baoyu-cover-image
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseCover Image Generator
封面图生成器
Generate elegant cover images for articles with 5-dimensional customization.
可通过5维度自定义生成精美的文章封面图。
Usage
使用方法
bash
undefinedbash
undefinedAuto-select all dimensions based on content
根据内容自动选择所有维度
/baoyu-cover-image path/to/article.md
/baoyu-cover-image path/to/article.md
Quick mode: skip confirmation, use auto-selection
快速模式:跳过确认,使用自动选择
/baoyu-cover-image article.md --quick
/baoyu-cover-image article.md --quick
Specify dimensions (new 5D system)
指定维度(全新5D系统)
/baoyu-cover-image article.md --type conceptual --palette warm --rendering flat-vector
/baoyu-cover-image article.md --text title-subtitle --mood bold
/baoyu-cover-image article.md --type conceptual --palette warm --rendering flat-vector
/baoyu-cover-image article.md --text title-subtitle --mood bold
Style presets (backward-compatible shorthand for palette + rendering)
风格预设(palette + rendering的向后兼容简写)
/baoyu-cover-image article.md --style blueprint
/baoyu-cover-image article.md --style blueprint --rendering hand-drawn # override rendering
/baoyu-cover-image article.md --style blueprint
/baoyu-cover-image article.md --style blueprint --rendering hand-drawn # 覆盖渲染风格
Visual only (no title text)
仅展示视觉效果(无标题文本)
/baoyu-cover-image article.md --no-title
/baoyu-cover-image article.md --no-title
Direct content input
直接输入内容
/baoyu-cover-image
[paste content]
/baoyu-cover-image
[paste content]
Direct input with options
带选项的直接输入
/baoyu-cover-image --palette mono --rendering digital --aspect 1:1 --quick
[paste content]
/baoyu-cover-image --palette mono --rendering digital --aspect 1:1 --quick
[paste content]
With reference images
结合参考图片
/baoyu-cover-image article.md --ref style-ref.png
/baoyu-cover-image article.md --ref ref1.png ref2.png --quick
undefined/baoyu-cover-image article.md --ref style-ref.png
/baoyu-cover-image article.md --ref ref1.png ref2.png --quick
undefinedOptions
选项
| Option | Description |
|---|---|
| Cover type: hero, conceptual, typography, metaphor, scene, minimal |
| Color palette: warm, elegant, cool, dark, earth, vivid, pastel, mono, retro |
| Rendering style: flat-vector, hand-drawn, painterly, digital, pixel, chalk |
| Preset shorthand (expands to palette + rendering, see Style Presets) |
| Text density: none, title-only, title-subtitle, text-rich |
| Emotional intensity: subtle, balanced, bold |
| 16:9 (default), 2.35:1, 4:3, 3:2, 1:1, 3:4 |
| Title language (en, zh, ja, etc.) |
| Alias for |
| Skip confirmation, use auto-selection for missing dimensions |
| Reference images for style/composition guidance |
| 选项 | 描述 |
|---|---|
| 封面类型:hero、conceptual、typography、metaphor、scene、minimal |
| 调色板:warm、elegant、cool、dark、earth、vivid、pastel、mono、retro |
| 渲染风格:flat-vector、hand-drawn、painterly、digital、pixel、chalk |
| 预设简写(展开为palette + rendering,详见Style Presets) |
| 文本密度:none、title-only、title-subtitle、text-rich |
| 情感强度:subtle、balanced、bold |
