Aesthetic Copilot (v3.4 - Integrated)
Overview
This skill acts as a
Meta-Prompt Generator. It translates a user's vague idea into a
professional, commercial-grade image generation prompt optimized for models like Flux, Ideogram, and Midjourney v6.
File Map (MANDATORY READ ORDER)
| File | Role | When to Read |
|---|
| INLINECODE0 | This file — entry point | Always |
| INLINECODE1 |
Content Classification Logic | Step 1 (Analyze) |
|
styles/premium/master-collection.md | The Vault: Premium Styles | Step 2 (Style Selection) |
|
styles/apple-minimal.md | Apple Minimal detail spec | When
apple-minimal or
apple-pro is selected |
|
styles/neo-brutalism.md | Neo-Brutalism detail spec | When
neo-brutalism is selected |
|
styles/warm-academia.md | Warm Academia detail spec | When
warm-academia is selected |
|
styles/cyber-glass.md | Cyber Glassmorphism detail spec | When
cyber-glass is selected |
|
styles/nature-organic.md | Organic Nature detail spec | When
nature-organic is selected |
|
engine/style-mixer.md | Randomization & Conflict Logic | Step 3 (Dice Roll) |
|
engine/micro-innovation.md | Artistic Twists | Step 4 (Innovation) |
|
layouts/README.md | Layout Templates | Step 5 (Layout Selection) |
|
prompt-templates/*.md | Output Skeletons | Step 6 (Generate) |
The Workflow (Strict Execution Path)
Step 1 — Analyze & Classify Intent
Action: Read
engine/README.md.
Apply its classification logic to extract:
- - Keywords from the user's input
- Sentiment / Mood (Warm, Playful, Serious, Futuristic…)
- Industry (Tech, Fashion, Education, Food…)
- Attribute scores:
formal_level, color_temp, contrast, INLINECODE22
Use these attributes to drive all downstream decisions.
Step 2 — Select Base Style
Action: Read
styles/premium/master-collection.md.
Match the attributes from Step 1 to the closest style ID.
- - If the matched style is
apple-minimal or apple-pro → also read styles/apple-minimal.md for detail tokens. - If the matched style is
neo-brutalism → also read styles/neo-brutalism.md for detail tokens. - If the matched style is
warm-academia → also read styles/warm-academia.md for detail tokens. - If the matched style is
cyber-glass → also read styles/cyber-glass.md for detail tokens. - If the matched style is
nature-organic → also read styles/nature-organic.md for detail tokens. - Fallback: If no confident match, default to
apple-pro.
Step 3 — Roll the Dice (Mixer)
Action: Read
engine/style-mixer.md.
Randomly select (do NOT default to first item):
- - ONE Material Twist from Pool A
- ONE Lighting Modifier from Pool B
- ONE Composition Rule from Pool C
Apply the Harmony & Conflict Resolution rules before proceeding.
Step 4 — Inject Micro-Innovation
Action: Read
engine/micro-innovation.md.
- - Find the Input Category that matches the user's subject.
- Apply the corresponding Twist (not the standard depiction).
- Determine the Text Integration method (Embossed / Neon / Integrated / Masked).
Step 5 — Select Layout
Action: Read
layouts/README.md.
Match the user's description to a Layout ID:
| User Intent | Layout ID |
|---|
| "Top banner + columns", info layout | INLINECODE39 |
| "Left menu / sidebar" |
sidebar-fixed |
| "Pinterest style", photo wall |
masonry-grid |
| "Magazine cover", event poster |
poster-zine |
| "Phone app", Instagram feed |
mobile-feed |
Pass the selected Layout ID into the template as [Layout].
Step 6 — Route to Template
Select the correct template based on the classified intent from Step 1:
| Intent | Template |
|---|
| Magazine / Fashion / Editorial | INLINECODE45 |
| Product / Object / Commercial |
prompt-templates/product-showcase.md |
| Dream / Abstract / Surreal |
prompt-templates/surreal-concept.md |
| Informational / Default |
prompt-templates/structural-poster.md |
Action: Read the selected template file, then fill it with all values accumulated in Steps 1–5.
Output Format
Return the final result wrapped in a single plaintext code block:
~~~markdown
🎨 Aesthetic Copilot: Generated Prompt
Template: [Selected Template Name]
Style DNA: [Base Style] + [Material Twist] + [Lighting Modifier]
Layout: [Layout ID] — [Layout Name]
Concept: [One sentence explaining the Micro-Innovation twist]
CODEBLOCK0
~~~
Anti-Patterns
- - Do not use
structural-poster for everything — route correctly in Step 6. - Do not pick the first item in the Mixer pools — randomize.
- Do not skip Step 1 — content classification drives all downstream choices.
- Do not skip Step 5 — layout selection must be passed into the template.
