图像设计

Name: 图像设计
Author: nexu-io

设计与多媒体社区

作者仓库星标 3,082
作者更新于实时读取
作者仓库 nexu

流狐档案事实层信息：领域、Agent、信任分、运行环境、权限与网络

领域: 设计与多媒体
兼容 Agent: Claude Code
Cursor
Cline
Codex
Windsurf
Gemini CLI

+20
信任分: 88 / 100 · 社区维护
作者 / 版本 / 许可: @nexu-io · 未声明 license
Token 消耗评级: 低消耗
接入复杂程度: 需简单配置
是否需要外部 API Key: 不需要
兼容的系统: 未声明（默认跨平台）
底层运行要求: 无特殊要求
文件与系统权限: 只读
允许写入 / 修改
网络行为: 仅限本地
安装命令数: 26 条

档案由构建时根据 SKILL.md 与安装命令自动衍生，可能与作者实际意图存在差异。

需要注意： 未限定 allowed-tools，默认拥有全部工具权限。

输出预览 qiaomu-mondo-poster-design.preview

---
name: qiaomu-mondo-poster-design
description: 一句话生成大师级海报、书籍封面、专辑封面和各类设计作品。无需懂PS、配色或艺术史，AI自动选择最佳风格（基于33+位传奇设计师）。支持多平台多比例：公众号封面(21:9)、小红书配图(3:4)…
category: 设计与多媒体
runtime: 无特殊运行时
---

# qiaomu-mondo-poster-design 输出预览

## PART A: 任务判断
- 适用问题：视觉内容、演示材料、信息图或设计交付。
- 输入要求：目标材料、限制条件、期望输出和验收方式。
- 证据边界：围绕“Core Mondo Aesthetic / Prompt Structure / Essential Components”读取原文规则，不把推断写成作者承诺。

## PART B: 执行结果
- **01** 任务判断：确认你的需求是否属于视觉内容、演示材料、信息图或设计交付，并标出输入、限制和预期结果。
- **02** 执行计划：优先按“Core Mondo Aesthetic / Prompt Structure / Essential Components”拆成步骤，说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果：给出可复制的命令、文件改动、检查清单或内容草稿，并说明如何继续迭代。
- **04** 风险边界：结合 读取文件、写入/修改文件、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。

## Running Rules
- 读取文件、写入/修改文件；主要在本地完成；通常不需要额外 API Key。
- 先小样例验证，再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。

SKILL.md SKILL.md

---
name: qiaomu-mondo-poster-design
description: 一句话生成大师级海报、书籍封面、专辑封面和各类设计作品。无需懂PS、配色或艺术史，AI自动选择最佳风格（基于33+位传奇设计师）。支持多平台多比例：公众号封面(21:9)、小红书配图(3:4)…
category: 设计与多媒体
source: nexu-io/nexu
---

# qiaomu-mondo-poster-design

## 什么时候使用
- 把设计与视觉方向的常用动作沉淀成 Agent 可调用的技能 适合处理界面、视觉、封面、信息图或演示材料交付，核心价值是把输入、判断、执行、验证和交付边界固定下来，避免 Agent 泛泛回答。 把任务拆成可执行、可检查、可继续迭代的步骤…
- 面向视觉内容、演示材料、信息图或设计交付，优先处理能明确输入、步骤和验收标准的工作。

## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。

## 执行规则
- 围绕「Core Mondo Aesthetic / Prompt Structure / Essential Components」组织步骤，不把推断写成作者事实。
- 读取文件、写入/修改文件；主要在本地完成；通常不需要额外 API Key。
- 先跑小样例，确认结果可检查后再扩大任务范围。

## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown，不编造命令、平台或依赖。

证据边界与执行链路

作者原文负责流程事实；仓库文件负责来源和命令；流狐只补充适用场景、限制和质量判断。

skill "qiaomu-mondo-poster-design" {
  输入层     -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
  上下文层   -> Core Mondo Aesthetic / Prompt Structure / Essential Components
  规则层     -> SKILL.md 触发条件 / 执行顺序 / 输出格式
  运行层     -> 无特殊运行时 | 读取文件、写入/修改文件 | 主要在本地完成
  安全层     -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
  输出层     -> 可复制结果 + 检查清单 + 下一步迭代
}