| 16:9(默认)、2.35:1、4:3、3:2、1:1、3:4 |
| 标题语言(en、zh、ja等) |
| |
| 跳过确认,对未指定的维度使用自动选择 |
| 用于风格/构图参考的图片 |
Five Dimensions
五个维度
| Dimension | Controls | Values | Default |
|---|---|---|---|
| Type | Visual composition, information structure | hero, conceptual, typography, metaphor, scene, minimal | auto |
| Palette | Colors, color scheme, decorative hints | warm, elegant, cool, dark, earth, vivid, pastel, mono, retro | auto |
| Rendering | Line quality, texture, depth, element style | flat-vector, hand-drawn, painterly, digital, pixel, chalk | auto |
| Text | Text density, information hierarchy | none, title-only, title-subtitle, text-rich | title-only |
| Mood | Emotional intensity, visual weight | subtle, balanced, bold | balanced |
Dimensions can be freely combined. Auto-selection rules: references/auto-selection.md
| 维度 | 控制项 | 取值 | 默认值 |
|---|---|---|---|
| Type | 视觉构图、信息结构 | hero、conceptual、typography、metaphor、scene、minimal | auto |
| Palette | 色彩、配色方案、装饰细节 | warm、elegant、cool、dark、earth、vivid、pastel、mono、retro | auto |
| Rendering | 线条质感、纹理、深度、元素风格 | flat-vector、hand-drawn、painterly、digital、pixel、chalk | auto |
| Text | 文本密度、信息层级 | none、title-only、title-subtitle、text-rich | title-only |
| Mood | 情感强度、视觉权重 | subtle、balanced、bold | balanced |
维度可自由组合。自动选择规则:references/auto-selection.md
Type Gallery
类型图库
| Type | Description | Best For |
|---|---|---|
| Large visual impact, title overlay | Product launch, brand promotion, major announcements |
| Concept visualization, abstract core ideas | Technical articles, methodology, architecture design |
| Text-focused layout, prominent title | Opinion pieces, quotes, insights |
| Visual metaphor, concrete expressing abstract | Philosophy, growth, personal development |
| Atmospheric scene, narrative feel | Stories, travel, lifestyle |
| Minimalist composition, generous whitespace | Zen, focus, core concepts |
Type composition details: references/types.md
| 类型 | 描述 | 适用场景 |
|---|---|---|
| 视觉冲击力强,标题叠加 | 产品发布、品牌推广、重大公告 |
| 概念可视化,抽象核心思想 | 技术文章、方法论、架构设计 |
| 文本聚焦布局,标题突出 | 观点文章、名言警句、洞察分享 |
| 视觉隐喻,具象化抽象内容 | 哲学、成长、个人发展 |
| 氛围感场景,叙事感强 | 故事、旅行、生活方式 |
| 极简构图,留白充足 | 禅意、专注、核心概念 |
类型构图细节:references/types.md
Palette Gallery
调色板图库
| Palette | Vibe | Primary Colors |
|---|---|---|
| Friendly, approachable | Orange, golden yellow, terracotta |
| Sophisticated, refined | Soft coral, muted teal, dusty rose |
| Technical, professional | Engineering blue, navy, cyan |
| Cinematic, premium | Electric purple, cyan, magenta |
| Natural, organic | Forest green, sage, earth brown |
| Energetic, bold | Bright red, neon green, electric blue |
| Gentle, whimsical | Soft pink, mint, lavender |
| Clean, focused | Black, near-black, white |
| Nostalgic, vintage | Muted orange, dusty pink, maroon |
Palette definitions: references/palettes/
| 调色板 | 氛围 | 主色调 |
|---|---|---|
| 友好、亲切 | 橙色、金黄色、赤陶色 |
| 精致、高雅 | 柔和珊瑚色、暗蓝绿色、灰粉色 |
| 科技感、专业 | 工程蓝、藏青、青色 |
| 电影感、高端 | 电光紫、青色、品红 |
| 自然、有机 | 森林绿、鼠尾草绿、土棕色 |
| 活力、大胆 | 亮红、霓虹绿、电光蓝 |
