AI封面图片生成器 - 5维定制文章封面，一键生成优雅视觉

baoyu-cover-image by jimliu/baoyu-skills

13,300 周安装量

11,800 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/jimliu/baoyu-skills --skill baoyu-cover-image

AI/机器学习生产力设计

🇨🇳中文介绍

封面图片生成器

通过 5 维定制，为文章生成优雅的封面图片。

使用方法

# 基于内容自动选择维度
/baoyu-cover-image path/to/article.md

# 快速模式：跳过确认
/baoyu-cover-image article.md --quick

# 指定维度
/baoyu-cover-image article.md --type conceptual --palette warm --rendering flat-vector

# 样式预设（调色板和渲染的简写）
/baoyu-cover-image article.md --style blueprint

# 使用参考图片
/baoyu-cover-image article.md --ref style-ref.png

# 直接输入内容
/baoyu-cover-image --palette mono --aspect 1:1 --quick
[粘贴内容]

选项

选项	描述
`--type <名称>`	hero, conceptual, typography, metaphor, scene, minimal
`--palette <名称>`	warm, elegant, cool, dark, earth, vivid, pastel, mono, retro, duotone

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

维度	值	默认值
类型	hero, conceptual, typography, metaphor, scene, minimal	auto
调色板	warm, elegant, cool, dark, earth, vivid, pastel, mono, retro, duotone	auto
渲染风格	flat-vector, hand-drawn, painterly, digital, pixel, chalk, screen-print	auto
文本	none, title-only, title-subtitle, text-rich	title-only
氛围	subtle, balanced, bold	balanced
字体	clean, handwritten, serif, display	clean

步骤 0：加载偏好设置 ⛔ 阻塞

检查 EXTEND.md 是否存在（优先级：项目 → 用户）：

# macOS, Linux, WSL, Git Bash
test -f .baoyu-skills/baoyu-cover-image/EXTEND.md && echo "project"
test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-cover-image/EXTEND.md" && echo "xdg"
test -f "$HOME/.baoyu-skills/baoyu-cover-image/EXTEND.md" && echo "user"

# PowerShell (Windows)
if (Test-Path .baoyu-skills/baoyu-cover-image/EXTEND.md) { "project" }
$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
if (Test-Path "$xdg/baoyu-skills/baoyu-cover-image/EXTEND.md") { "xdg" }
if (Test-Path "$HOME/.baoyu-skills/baoyu-cover-image/EXTEND.md") { "user" }

结果	操作
找到	加载，显示摘要 → 继续
未找到	⛔ 运行首次设置（references/config/first-time-setup.md） → 保存 → 继续

关键：如果未找到，必须在任何其他步骤或提问之前完成设置。

步骤 1：分析内容

保存参考图片（如果提供）→ references/workflow/reference-images.md
保存源内容（如果粘贴，保存到 source.md）
分析内容：主题、基调、关键词、视觉隐喻
深度分析参考图片 ⚠️：提取具体、明确的元素（参见 reference-images.md）
检测语言：比较源内容、用户输入、EXTEND.md 偏好设置
确定输出目录：根据文件结构规则

⚠️ 参考图片中的人物：

如果参考图片包含应该出现在封面中的人物：

模型支持 --ref（默认）：将图片复制到 refs/，在生成时通过 --ref 传递。不需要描述文件——模型直接看到人脸。
模型不支持 --ref（Jimeng, Seedream 3.0）：创建 refs/ref-NN-{slug}.md，包含每个角色的描述（头发、眼镜、肤色、服装）。作为 MUST/REQUIRED 指令嵌入到提示词文本中。

完整决策表请参见 reference-images.md。

步骤 2：确认选项 ⚠️

必须使用 AskUserQuestion 工具以交互式选择的形式呈现选项——不要使用纯文本表格。在单个 AskUserQuestion 调用中最多呈现 4 个问题（类型、调色板、渲染风格、字体 + 设置）。每个问题首先显示推荐选项及其理由，然后是备选项。

完整的确认流程和问题格式：references/workflow/confirm-options.md

条件	跳过	仍需询问
`--quick` 或 `quick_mode: true`	6 个维度	宽高比（除非指定了 `--aspect`）
指定了全部 6 个维度 + `--aspect`	全部	无

步骤 3：创建提示词

保存到 prompts/cover.md。模板：references/workflow/prompt-template.md

关键 - Frontmatter 中的参考：

保存到 refs/ 的文件 → 添加到 frontmatter 的 references 列表中
口头提取的样式（无文件）→ 省略 references，在正文中描述
写入前 → 验证：test -f refs/ref-NN-{slug}.{ext}

正文中的参考元素 必须详细，前缀为 "MUST"/"REQUIRED"，并说明整合方式。

步骤 4：生成图片

备份现有 cover.png（如果重新生成）
检查图片生成技能；如果有多个，询问偏好
处理提示词 frontmatter 中的参考：
- direct 用法 → 通过 --ref 传递（使用支持 ref 的后端）
- style/palette → 提取特征，附加到提示词
生成：使用提示词文件、输出路径、宽高比调用技能
失败时：自动重试一次