解读按原文结构重写，命令、链接、术语均保留；右侧可核对作者原始 SKILL.md

先判断是否适合

核心用途：把设计与视觉方向的常用动作沉淀成 Agent 可调用的技能适合处理界面、视觉、封面、信息图或演示材料交付，核心价值是把输入、判断、执行、验证和交付边界固定下来，避免 Agent 泛泛回答。把任务拆成可执行、可检查、可继续迭代的步骤；通常不需要额外 AP…
适用任务：更适合界面、视觉、封面、信息图或演示材料交付，尤其是输入、步骤、验收口径可以反复复用的场景。
不宜硬套：如果任务只有一次性问答、来源材料很少，或需要作者没有说明的命令和外部服务，应先降级为普通对话。

作者设计意图

触发依据：使用时机、上下文收集、输出格式和失败处理共同决定它是否适合当前任务。
来源边界：作者原文负责事实，仓库文件负责命令和文件证据；Fluxly 只补充用途、限制和使用判断。

作者的方法与取舍

执行主线：任务围绕「Core Mondo Aesthetic / Prompt Structure / Essential Components」组织，把触发条件、必要上下文、执行规则和交付标准连成一条可复核的链路。
设计重点：重点不在重复教程，而在解释作者为什么规定这些步骤、哪些条件不可省略，以及结果偏离时应回到哪一层检查。
使用判断：先确认任务与原文边界一致，再决定是否启用；来源没有说明的命令、平台和依赖保持未知，不由 Fluxly 补写。

边界和复核

依赖条件：通常不需要额外 API Key，适合先用小任务验证触发是否稳定。
权限提醒：会涉及 read / write 权限，执行前要说明可读写范围、命令边界和回退方式。
质量标准：结果应包含明确产物、必要证据和下一步动作；如果只是泛泛解释，需要补充输入和验收条件后重跑。

Mondo Style Design Generator

Generate AI image prompts AND create actual designs in Mondo's distinctive alternative aesthetic - known for limited-edition screen-printed posters, book covers, and album art with bold colors, minimalist compositions, and symbolic storytelling.

This skill can:

Generate detailed Mondo-style prompts for any subject
Create actual images directly via AI Gateway API
Design movie posters, book covers, album art, event posters
Provide genre-specific and format-specific templates

Core Mondo Aesthetic

Mondo posters are characterized by:

Artistic Reinterpretation - Not literal film scenes, but conceptual visual distillations
Screen Print Aesthetics - Limited color palettes (2-5 colors), flat color blocks, halftone textures
Minimalist Symbolism - Key props, silhouettes, negative space over character faces
Bold Vintage Typography - Hand-drawn lettering, condensed sans-serifs, Art Deco influences
Retro Color Palettes - High saturation, vintage duotones, bold contrasts (orange/teal, red/cream, etc.)

Prompt Structure

When generating Mondo-style prompts, use this template:

[SUBJECT] in Mondo poster style, [COMPOSITION], [COLOR PALETTE],
screen print aesthetic, limited edition poster art, [KEY VISUAL ELEMENTS],
[TEXTURE/FINISH], minimalist design, vintage movie poster, [MOOD/TONE]

Essential Components

Style Anchors (always include):

"Mondo poster style" or "alternative movie poster"
"screen print aesthetic" or "silkscreen print"
"limited edition poster art"
"vintage [decade] movie poster" (60s/70s/80s)

Composition Techniques (choose 1-2):

Centered symmetrical composition
Silhouette against [color] background
Negative space storytelling
Geometric framing (circles, triangles, arches)
Layered depth with foreground/midground/background

Color Strategy (specify clearly):

Limited palette: "3-color screen print: [color 1], [color 2], [color 3]"
Duotone: "[warm color] and [cool color] duotone"
Vintage scheme: "70s palette: burnt orange, mustard yellow, brown"
High contrast: "bold [color] on [color] background"

Visual Elements (symbolic, not literal):

Key prop or object (weapon, vehicle, iconic item)
Silhouettes over detailed faces
Geometric shapes hiding imagery
Environmental mood (fog, rain, shadows)
Symbolic animals or nature elements

Texture & Finish (adds authenticity):

"halftone dot texture"
"risograph printing effect"
"paper texture grain"
"slight misalignment between color layers"
"vintage print imperfections"

Artist-Specific Variations

For different Mondo artist styles, see references/artist-styles.md.