| 柔和、奇幻 | 浅粉、薄荷绿、薰衣草紫 |
| 简洁、聚焦 | 黑、近黑、白 |
| 怀旧、复古 | 暗橙色、灰粉色、栗色 |
调色板定义:references/palettes/
Rendering Gallery
渲染风格图库
| Rendering | Description | Key Characteristics |
|---|---|---|
| Clean modern vector | Uniform outlines, flat fills, geometric icons |
| Sketchy organic illustration | Imperfect strokes, paper texture, doodles |
| Soft watercolor/paint | Brush strokes, color bleeds, soft edges |
| Polished modern digital | Precise edges, subtle gradients, UI components |
| Retro 8-bit pixel art | Pixel grid, dithering, chunky shapes |
| Chalk on blackboard | Chalk strokes, dust effects, board texture |
Rendering definitions: references/renderings/
| 渲染风格 | 描述 | 核心特征 |
|---|---|---|
| 简洁现代矢量风 | 统一轮廓、平涂填充、几何图标 |
| 手绘有机插画风 | 不规则笔触、纸张纹理、涂鸦感 |
| 柔和水彩/油画风 | 笔触痕迹、色彩晕染、柔和边缘 |
| 精致现代数字风 | 精准边缘、微妙渐变、UI组件感 |
| 复古8位像素风 | 像素网格、抖动效果、块状造型 |
| 黑板粉笔风 | 粉笔笔触、粉尘效果、黑板纹理 |
渲染风格定义:references/renderings/
Text & Mood
文本与氛围
| Text Level | Title | Subtitle | Tags | Use Case |
|---|---|---|---|---|
| - | - | - | Pure visual, no text |
| ✓ | - | - | Simple headline (default) |
| ✓ | ✓ | - | Title + supporting context |
| ✓ | ✓ | ✓ (2-4) | Information-dense |
| Mood | Contrast | Saturation | Weight | Use Case |
|---|---|---|---|---|
| Low | Muted | Light | Corporate, thought leadership |
| Medium | Normal | Medium | General articles (default) |
| High | Vivid | Heavy | Announcements, promotions |
Full guides: references/dimensions/text.md | references/dimensions/mood.md
| 文本层级 | 标题 | 副标题 | 标签 | 适用场景 |
|---|---|---|---|---|
| - | - | - | 纯视觉效果,无文本 |
| ✓ | - | - | 简单标题(默认) |
| ✓ | ✓ | - | 标题+辅助说明 |
| ✓ | ✓ | ✓(2-4个) | 信息密集型 |
| 氛围 | 对比度 | 饱和度 | 视觉权重 | 适用场景 |
|---|---|---|---|---|
| 低 | 柔和 | 轻量 | 企业内容、思想领导力 |
| 中等 | 正常 | 中等 | 通用文章(默认) |
| 高 | 鲜艳 | 厚重 | 公告、推广内容 |
完整指南:references/dimensions/text.md | references/dimensions/mood.md
Style Presets & Compatibility
风格预设与兼容性
- Style Presets: expands to palette + rendering. See references/style-presets.md
--style X - Compatibility Matrices: Palette×Rendering, Type×Rendering, Type×Text, Type×Mood. See references/compatibility.md
- ✓✓ = highly recommended | ✓ = compatible | ✗ = not recommended
- 风格预设:展开为palette + rendering。详见references/style-presets.md
--style X - 兼容性矩阵:Palette×Rendering、Type×Rendering、Type×Text、Type×Mood。详见references/compatibility.md
- ✓✓ = 高度推荐 | ✓ = 兼容 | ✗ = 不推荐
File Structure
文件结构
Output directory depends on preference:
default_output_dir| Preference | Output Path |
|---|---|
| |
| |
| |
| Pasted content | |
<output-dir>/
├── source-{slug}.{ext} # Source files (text, images, etc.)
├── refs/ # Reference images (if provided)
│ ├── ref-01-{slug}.{ext}
│ ├── ref-01-{slug}.md # Description file (optional)
│ ├── ref-02-{slug}.{ext}
│ ├── ref-02-{slug}.md # Description file (optional)
│ └── extracted-style.md # Verbally extracted style (if no file path)
├── prompts/cover.md # Generation prompt
└── cover.png # Output imageSlug: Extract main topic (2-4 words, kebab-case). Example: "The Future of AI" →