步骤 5：完成报告

封面已生成！

主题：[主题]
类型：[类型] | 调色板：[调色板] | 渲染风格：[渲染风格]
文本：[文本] | 氛围：[氛围] | 字体：[字体] | 宽高比：[比例]
标题：[标题 或 "纯视觉"]
语言：[语言] | 水印：[启用/禁用]
参考：[N 张图片 或 "提取的样式" 或 "无"]
位置：[目录路径]

文件：
✓ source-{slug}.{ext}
✓ prompts/cover.md
✓ cover.png

操作	步骤
重新生成	备份 → 首先更新提示词文件 → 重新生成
更改维度	备份 → 确认新值 → 更新提示词 → 重新生成

留白：40-60% 的呼吸空间
视觉锚点：主要元素居中或偏左
角色：简化的剪影；不要写实的人类
标题：使用用户/源中的确切标题；绝不编造

通过 EXTEND.md 进行自定义配置。路径参见步骤 0。

🇺🇸English

Cover Image Generator

Generate elegant cover images for articles with 5-dimensional customization.

Usage

# Auto-select dimensions based on content
/baoyu-cover-image path/to/article.md

# Quick mode: skip confirmation
/baoyu-cover-image article.md --quick

# Specify dimensions
/baoyu-cover-image article.md --type conceptual --palette warm --rendering flat-vector

# Style presets (shorthand for palette + rendering)
/baoyu-cover-image article.md --style blueprint

# With reference images
/baoyu-cover-image article.md --ref style-ref.png

# Direct content input
/baoyu-cover-image --palette mono --aspect 1:1 --quick
[paste content]

Options

Option	Description
`--type <name>`	hero, conceptual, typography, metaphor, scene, minimal
`--palette <name>`	warm, elegant, cool, dark, earth, vivid, pastel, mono, retro, duotone
`--rendering <name>`	flat-vector, hand-drawn, painterly, digital, pixel, chalk, screen-print
`--style <name>`	Preset shorthand (see Style Presets)
`--text <level>`	none, title-only, title-subtitle, text-rich
`--mood <level>`	subtle, balanced, bold
`--font <name>`	clean, handwritten, serif, display
`--aspect <ratio>`	16:9 (default), 2.35:1, 4:3, 3:2, 1:1, 3:4
`--lang <code>`	Title language (en, zh, ja, etc.)
`--no-title`	Alias for `--text none`
`--quick`	Skip confirmation, use auto-selection
`--ref <files...>`	Reference images for style/composition guidance

Five Dimensions

Dimension	Values	Default
Type	hero, conceptual, typography, metaphor, scene, minimal	auto
Palette	warm, elegant, cool, dark, earth, vivid, pastel, mono, retro, duotone	auto
Rendering	flat-vector, hand-drawn, painterly, digital, pixel, chalk, screen-print	auto
Text	none, title-only, title-subtitle, text-rich	title-only
Mood	subtle, balanced, bold	balanced
Font	clean, handwritten, serif, display	clean

Auto-selection rules: references/auto-selection.md

Galleries

Types : hero, conceptual, typography, metaphor, scene, minimal → Details: references/types.md

Palettes : warm, elegant, cool, dark, earth, vivid, pastel, mono, retro, duotone → Details: references/palettes/

Renderings : flat-vector, hand-drawn, painterly, digital, pixel, chalk, screen-print → Details: references/renderings/

Text Levels : none (pure visual) | title-only (default) | title-subtitle | text-rich (with tags) → Details: references/dimensions/text.md

Mood Levels : subtle (low contrast) | balanced (default) | bold (high contrast) → Details: references/dimensions/mood.md

Fonts : clean (sans-serif) | handwritten | serif | display (bold decorative) → Details: references/dimensions/font.md

File Structure

Output directory per default_output_dir preference:

same-dir: {article-dir}/
imgs-subdir: {article-dir}/imgs/
independent (default): cover-image/{topic-slug}/

<output-dir>/ ├── source-{slug}.{ext} # Source files ├── refs/ # Reference images (if provided) │ ├── ref-01-{slug}.{ext} │ └── ref-01-{slug}.md # Description file ├── prompts/cover.md # Generation prompt └── cover.png # Output image

Slug : 2-4 words, kebab-case. Conflict: append -YYYYMMDD-HHMMSS

Workflow

Progress Checklist

Cover Image Progress:
- [ ] Step 0: Check preferences (EXTEND.md) ⛔ BLOCKING
- [ ] Step 1: Analyze content + save refs + determine output dir
- [ ] Step 2: Confirm options (6 dimensions) ⚠️ unless --quick
- [ ] Step 3: Create prompt
- [ ] Step 4: Generate image
- [ ] Step 5: Completion report

Flow

Input → [Step 0: Preferences] ─┬─ Found → Continue
                               └─ Not found → First-Time Setup ⛔ BLOCKING → Save EXTEND.md → Continue
        ↓
Analyze + Save Refs → [Output Dir] → [Confirm: 6 Dimensions] → Prompt → Generate → Complete
                                              ↓
                                     (skip if --quick or all specified)