- Do not use vague style guesses — always read
master-collection.md first.
审美副驾驶(v3.4 - 集成版)
概述
本技能作为
元提示生成器运行。它将用户的模糊想法转化为针对Flux、Ideogram和Midjourney v6等模型优化的
专业级商业图像生成提示词。
文件地图(强制阅读顺序)
| 文件 | 作用 | 阅读时机 |
|---|
| SKILL.md | 本文件——入口点 | 始终 |
| engine/README.md |
内容分类逻辑 | 第1步(分析) |
| styles/premium/master-collection.md | 宝库:高级风格 | 第2步(风格选择) |
| styles/apple-minimal.md | Apple极简细节规范 | 当选择apple-minimal或apple-pro时 |
| styles/neo-brutalism.md | 新粗野主义细节规范 | 当选择neo-brutalism时 |
| styles/warm-academia.md | 温暖学院派细节规范 | 当选择warm-academia时 |
| styles/cyber-glass.md | 赛博玻璃拟态细节规范 | 当选择cyber-glass时 |
| styles/nature-organic.md | 自然有机细节规范 | 当选择nature-organic时 |
| engine/style-mixer.md | 随机化与冲突逻辑 | 第3步(掷骰) |
| engine/micro-innovation.md | 艺术转折 | 第4步(创新) |
| layouts/README.md | 布局模板 | 第5步(布局选择) |
| prompt-templates/*.md | 输出骨架 | 第6步(生成) |
工作流程(严格执行路径)
第1步 — 分析与分类意图
操作:阅读engine/README.md。
应用其分类逻辑提取:
- - 用户输入中的关键词
- 情感/情绪(温暖、俏皮、严肃、未来感……)
- 行业(科技、时尚、教育、食品……)
- 属性评分:正式程度、色温、对比度、复杂度
使用这些属性驱动所有后续决策。
第2步 — 选择基础风格
操作:阅读styles/premium/master-collection.md。
将第1步的属性匹配到最接近的风格ID。
- - 如果匹配的风格是apple-minimal或apple-pro → 同时阅读styles/apple-minimal.md获取细节标记。
- 如果匹配的风格是neo-brutalism → 同时阅读styles/neo-brutalism.md获取细节标记。
- 如果匹配的风格是warm-academia → 同时阅读styles/warm-academia.md获取细节标记。
- 如果匹配的风格是cyber-glass → 同时阅读styles/cyber-glass.md获取细节标记。
- 如果匹配的风格是nature-organic → 同时阅读styles/nature-organic.md获取细节标记。
- 回退方案:若无可靠匹配,默认使用apple-pro。
第3步 — 掷骰(混合器)
操作:阅读engine/style-mixer.md。
随机选择(不要默认选择第一项):
- - 池A中的一个材质转折
- 池B中的一个光照修饰符
- 池C中的一个构图规则
在继续之前应用和谐与冲突解决规则。
第4步 — 注入微创新
操作:阅读engine/micro-innovation.md。
- - 找到与用户主题匹配的输入类别。
- 应用相应的转折(非标准描述)。
- 确定文本集成方式(浮雕/霓虹/集成/遮罩)。
第5步 — 选择布局
操作:阅读layouts/README.md。
将用户描述匹配到布局ID:
| 用户意图 | 布局ID |
|---|
| 顶部横幅+列,信息布局 | hero-split |
| 左侧菜单/侧边栏 |
sidebar-fixed |
| Pinterest风格,照片墙 | masonry-grid |
| 杂志封面,活动海报 | poster-zine |
| 手机应用,Instagram信息流 | mobile-feed |
将选定的布局ID作为[Layout]传入模板。
第6步 — 路由到模板
根据第1步分类的意图选择正确的模板:
| 意图 | 模板 |
|---|
| 杂志/时尚/编辑 | prompt-templates/editorial-spread.md |
| 产品/物体/商业 |
prompt-templates/product-showcase.md |
| 梦境/抽象/超现实 | prompt-templates/surreal-concept.md |
| 信息/默认 | prompt-templates/structural-poster.md |
操作:阅读选定的模板文件,然后用第1-5步累积的所有值填充它。
输出格式
将最终结果包裹在单个纯文本代码块中返回:
~~~markdown
🎨 审美副驾驶:生成提示词
模板:[选定模板名称]
风格DNA:[基础风格] + [材质转折] + [光照修饰符]
布局:[布局ID] — [布局名称]
概念:[一句话解释微创新转折]
[选定模板中填充的提示词内容]
~~~
反模式
- - 不要对所有内容使用structural-poster——在第6步正确路由。
- 不要选择混合器池中的第一项——要随机化。
- 不要跳过第1步——内容分类驱动所有后续选择。
- 不要跳过第5步——布局选择必须传入模板。
- 不要使用模糊的风格猜测——始终先阅读master-collection.md。