Conflict: If directory exists, append timestamp:
Source Files: Copy all sources with naming (multiple supported)
future-of-ai{topic-slug}-YYYYMMDD-HHMMSSsource-{slug}.{ext}输出目录取决于偏好设置:
default_output_dir| 偏好设置 | 输出路径 |
|---|---|
| |
| |
| |
| 粘贴的内容 | |
<output-dir>/
├── source-{slug}.{ext} # 源文件(文本、图片等)
├── refs/ # 参考图片(若提供)
│ ├── ref-01-{slug}.{ext}
│ ├── ref-01-{slug}.md # 描述文件(可选)
│ ├── ref-02-{slug}.{ext}
│ ├── ref-02-{slug}.md # 描述文件(可选)
│ └── extracted-style.md # 提取的风格描述(若无文件路径)
├── prompts/cover.md # 生成提示词
└── cover.png # 输出图片Slug:提取主题核心(2-4个单词,短横线分隔)。示例:"The Future of AI" →
冲突处理:若目录已存在,追加时间戳:
源文件:复制所有源文件并命名为(支持多个)
future-of-ai{topic-slug}-YYYYMMDD-HHMMSSsource-{slug}.{ext}Workflow
工作流
Progress Checklist
进度检查清单
Cover Image Progress:
- [ ] Step 0: Check preferences (EXTEND.md) ⛔ BLOCKING
- [ ] Found → load preferences → continue
- [ ] Not found → run first-time setup → MUST complete before Step 1
- [ ] Step 1: Analyze content + determine output directory
- [ ] 1.1 Reference images ⚠️ (if provided)
- [ ] File path given → saved to refs/ ✓
- [ ] No path → asked user OR extracted verbally
- [ ] 1.2 Output directory determined
- [ ] Step 2: Confirm options (5 dimensions) ⚠️ REQUIRED unless --quick or all specified
- [ ] Step 3: Create prompt
- [ ] References in prompt ONLY if files exist in refs/
- [ ] Extracted style/palette appended to prompt body (if no file)
- [ ] Step 4: Generate image
- [ ] 4.1 References verified before generation
- [ ] 4.2 Pass refs via --ref if skill supports AND files exist
- [ ] Step 5: Completion report封面图生成进度:
- [ ] 步骤0:检查偏好设置(EXTEND.md) ⛔ 阻塞项
- [ ] 找到 → 加载偏好设置 → 继续
- [ ] 未找到 → 运行首次设置 → 必须完成后才能进入步骤1
- [ ] 步骤1:分析内容 + 确定输出目录
- [ ] 1.1 参考图片 ⚠️(若提供)
- [ ] 提供文件路径 → 保存至refs/ ✓
- [ ] 无路径 → 询问用户或提取描述
- [ ] 1.2 确定输出目录
- [ ] 步骤2:确认选项(5个维度) ⚠️ 必需,除非使用--quick或所有参数已指定
- [ ] 步骤3:创建提示词
- [ ] 仅当refs/目录存在文件时,才在提示词中加入参考
- [ ] 若无文件,将提取的风格/调色板追加至提示词主体
- [ ] 步骤4:生成图片
- [ ] 4.1 生成前验证参考内容
- [ ] 4.2 若技能支持且文件存在,通过--ref传递参考图片
- [ ] 步骤5:完成报告Flow
流程
Input → [Step 0: Preferences] ─┬─ Found → Continue
│
└─ Not found → First-Time Setup ⛔ BLOCKING
│
└─ Complete setup → Save EXTEND.md → Continue
│
┌───────────────────────────────────────────────────────────────────────────┘
↓
Analyze + Save Refs → [Output Dir ⚠️] → [Confirm: 5 Dimensions] → Prompt → Generate → Complete
↓
(skip if --quick or all specified)输入 → [步骤0:偏好设置] ─┬─ 找到 → 继续
│
└─ 未找到 → 首次设置 ⛔ 阻塞项
│
└─ 完成设置 → 保存EXTEND.md → 继续
│
┌───────────────────────────────────────────────────────────────────────────┘
↓
分析 + 保存参考图片 → [输出目录 ⚠️] → [确认:5个维度] → 提示词 → 生成 → 完成
↓
(若使用--quick或所有参数已指定则跳过)Step 0: Load Preferences (EXTEND.md) ⛔ BLOCKING
步骤0:加载偏好设置(EXTEND.md) ⛔ 阻塞项
Purpose: Load user preferences or run first-time setup.
CRITICAL: If EXTEND.md not found, MUST complete first-time setup before ANY other questions or steps. Do NOT proceed to content analysis, do NOT ask about reference images, do NOT ask about dimensions — ONLY complete the preferences setup first.