Quick reference:

Tyler Stout style: Dense character collages, intricate details, maximal composition
Olly Moss style: Ultra-minimal, clever negative space, 1-2 colors
Martin Ansin style: Art Deco influence, elegant line work, muted vintage tones

Example Prompts (Optimized for Clean Design)

Film Noir (Minimal)

Detective silhouette in fedora in Mondo poster style, vertical 9:16 portrait,
single centered figure, 3-color screen print: deep blue, cream, red accent,
clean minimalist composition, halftone texture, vintage 1940s aesthetic

Sci-Fi (Minimalist Eye Window)

Astronaut helmet visor reflecting alien planet in Mondo poster style, vertical 9:16,
centered circular composition, 3-color screen print: orange, teal, black, single
focal element, negative space storytelling, clean retro 1970s sci-fi aesthetic

Horror (Symbolic Architecture)

Victorian mansion single lit window in Mondo poster style, vertical 9:16 portrait,
centered Gothic silhouette, 3-color screen print: black, burgundy, cream, single
focal point, clean simple composition, vintage 1970s horror aesthetic

Advanced Negative Space Techniques

Master-level Mondo designs use figure-ground inversion - where the negative space (area without ink) forms meaningful shapes. This creates dual-layered visual experiences with hidden surprises.

Technique 1: Clever Visual Puns (Olly Moss Style)

One element serves double duty:

Silhouette CONTAINS another scene within negative space
Background shape IS the story element
What's NOT shown tells as much as what IS shown

Example structure:

[Subject silhouette] in Mondo poster style, vertical 9:16, negative space WITHIN
silhouette reveals [hidden element], Olly Moss figure-ground inversion, 2-color
duotone: [color 1] and [color 2], clever dual imagery, what's missing tells the story

Real-world inspiration:

Darth Vader silhouette with AT-ST battle scene in negative space
Detective hat where negative space forms city skyline
Knife blade reflecting villain's silhouette

Technique 2: Scale Contrast Drama

Tiny vs. Massive creates emotional impact:

Small human figure + giant object/creature
Emphasizes isolation, wonder, or threat
Uses 70% negative space for breathing room

Example structure:

Tiny [subject] with massive [object] looming in Mondo poster style, vertical 9:16,
dramatic scale contrast, [subject] occupies only bottom 20%, vast negative space
above, 2-3 color screen print, sense of [emotion: awe/isolation/danger]

Technique 3: Single Shape Storytelling

ONE iconic shape captures entire narrative:

No clutter, no multiple elements
Let one perfect symbol do ALL the work
30% graphic, 30% text, 40% empty space (2024 best practice)

Example structure:

Single [iconic object/symbol] centered in Mondo poster style, vertical 9:16,
ONLY this one element, surrounded by vast negative space, 2-color print:
[color 1] on [color 2] background, Olly Moss ultra-minimal approach, one
image tells complete story

Proven Success Patterns

Based on successful generations, these patterns consistently deliver exceptional results:

Pattern 1: Single Focal Point (Minimalist Clean)

Key principles:

ONE central element only (eye, object, silhouette)
Vertical 9:16 format
2-3 colors maximum
Negative space around focal point
Clean, uncluttered, iconic

Simplified structure:

[Single element] in Mondo poster style, vertical 9:16, centered single focal point,
3-color screen print: [color 1], [color 2], [color 3], clean minimalist composition,
vintage [decade] aesthetic, simple and iconic

Pattern 2: Atmospheric Single Subject (Clean Layered)

Key principles:

ONE main subject with simple background
Vertical 9:16 format
3-4 colors for atmosphere
Subject in foreground, simple backdrop
Clean composition, not cluttered

Simplified structure:

[Main subject] in Mondo poster style, vertical 9:16, single subject with [simple backdrop],
3-color screen print: [atmospheric colors], clean composition, vintage [decade] aesthetic,
focused and simple

Workflow

Identify the subject - Film, book, album, band, event, or concept
Choose symbolic element - What single image captures the essence?
Select composition pattern - Minimalist symbolic OR layered atmospheric
Select color palette - 2-4 colors max, high contrast, vintage-inspired
Add texture keywords - Screen print, halftone, risograph effects
Set the era - Specify 60s/70s/80s for period-accurate aesthetics

Tips for Best Results

Do:

Specify exact color names and counts ("3-color: burnt orange, cream, navy")
Use geometric composition terms (centered, symmetrical, negative space)
Reference specific decades for vintage accuracy
Emphasize symbolic over literal elements
Include texture/printing process keywords

Don't:

Use photorealistic or digital gradient terms
Request complex facial details (use silhouettes instead)
Mix too many styles (keep it focused on screen print aesthetic)
Forget the vintage era context (60s-80s is key)
Overlook negative space opportunities

Advanced: Format-Specific Approaches

For detailed format and genre-specific templates:

references/genre-templates.md - Horror, Sci-Fi, Western, Noir, etc.
references/composition-patterns.md - Layout strategies and visual hierarchy
references/book-covers.md - Book cover design patterns and best practices
references/artist-styles.md - Tyler Stout, Olly Moss, Martin Ansin, etc.

🚀 Enhanced Features (NEW!)

