Token导航 LogoToken导航

Agent Skill · 图像处理

baoyu-cover-image(宝玉封面图)

用于辅助图像生成、图片编辑、视觉素材处理或图像模型工作流。它适合让 Agent 根据文本生成图片、处理背景、整理视觉提示词或调用相关图像工具。使用时需要确认输入图片、版权来源、输出格式和模型限制;涉及人物、品牌、商品或公开展示素材时,应额外核对授权、真实性和内容合规边界。

baoyu-cover-image 是图像处理类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证为 MIT,第三方扫描有提醒项,按安装量在图像处理类的 1,562 个 Skill 里排第 4。

总安装 474,240周安装 18,971GitHub Stars 16,779下载 153,520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
MIT

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:baoyu-cover-image(宝玉封面图)
来源仓库:https://github.com/jimliu/baoyu-skills
仓库路径:skills/baoyu-cover-image
安装命令:
npx skills add https://github.com/jimliu/baoyu-skills --skill baoyu-cover-image
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

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

这个 Skill 是做什么的

图像处理类 Skill 处理生成、裁剪、压缩和批量转换图片的任务。

生成跨 5 个独立尺寸和 3 个长宽比的可定制文章封面图像。

将 6 种图像类型(英雄、概念、排版、隐喻、场景、简约)与 10 种调色板和 7 种渲染风格相结合,实现细粒度的视觉控制 支持电影 (2.35:1)、宽屏 (16:9) 和方形 (1:1) 宽高比,以及其他比例(4:3、3:2、3:4) 自动分析文章内容以推荐尺寸,或接受类型、调色板、渲染、文本级别、情绪和字体的显式标志 包括参考图像支持以及封面中真实人物的人物分析,以及常见组合的样式预设快捷方式 生成与源文件和输出一起保存的详细提示,并通过 EXTEND.md 首选项提供可配置水印和多语言标题支持

来源仓库内路径:skills/baoyu-cover-image

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/jimliu/baoyu-skills --skill baoyu-cover-image;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

baoyu-cover-image 怎么安装?

在终端执行 npx skills add https://github.com/jimliu/baoyu-skills --skill baoyu-cover-image。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

baoyu-cover-image 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。

baoyu-cover-image 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

baoyu-cover-image 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

baoyu-cover-image 用的人多吗?

公开数据是累计安装 474,240 次,近一周安装 18,971 次,下载 153,520 次,GitHub 16,779 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。

baoyu-cover-image 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。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 来源仓库有 16,779 星,维护活跃度相对可查。

先想清楚的地方

  • 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。
  • 需要处理图像处理类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

图像处理类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
ai-image-generation

AI 图像生成 · Codex、Claude

4,365,552382调用外部服务未明确有提醒
openai-image-gen

OpenAI 图像生成 · OpenClaw

1,906,88432需要联网MIT-0有提醒
image

图像 · OpenClaw

525,99926需要联网MIT-0通过
baoyu-cover-image

宝玉封面图 · 本页

474,24016,779只读MIT有提醒
baoyu-image-gen

宝玉图像生成器 · Codex、Claude

468,00716,778接触敏感数据MIT通过
baoyu-xhs-images

baoyu xhs 图片 · Codex、Claude

467,20816,818只读MIT通过

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

name
baoyu-cover-image
description
Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 9 color palettes and 6 rendering styles. Supports cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects. Use when user asks to "generate cover image", "create article cover", "make cover", or mentions "封面图".

Cover Image Generator

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

Usage

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

# Quick mode: skip confirmation, use auto-selection
/baoyu-cover-image article.md --quick

# Specify dimensions (new 5D system)
/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)
/baoyu-cover-image article.md --style blueprint
/baoyu-cover-image article.md --style blueprint --rendering hand-drawn  # override rendering