Use Bash to check EXTEND.md existence (priority order):
bash
undefined目的:加载用户偏好设置或运行首次设置。
关键:若未找到EXTEND.md,必须先完成首次设置,才能进行任何其他步骤。不得继续内容分析、询问参考图片或维度设置,仅能完成偏好设置。
使用Bash检查EXTEND.md是否存在(优先级顺序):
bash
undefinedCheck project-level first
先检查项目级
test -f .baoyu-skills/baoyu-cover-image/EXTEND.md && echo "project"
test -f .baoyu-skills/baoyu-cover-image/EXTEND.md && echo "project"
Then user-level (cross-platform: $HOME works on macOS/Linux/WSL)
再检查用户级(跨平台:$HOME适用于macOS/Linux/WSL)
test -f "$HOME/.baoyu-skills/baoyu-cover-image/EXTEND.md" && echo "user"
| Result | Action |
|--------|--------|
| Found | Read, parse, display preferences summary → Continue to Step 1 |
| Not found | ⛔ **BLOCKING**: Run first-time setup ONLY ([references/config/first-time-setup.md](references/config/first-time-setup.md)) → Complete and save EXTEND.md → Then continue to Step 1 |
**Preferences Summary** (when found):
Preferences loaded from [project/user]:
• Watermark: [enabled/disabled] [content if enabled]
• Type/Palette/Rendering: [value or "auto"]
• Text: [value or "title-only"] | Mood: [value or "balanced"]
• Aspect: [default_aspect] | Output: [dir or "not set — will ask in Step 1.5"]
• Quick mode: [enabled/disabled] | Language: [value or "auto"]
**EXTEND.md Supports**: Watermark | Preferred type | Preferred palette | Preferred rendering | Preferred text | Preferred mood | Default aspect ratio | Default output directory | Quick mode | Custom palette definitions | Language preference
Schema: [references/config/preferences-schema.md](references/config/preferences-schema.md)test -f "$HOME/.baoyu-skills/baoyu-cover-image/EXTEND.md" && echo "user"
| 结果 | 操作 |
|--------|--------|
| 找到 | 读取、解析、展示偏好设置摘要 → 进入步骤1 |
| 未找到 | ⛔ **阻塞项**:仅运行首次设置([references/config/first-time-setup.md](references/config/first-time-setup.md)) → 完成设置并保存EXTEND.md → 进入步骤1 |
**偏好设置摘要**(找到时):
从[项目/用户]加载偏好设置:
• 水印:[启用/禁用] [启用时的内容]
• Type/Palette/Rendering:[取值或“auto”]
• Text:[取值或“title-only”] | Mood:[取值或“balanced”]
• 比例:[default_aspect] | 输出:[目录或“未设置 — 将在步骤1.5询问”]
• 快速模式:[启用/禁用] | 语言:[取值或“auto”]
**EXTEND.md支持**:水印 | 首选type | 首选palette | 首选rendering | 首选text | 首选mood | 默认比例 | 默认输出目录 | 快速模式 | 自定义调色板定义 | 语言偏好
Schema:[references/config/preferences-schema.md](references/config/preferences-schema.md)Step 1: Analyze Content
步骤1:分析内容
1.0 Detect & Save Reference Images ⚠️ REQUIRED if images provided
Check if user provided reference images. Handle based on input type:
| Input Type | Action |
|---|---|
| Image file path provided | Copy to |
| Image in conversation (no path) | ASK user for file path with AskUserQuestion |
| User can't provide path | Extract style/palette verbally → append to prompt (NO frontmatter references) |
CRITICAL: Only add to prompt frontmatter if files are ACTUALLY SAVED to directory.
referencesrefs/If user provides file path:
- Copy to (NN = 01, 02, ...)
refs/ref-NN-{slug}.{ext} - Create description:
refs/ref-NN-{slug}.md - Verify files exist before proceeding
If user can't provide path (extracted verbally):
- Analyze image visually, extract: colors, style, composition
- Create with extracted info
refs/extracted-style.md - DO NOT add to prompt frontmatter
references - Instead, append extracted style/colors directly to prompt text
Description File Format (only when file saved):
yaml
---
ref_id: NN
filename: ref-NN-{slug}.{ext}
usage: direct | style | palette
---
[User's description or auto-generated description]| Usage | When to Use |
|---|---|
| Reference matches desired output closely |
| Extract visual style characteristics only |
| Extract color scheme only |
Verification (only for saved files):
Reference Images Saved:
- ref-01-{slug}.png ✓ (can use --ref)
- ref-02-{slug}.png ✓ (can use --ref)Or for extracted style:
Reference Style Extracted (no file):
- Colors: #E8756D coral, #7ECFC0 mint...
- Style: minimal flat vector, clean lines...
