/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Gbro Cover Design?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Gbro Cover Design?

As many as you like. As long as a model supports skills, you can use Gbro Cover Design with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Gbro Cover Design AI skill free?

It is published on GitHub by pyang5166. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