# Visual only (no title text)
/baoyu-cover-image article.md --no-title

# Direct content input
/baoyu-cover-image
[paste content]

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

Options

OptionDescription
--type <name>Cover type: hero, conceptual, typography, metaphor, scene, minimal
--palette <name>Color palette: warm, elegant, cool, dark, earth, vivid, pastel, mono, retro
--rendering <name>Rendering style: flat-vector, hand-drawn, painterly, digital, pixel, chalk
--style <name>Preset shorthand (expands to palette + rendering, see Style Presets)
--text <level>Text density: none, title-only, title-subtitle, text-rich
--mood <level>Emotional intensity: subtle, balanced, bold
--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-titleAlias for --text none
--quickSkip confirmation, use auto-selection for missing dimensions

Five Dimensions

DimensionControlsValuesDefault
TypeVisual composition, information structurehero, conceptual, typography, metaphor, scene, minimalauto
PaletteColors, color scheme, decorative hintswarm, elegant, cool, dark, earth, vivid, pastel, mono, retroauto
RenderingLine quality, texture, depth, element styleflat-vector, hand-drawn, painterly, digital, pixel, chalkauto
TextText density, information hierarchynone, title-only, title-subtitle, text-richtitle-only
MoodEmotional intensity, visual weightsubtle, balanced, boldbalanced

Dimensions can be freely combined. Auto-selection rules: references/auto-selection.md

Type Gallery

TypeDescriptionBest For
heroLarge visual impact, title overlayProduct launch, brand promotion, major announcements
conceptualConcept visualization, abstract core ideasTechnical articles, methodology, architecture design
typographyText-focused layout, prominent titleOpinion pieces, quotes, insights
metaphorVisual metaphor, concrete expressing abstractPhilosophy, growth, personal development
sceneAtmospheric scene, narrative feelStories, travel, lifestyle
minimalMinimalist composition, generous whitespaceZen, focus, core concepts

Type composition details: references/types.md

Palette Gallery

PaletteVibePrimary Colors
warmFriendly, approachableOrange, golden yellow, terracotta
elegantSophisticated, refinedSoft coral, muted teal, dusty rose
coolTechnical, professionalEngineering blue, navy, cyan
darkCinematic, premiumElectric purple, cyan, magenta
earthNatural, organicForest green, sage, earth brown
vividEnergetic, boldBright red, neon green, electric blue
pastelGentle, whimsicalSoft pink, mint, lavender
monoClean, focusedBlack, near-black, white
retroNostalgic, vintageMuted orange, dusty pink, maroon

Palette definitions: references/palettes/

Rendering Gallery

RenderingDescriptionKey Characteristics
flat-vectorClean modern vectorUniform outlines, flat fills, geometric icons
hand-drawnSketchy organic illustrationImperfect strokes, paper texture, doodles
painterlySoft watercolor/paintBrush strokes, color bleeds, soft edges
digitalPolished modern digitalPrecise edges, subtle gradients, UI components
pixelRetro 8-bit pixel artPixel grid, dithering, chunky shapes
chalkChalk on blackboardChalk strokes, dust effects, board texture

Rendering definitions: references/renderings/

Text & Mood

Text LevelTitleSubtitleTagsUse Case
none---Pure visual, no text
title-only✓ (≤8 字)--Simple headline (default)
title-subtitle✓✓ (≤15 字)-Title + supporting context
text-rich✓✓✓ (2-4)Information-dense
MoodContrastSaturationWeightUse Case
subtleLowMutedLightCorporate, thought leadership
balancedMediumNormalMediumGeneral articles (default)
boldHighVividHeavyAnnouncements, promotions

Full guides: references/dimensions/text.md | references/dimensions/mood.md

Style Presets & Compatibility

- ✓✓ = highly recommended | ✓ = compatible | ✗ = not recommended

File Structure

Output directory depends on default_output_dir preference:

PreferenceOutput Path
same-dir{article-dir}/
imgs-subdir{article-dir}/imgs/
independent (default)cover-image/{topic-slug}/
Pasted contentcover-image/{topic-slug}/ (always)
<output-dir>/
├── source-{slug}.{ext}    # Source files (text, images, etc.)
├── prompts/cover.md       # Generation prompt
└── cover.png              # Output image

Slug: Extract main topic (2-4 words, kebab-case). Example: "The Future of AI" → future-of-ai Conflict: If directory exists, append timestamp: {topic-slug}-YYYYMMDD-HHMMSS Source Files: Copy all sources with naming source-{slug}.{ext} (multiple supported)