→ Will append to prompt text (not --ref)1.1 Save Source Content
- If pasted, save to in target directory; if file path, use as-is
source.md - Backup rule: If exists, rename to
source.mdsource-backup-YYYYMMDD-HHMMSS.md
1.2 Content Analysis
- Extract topic, core message, tone, keywords
- Identify visual metaphors
- Detect content type
1.3 Reference Image Analysis (if provided in Step 1.0)
For each reference image:
| Analysis | Description |
|---|---|
| Visual characteristics | Style, colors, composition |
| Content/subject | What the reference depicts |
| Style match | Which type/palette/rendering align |
| Usage recommendation | |
1.4 Language Detection
- Detect source language
- Note user's input language
- Compare with EXTEND.md preference
1.5 Determine Output Directory
- Per File Structure rules
- If no preference + file path input, include in Step 2 Q4
default_output_dir
1.0 检测并保存参考图片 ⚠️ 若提供图片则必需
检查用户是否提供参考图片,根据输入类型处理:
| 输入类型 | 操作 |
|---|---|
| 提供图片文件路径 | 复制至 |
| 对话中包含图片(无路径) | 通过AskUserQuestion询问用户文件路径 |
| 用户无法提供路径 | 口头提取风格/调色板 → 追加至提示词(不添加前置引用) |
关键:仅当文件实际保存至目录时,才在提示词的YAML前置部分添加字段。
refs/references若用户提供文件路径:
- 复制至(NN = 01, 02, ...)
refs/ref-NN-{slug}.{ext} - 创建描述文件:
refs/ref-NN-{slug}.md - 继续前验证文件是否存在
若用户无法提供路径(口头提取):
- 视觉分析图片,提取:色彩、风格、构图
- 创建,写入提取的信息
refs/extracted-style.md - 不在提示词前置部分添加字段
references - 而是将提取的风格/色彩直接追加至提示词文本
描述文件格式(仅当文件已保存时):
yaml
---
ref_id: NN
filename: ref-NN-{slug}.{ext}
usage: direct | style | palette
---
[用户描述或自动生成的描述]| Usage | 使用场景 |
|---|---|
| 参考图片与期望输出高度匹配 |
| 仅提取视觉风格特征 |
| 仅提取配色方案 |
验证(仅针对已保存的文件):
参考图片已保存:
- ref-01-{slug}.png ✓(可使用--ref)
- ref-02-{slug}.png ✓(可使用--ref)针对口头提取的风格:
提取参考风格(无文件):
- 色彩:#E8756D珊瑚色、#7ECFC0薄荷绿...
- 风格:极简扁平矢量、简洁线条...
→ 将追加至提示词文本(不使用--ref)1.1 保存源内容
- 若为粘贴内容,保存至目标目录的;若为文件路径,直接使用原文件
source.md - 备份规则:若已存在,重命名为
source.mdsource-backup-YYYYMMDD-HHMMSS.md
1.2 内容分析
- 提取主题、核心信息、语气、关键词
- 识别视觉隐喻
- 检测内容类型
1.3 参考图片分析(若步骤1.0中提供)
针对每张参考图片:
| 分析项 | 描述 |
|---|---|
| 视觉特征 | 风格、色彩、构图 |
| 内容/主体 | 参考图片描绘的对象 |
| 风格匹配 | 对应的type/palette/rendering |
| 使用建议 | |
1.4 语言检测
- 检测源内容语言
- 记录用户输入语言
- 与EXTEND.md偏好设置对比
1.5 确定输出目录
- 遵循文件结构规则
- 若无偏好且为文件路径输入,将在步骤2的问题4中询问
default_output_dir
Step 2: Confirm Options ⚠️
步骤2:确认选项 ⚠️
Validate all 5 dimensions + aspect ratio. Full confirmation flow: references/workflow/confirm-options.md
Skip Conditions:
| Condition | Skipped | Still Asked |
|---|---|---|
| 5 dimensions | Aspect ratio (unless |
All 5 + | All | None |
验证所有5个维度 + 比例。完整确认流程:references/workflow/confirm-options.md
跳过条件:
| 条件 | 跳过项 | 仍需询问项 |
|---|---|---|
| 5个维度 | 比例(除非指定 |
所有5个维度 + | 全部 | 无 |
Step 3: Create Prompt
步骤3:创建提示词
Backup rule: If exists, rename to
prompts/cover.mdprompts/cover-backup-YYYYMMDD-HHMMSS.mdSave to . Full template: references/workflow/prompt-template.md
prompts/cover.mdCRITICAL - References in YAML Frontmatter:
When reference files are saved to , MUST add field in frontmatter:
refs/referencesyaml
---
type: cover
palette: warm
rendering: flat-vector
references:
- ref_id: 01
filename: refs/ref-01-podcast-thumbnail.jpg
usage: style
---| Rule | Action |
|---|---|
Files saved to | Add to frontmatter |
| Style extracted verbally (no file) | Omit |
| Before writing | Verify: |
Reference Embedding:
| Situation | Frontmatter | Body |