Step 0: Load Preferences ⛔ BLOCKING

Check EXTEND.md existence (priority: project → user):

# macOS, Linux, WSL, Git Bash
test -f .baoyu-skills/baoyu-cover-image/EXTEND.md && echo "project"
test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-cover-image/EXTEND.md" && echo "xdg"
test -f "$HOME/.baoyu-skills/baoyu-cover-image/EXTEND.md" && echo "user"



# PowerShell (Windows)
if (Test-Path .baoyu-skills/baoyu-cover-image/EXTEND.md) { "project" }
$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
if (Test-Path "$xdg/baoyu-skills/baoyu-cover-image/EXTEND.md") { "xdg" }
if (Test-Path "$HOME/.baoyu-skills/baoyu-cover-image/EXTEND.md") { "user" }

Result	Action
Found	Load, display summary → Continue
Not found	⛔ Run first-time setup (references/config/first-time-setup.md) → Save → Continue

CRITICAL : If not found, complete setup BEFORE any other steps or questions.

Step 1: Analyze Content

Save reference images (if provided) → references/workflow/reference-images.md
Save source content (if pasted, save to source.md)
Analyze content : topic, tone, keywords, visual metaphors
Deep analyze references ⚠️: Extract specific, concrete elements (see reference-images.md)
Detect language : Compare source, user input, EXTEND.md preference
Determine output directory : Per File Structure rules

⚠️ People in Reference Images:

If reference images contain people who should appear in the cover:

Model supports--ref (default): Copy image to refs/, pass via --ref at generation. No description file needed — the model sees the face directly.
Model does NOT support--ref (Jimeng, Seedream 3.0): Create refs/ref-NN-{slug}.md with per-character description (hair, glasses, skin tone, clothing). Embed as MUST/REQUIRED instructions in prompt text.

See reference-images.md for full decision table.

Step 2: Confirm Options ⚠️

MUST useAskUserQuestion tool to present options as interactive selection — NOT plain text tables. Present up to 4 questions in a single AskUserQuestion call (Type, Palette, Rendering, Font + Settings). Each question shows the recommended option first with reason, followed by alternatives.

Full confirmation flow and question format: references/workflow/confirm-options.md

Condition	Skipped	Still Asked
`--quick` or `quick_mode: true`	6 dimensions	Aspect ratio (unless `--aspect`)
All 6 + `--aspect` specified	All	None

Step 3: Create Prompt

Save to prompts/cover.md. Template: references/workflow/prompt-template.md

CRITICAL - References in Frontmatter :

Files saved to refs/ → Add to frontmatter references list
Style extracted verbally (no file) → Omit references, describe in body
Before writing → Verify: test -f refs/ref-NN-{slug}.{ext}

Reference elements in body MUST be detailed, prefixed with "MUST"/"REQUIRED", with integration approach.

Step 4: Generate Image

Backup existing cover.png if regenerating
Check image generation skills ; if multiple, ask preference
Process references from prompt frontmatter:
- direct usage → pass via --ref (use ref-capable backend)
- style/palette → extract traits, append to prompt
Generate : Call skill with prompt file, output path, aspect ratio
On failure: auto-retry once

Step 5: Completion Report

Cover Generated!

Topic: [topic]
Type: [type] | Palette: [palette] | Rendering: [rendering]
Text: [text] | Mood: [mood] | Font: [font] | Aspect: [ratio]
Title: [title or "visual only"]
Language: [lang] | Watermark: [enabled/disabled]
References: [N images or "extracted style" or "none"]
Location: [directory path]

Files:
✓ source-{slug}.{ext}
✓ prompts/cover.md
✓ cover.png

Image Modification

Action	Steps
Regenerate	Backup → Update prompt file FIRST → Regenerate
Change dimension	Backup → Confirm new value → Update prompt → Regenerate

Composition Principles

Whitespace : 40-60% breathing room
Visual anchor : Main element centered or offset left
Characters : Simplified silhouettes; NO realistic humans
Title : Use exact title from user/source; never invent

Extension Support

Custom configurations via EXTEND.md. See Step 0 for paths.

Schema: references/config/preferences-schema.md

References

Dimensions : text.md | mood.md | font.md Palettes : references/palettes/ Renderings : references/renderings/ Types : references/types.md Auto-Selection : references/auto-selection.md Style Presets : references/style-presets.md Compatibility : references/compatibility.md Visual Elements : references/visual-elements.md Workflow : confirm-options.md | prompt-template.md | : | |

Weekly Installs

12.9K

Repository

jimliu/baoyu-skills

GitHub Stars

11.3K

First Seen

Jan 19, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykPass

Installed on

opencode11.7K

gemini-cli11.3K

codex11.1K

cursor10.7K

github-copilot10.3K

amp9.9K

头脑风暴技能：AI协作设计流程，将创意转化为完整规范与实施计划

75,000 周安装