Workflow

Progress Checklist

Cover Image Progress:
- [ ] Step 0: Check preferences (EXTEND.md) ⚠️ REQUIRED if not found
- [ ] Step 1: Analyze content + determine output directory ⚠️ MUST ask if not configured
- [ ] Step 2: Confirm options (5 dimensions) ⚠️ REQUIRED unless --quick or all specified
- [ ] Step 3: Create prompt
- [ ] Step 4: Generate image
- [ ] Step 5: Completion report

Flow

Input → [Step 0: Preferences/Setup] → Analyze → [Output Dir ⚠️] → [Confirm: 5 Dimensions] → Prompt → Generate → Complete
                                                                          ↓
                                                                  (skip if --quick or all specified)

Step 0: Load Preferences (EXTEND.md) ⚠️

Purpose: Load user preferences or run first-time setup. Do NOT skip setup if EXTEND.md not found.

Use Bash to check EXTEND.md existence (priority order):

# Check project-level first
test -f .baoyu-skills/baoyu-cover-image/EXTEND.md && echo "project"

# Then user-level (cross-platform: $HOME works on macOS/Linux/WSL)
test -f "$HOME/.baoyu-skills/baoyu-cover-image/EXTEND.md" && echo "user"
ResultAction
FoundRead, parse, display preferences summary → Continue to Step 1
Not found⚠️ MUST run first-time setup (references/config/first-time-setup.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

Step 1: Analyze Content

  1. Save source content (if pasted, save to source.md in target directory; if file path, use as-is)

- Backup rule: If source.md exists, rename to source-backup-YYYYMMDD-HHMMSS.md

  1. Content analysis: Extract topic, core message, tone, keywords; identify visual metaphors; detect content type
  2. Language detection: Detect source language, note user's input language, compare with EXTEND.md preference
  3. Determine output directory per File Structure rules. If no default_output_dir preference + file path input, include in Step 2 Q4

Step 2: Confirm Options ⚠️

Validate all 5 dimensions + aspect ratio. Full confirmation flow: references/workflow/confirm-options.md

Skip Conditions:

ConditionSkippedStill Asked
--quick or quick_mode: true5 dimensionsAspect ratio (unless --aspect)
All 5 + --aspect specifiedAllNone

Step 3: Create Prompt

Backup rule: If prompts/cover.md exists, rename to prompts/cover-backup-YYYYMMDD-HHMMSS.md

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

Step 4: Generate Image

  1. Backup existing cover.png → cover-backup-YYYYMMDD-HHMMSS.png (if regenerating)
  2. Check available image generation skills; if multiple, ask user preference
  3. Call selected skill with prompt file path, output path (cover.png), aspect ratio
  4. On failure: auto-retry once before reporting error

Step 5: Completion Report

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]
Location: [directory path]

Files:
✓ source-{slug}.{ext}
✓ prompts/cover.md
✓ cover.png
[✓ cover-backup-{timestamp}.png (if regenerated)]

Image Modification

ActionSteps
RegenerateBackup existing → Update prompt file FIRST → Regenerate with same settings
Change dimensionBackup existing → Confirm new value → Update prompt file FIRST → Regenerate

IMPORTANT: When regenerating, ALWAYS update the prompt file (prompts/cover.md) FIRST before regenerating. This ensures changes are documented and reproducible.

All modifications automatically backup existing cover.png before regenerating.

Notes

  • Cover must be readable at small preview sizes
  • Visual metaphors > literal representations
  • Title: max 8 chars, 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
  • --no-title is alias for --text none
  • --style presets are backward-compatible; explicit --palette/--rendering override preset values

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 Workflow: confirm-options.md | prompt-template.md Config: preferences-schema.md | first-time-setup.md | watermark-guide.md

平台分布

Claude Code

28.55%
按下载量换算43,830

OpenCode

26.07%
按下载量换算40,023

Gemini CLI

16.86%
按下载量换算25,883

Cursor

14.51%
按下载量换算22,276

Antigravity

7.84%
按下载量换算12,036

Codex

3.29%
按下载量换算5,051

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。

继续浏览同类 Skills