|---|---|---|
Reference file saved to | Add to | Brief style note |
| Style extracted verbally (no file) | Omit | Full style description |
| File in frontmatter but doesn't exist | ERROR - fix or remove | — |
备份规则:若已存在,重命名为
prompts/cover.mdprompts/cover-backup-YYYYMMDD-HHMMSS.md保存至。完整模板:references/workflow/prompt-template.md
prompts/cover.md关键 - YAML前置部分的引用:
当参考文件已保存至目录时,必须在前置部分添加字段:
refs/referencesyaml
---
type: cover
palette: warm
rendering: flat-vector
references:
- ref_id: 01
filename: refs/ref-01-podcast-thumbnail.jpg
usage: style
---| 规则 | 操作 |
|---|---|
文件已保存至 | 添加至前置部分的 |
| 口头提取风格(无文件) | 省略 |
| 写入前 | 验证: |
引用嵌入:
| 场景 | 前置部分 | 主体部分 |
|---|---|---|
参考文件已保存至 | 添加至 | 简要风格说明 |
| 口头提取风格(无文件) | 省略 | 完整风格描述 |
| 前置部分包含文件但实际不存在 | 错误 - 修复提示词或移除引用 | — |
Step 4: Generate Image
步骤4:生成图片
4.1 Backup existing → (if regenerating)
cover.pngcover-backup-YYYYMMDD-HHMMSS.png4.2 Check available image generation skills; if multiple, ask user preference
4.3 Process References ⚠️ REQUIRED if references in frontmatter
Read from prompt frontmatter and process each entry:
references-
Parse frontmatter to get references list:yaml
references: - ref_id: 01 filename: refs/ref-01-podcast-thumbnail.jpg usage: style -
VERIFY each file exists:bash
test -f refs/ref-NN-{slug}.{ext} && echo "exists" || echo "MISSING"- If file MISSING → ERROR, fix prompt or remove from references
- If file exists → proceed with processing
-
Process based ontype:
usage
| Usage | Action | Example |
|---|---|---|
| Add reference path to | |
| Analyze reference, append style traits to prompt | "Style: clean lines, gradient backgrounds..." |
| Extract colors from reference, append to prompt | "Colors: #E8756D coral, #7ECFC0 mint..." |
- Check image generation skill capability:
Skill Supports | Action |
|---|---|
| Yes (e.g., baoyu-image-gen with Google) | Pass reference images via |
| No | Convert to text description, append to prompt |
Verification: Before generating, confirm reference processing:
Reference Processing:
- ref-01-brand.png: using as direct reference ✓
- ref-02-style.png: extracted palette ✓4.4 Generate
- Call selected skill with prompt file path, output path (), aspect ratio
cover.png - If references with usage AND skill supports
direct: include--refparameter--ref - On failure: auto-retry once before reporting error
4.1 备份现有 → (若重新生成)
cover.pngcover-backup-YYYYMMDD-HHMMSS.png4.2 检查可用的图片生成技能;若有多个,询问用户偏好
4.3 处理参考内容 ⚠️ 若前置部分包含引用则必需
**从提示词的YAML前置部分读取**并处理每个条目:
references-
解析前置部分获取引用列表:yaml
references: - ref_id: 01 filename: refs/ref-01-podcast-thumbnail.jpg usage: style -
验证每个文件是否存在:bash
test -f refs/ref-NN-{slug}.{ext} && echo "exists" || echo "MISSING"- 若文件不存在 → 错误,修复提示词或移除引用
- 若文件存在 → 继续处理
-
根据类型处理:
usage
| Usage | 操作 | 示例 |
|---|---|---|
| 将引用路径添加至 | |
| 分析参考图片,将风格特征追加至提示词 | "风格:简洁线条、渐变背景..." |
| 从参考图片提取色彩,追加至提示词 | "色彩:#E8756D珊瑚色、#7ECFC0薄荷绿..." |
- 检查图片生成技能的能力:
技能是否支持 | 操作 |
|---|---|
| 是(如集成Google的baoyu-image-gen) | 通过 |
| 否 | 转换为文本描述,追加至提示词 |
验证:生成前确认参考内容处理情况:
参考内容处理:
- ref-01-brand.png:用作直接参考 ✓
- ref-02-style.png:提取调色板 ✓4.4 生成
- 调用选定的技能,传入提示词文件路径、输出路径()、比例
cover.png - 若存在类型的引用且技能支持
direct:包含--ref参数--ref - 失败时:自动重试一次后再报告错误
Step 5: Completion Report
步骤5:完成报告
Cover Generated!