1. AI-Powered Prompt Optimization

Let AI enhance your prompt while respecting your original intent:

python3 scripts/generate_mondo_enhanced.py "Blade Runner" movie --ai-enhance

How it works:

Takes your original idea
Adds ONE perfect symbolic element
Suggests complementary colors (you can override)
Uses negative space techniques
Keeps it clean and minimal

Example:

# Your input: "Inception movie"
# AI enhances to: "Spinning top floating in Mondo poster style, vertical 9:16,
# single iconic object, negative space reveals dream layers, 2-color duotone:
# gold and deep blue, Olly Moss minimal approach"

2. Three-Column Style Comparison

Generate 3 different styles side-by-side to choose the best:

python3 scripts/generate_mondo_enhanced.py "Dune" movie --compare saul-bass,olly-moss,kilian-eng

Perfect for:

Exploring different artistic approaches
Client presentations
Finding the best style for your subject

3. Image-to-Image Transformation

Transform existing posters into Mondo style:

python3 scripts/generate_mondo_enhanced.py "noir thriller" movie --input original_poster.jpg --style saul-bass

Use cases:

Convert photographic posters to illustrated style
Apply Mondo aesthetic to existing designs
Reimagine classic posters

4. 20 Greatest Poster Artists

Now includes 20 legendary artist styles:

Belle Époque Pioneers:

jules-cheret - Bright joyful colors, dynamic feminine figures
toulouse-lautrec - Flat blocks, Japanese influence, bold silhouettes
alphonse-mucha - Art Nouveau flowing curves, ornate floral
steinlen - Social realist, expressive lines, cat motifs
eugène-grasset - Medieval Gothic, stained glass aesthetic

Modernist Masters:

saul-bass - Minimalist geometric abstraction, visual metaphors
cassandre - Cubist planes, dramatic perspective, Art Deco
milton-glaser - Psychedelic pop art, innovative typography
josef-muller-brockmann - Swiss grid, mathematical precision
paul-rand - Playful geometry, clever visual puns

Film Legends:

drew-struzan - Painted realism, epic cinematic, nostalgic glow
olly-moss - Ultra-minimal negative space, hidden imagery
tyler-stout - Maximalist collages, intricate details
martin-ansin - Art Deco elegance, refined vintage
laurent-durieux - Visual puns, mysterious atmospheric

Contemporary:

kilian-eng - Geometric futurism, precise technical lines
dan-mccarthy - Ultra-flat geometric abstraction
jock - Gritty expressive brushwork, dynamic action
shepard-fairey - Propaganda style, halftone, political
jay-ryan - Folksy handmade, warm textured simple
paula-scher - Typographic maximalism, layered text

View all styles:

python3 scripts/generate_mondo_enhanced.py --list-styles

5. Smart Color Suggestions

AI suggests complementary colors, but you can override:

# Let AI suggest colors
python3 scripts/generate_mondo_enhanced.py "Jazz Festival" event --style jules-cheret

# Or specify your own
python3 scripts/generate_mondo_enhanced.py "Jazz Festival" event --style jules-cheret --colors "vibrant yellow, deep blue, red"

Interactive Usage with Claude

When using this skill through Claude Code, I can guide you interactively:

I'll ask you simple questions like:

"What's your subject?" (movie/book/album title)
"Which style feels right?" (show 3-4 options with previews)
"Any color preferences?" (or let AI suggest)
"Want to see comparisons?" (generate 3 versions)

This makes it easy even if you're unfamiliar with Mondo aesthetics!

Direct Image Generation

This skill can generate actual images directly using the bundled scripts:

Enhanced Version (Recommended)

Full feature set: AI enhancement, comparisons, image-to-image, 20 artists

python3 scripts/generate_mondo_enhanced.py "subject" "type" [options]

Enhanced Parameters:

subject: What to design
type: Design type - "movie", "book", "album", "event"
--style: Artist style (20 options, see --list-styles)
--ai-enhance: Let AI optimize prompt (respects your intent)
--compare: Generate 3-style comparison (e.g., "saul-bass,olly-moss,jock")
--input: Input image for image-to-image transformation
--colors: Color preferences (e.g., "orange, teal, black")
--aspect-ratio: Aspect ratio (default: 9:16)
--output: Custom output path
--no-generate: Only show prompt

Enhanced Examples:

AI-optimized generation:

python3 scripts/generate_mondo_enhanced.py "Blade Runner" movie --ai-enhance

3-style comparison:

python3 scripts/generate_mondo_enhanced.py "Akira" movie --compare kilian-eng,saul-bass,jock

Image-to-image with specific artist:

python3 scripts/generate_mondo_enhanced.py "cyberpunk noir" movie --input poster.jpg --style saul-bass