Topic: [topic]
Type: [type] | Palette: [palette] | Rendering: [rendering]
Text: [text] | Mood: [mood] | Aspect: [ratio]
Title: [title text or "visual only"]
Language: [lang] | Watermark: [enabled/disabled]
References: [N images (direct/style/palette) or "extracted style" or "none"]
Location: [directory path]
Files:
✓ source-{slug}.{ext}
[✓ refs/ref-01-{slug}.{ext} ... (if references saved)]
[✓ refs/ref-01-{slug}.md ... (description files)]
[✓ refs/extracted-style.md (if style extracted verbally)]
✓ prompts/cover.md
✓ cover.png
[✓ cover-backup-{timestamp}.png (if regenerated)]封面图已生成!
主题:[topic]
Type: [type] | Palette: [palette] | Rendering: [rendering]
Text: [text] | Mood: [mood] | 比例: [ratio]
标题: [标题文本或“仅视觉效果”]
语言: [lang] | 水印: [启用/禁用]
参考内容: [N张图片(direct/style/palette)或“提取的风格”或“无”]
位置: [目录路径]
文件:
✓ source-{slug}.{ext}
[✓ refs/ref-01-{slug}.{ext} ...(若保存参考图片)]
[✓ refs/ref-01-{slug}.md ...(描述文件)]
[✓ refs/extracted-style.md(若口头提取风格)]
✓ prompts/cover.md
✓ cover.png
[✓ cover-backup-{timestamp}.png(若重新生成)]Image Modification
图片修改
| Action | Steps |
|---|---|
| Regenerate | Backup existing → Update prompt file FIRST → Regenerate with same settings |
| Change dimension | Backup existing → Confirm new value → Update prompt file FIRST → Regenerate |
IMPORTANT: When regenerating, ALWAYS update the prompt file () FIRST before regenerating. This ensures changes are documented and reproducible.
prompts/cover.mdAll modifications automatically backup existing before regenerating.
cover.png| 操作 | 步骤 |
|---|---|
| 重新生成 | 备份现有文件 → 先更新提示词文件 → 使用相同设置重新生成 |
| 修改维度 | 备份现有文件 → 确认新取值 → 先更新提示词文件 → 重新生成 |
重要:重新生成时,必须先更新提示词文件(),再执行生成操作。确保变更已记录且可复现。
prompts/cover.md所有修改操作都会在重新生成前自动备份现有。
cover.pngNotes
注意事项
- Cover must be readable at small preview sizes
- Visual metaphors > literal representations
- Title: readable, impactful
- Two confirmation points: Step 0 (first-time setup) + Step 2 (options) - skip Step 2 with
--quick - Use confirmed language for title text
- Maintain watermark consistency if enabled
- Check compatibility matrices when selecting combinations
- is alias for
--no-title--text none - presets are backward-compatible; explicit
--style/--paletteoverride preset values--rendering
- 封面图在小尺寸预览时必须清晰可读
- 视觉隐喻优于字面表达
- 标题:清晰可读、有冲击力
- 两个确认节点:步骤0(首次设置)+ 步骤2(选项) - 使用可跳过步骤2
--quick - 标题文本使用已确认的语言
- 若启用水印,保持水印一致性
- 选择组合时参考兼容性矩阵
- 是
--no-title的别名--text none - 预设向后兼容;显式指定的
--style/--palette会覆盖预设值--rendering
Composition Principles
—
- Generous whitespace: 40-60% breathing room; avoid cluttered layouts
- Visual anchor: Main element centered or offset left (reserve right for title)
- Character handling: Simplified silhouettes or icon-style figures; NO realistic humans
- Icon vocabulary: Use simple, recognizable symbols (see references/visual-elements.md)
—
Title Handling
—
- Source: Use the exact title provided by user, or extract from source content
- Do NOT invent titles: Stay faithful to the original
- If no title in source and user doesn't provide one, ask user to specify
—
References
—
Dimensions: text.md | mood.md
Palettes: references/palettes/
Renderings: references/renderings/
Auto-Selection: references/auto-selection.md
Style Presets: references/style-presets.md
Compatibility: references/compatibility.md
Types: references/types.md
Visual Elements: references/visual-elements.md
Workflow: confirm-options.md | prompt-template.md
Config: preferences-schema.md | first-time-setup.md | watermark-guide.md
—