With color preferences:

python3 scripts/generate_mondo_enhanced.py "Jazz Night" event --style milton-glaser --colors "psychedelic orange, purple, yellow"

List all 20 artist styles:

python3 scripts/generate_mondo_enhanced.py --list-styles

Standard Version (Simple & Fast)

Basic usage for quick generation:

python3 scripts/generate_mondo.py "subject" "type" [options]

Parameters:

subject: What to design (e.g., "Neuromancer cyberpunk novel", "Jazz concert poster")
type: Design type - "movie", "book", "album", "event"
--aspect-ratio / --ratio: Aspect ratio (default: 9:16 for mobile/social media)
- Common ratios: 9:16 (vertical mobile), 16:9 (horizontal), 1:1 (square), 2:3, 3:2, 4:5
--style: Artist style - "olly-moss", "tyler-stout", "minimal", "atmospheric" (default: auto)
--output: Custom output path (default: outputs/)
--no-generate: Only create prompt without generating image

Why 9:16 Default?

Optimized for modern mobile devices and social media (Instagram Stories, TikTok, Reels)
Better vertical composition for posters and book covers
Maximizes screen space on smartphones

Examples:

Movie poster (default 9:16 vertical):

python3 scripts/generate_mondo.py "Akira cyberpunk anime" "movie"

Book cover with minimal style (9:16):

python3 scripts/generate_mondo.py "1984 dystopian novel" "book" --style minimal

Album cover with square ratio:

python3 scripts/generate_mondo.py "Pink Floyd The Wall progressive rock" "album" --aspect-ratio 1:1

Horizontal cinema poster:

python3 scripts/generate_mondo.py "Western film Sergio Leone" "movie" --aspect-ratio 16:9

Custom ratio for print:

python3 scripts/generate_mondo.py "Jazz Festival poster" "event" --ratio 2:3 --style atmospheric

Generate prompt only (no image):

python3 scripts/generate_mondo.py "Dune sci-fi epic" "movie" --no-generate

Manual Generation

If you prefer to generate prompts manually and use other image generation tools:

Use this skill to generate the Mondo-style prompt
Pass the prompt to:
- /generate-image - AI Gateway API (recommended)
- /ai-image-generation - FLUX, Gemini, and other models
- /qiaomu-image-generator - For article/content illustrations

Recommended settings:

Model: google/gemini-3.1-flash-image-preview (best quality/speed balance)
Resolution: 2K or higher for print quality
Format: PNG with transparency support

安装命令

一键复制安装选择包管理器,点击右侧复制,粘贴到终端回车即可

npx skills add nexu-io/nexu/apps/desktop/static/bundled-skills/qiaomu-mondo-poster-design -y

查看通用安装教程

查看 Skill 原文

兼容工具

Claude Code
Cursor
Cline
Codex
Windsurf
Gemini
OpenCode
Roo Code
AAide
+Augment
GitHub Copilot
OpenClaw
KKiro
Junie
WWarp
Goose
Trae
Kilo Code
OpenHands
Amp
Zencoder
CContinue
AIAider
CodeBuddy
CodeGeeX
Replit Agent

安全审计

88 / 100

社区

未声明 license/许可。
未声明 version。
未限定 allowed-tools，默认拥有全部工具权限。

元信息

来源: github
nexu-io/nexu
English

@nexu-io 的其他技能

分类与标签

分类设计与多媒体

先判断是否适合

作者设计意图

作者的方法与取舍

边界和复核

Mondo Style Design Generator

Core Mondo Aesthetic

Prompt Structure

Essential Components

Artist-Specific Variations

Example Prompts (Optimized for Clean Design)

Film Noir (Minimal)

Sci-Fi (Minimalist Eye Window)

Horror (Symbolic Architecture)

Advanced Negative Space Techniques

Technique 1: Clever Visual Puns (Olly Moss Style)

Technique 2: Scale Contrast Drama

Technique 3: Single Shape Storytelling

Proven Success Patterns

Pattern 1: Single Focal Point (Minimalist Clean)

Pattern 2: Atmospheric Single Subject (Clean Layered)

Workflow

Tips for Best Results

Advanced: Format-Specific Approaches

🚀 Enhanced Features (NEW!)

1. AI-Powered Prompt Optimization

2. Three-Column Style Comparison

3. Image-to-Image Transformation

4. 20 Greatest Poster Artists

5. Smart Color Suggestions

Interactive Usage with Claude

Direct Image Generation

Enhanced Version (Recommended)

Standard Version (Simple & Fast)

Manual Generation

讨论