bauhaus-visual-prompt

Bauhaus Visual Prompt Skill

Compile a title, theme, purpose, or interior reference image intooneBauhaus visual prompt that can be given directly to an image model.

Core principle:First determine the medium, then apply the rules. Bauhaus is not red-yellow-blue geometric decoration; different media must be broken down into different execution priorities: for covers, look at layout; for illustrations, look at conceptual structure; for posters, look at text-image impact; for interior redrawing, focus on space, furniture, materials, and circulation.

Read

Read in the following order, then begin compiling:

• references/compile-contract.md: compilation contract, field order, output quality threshold. Must be satisfied before every output.
• references/module-library.md: module library for purpose, aspect ratio, key visual, color, text mode, and interior redrawing rules.
• references/presets.md: 4 compiled presets. When the user just wants something ready to use or provides very little input, directly choose the closest set and adapt it.

Input

Prefer to infer from the user's words; do not require a form to be filled out:

1. Purpose: article cover, body illustration, column/event poster, interior photo redraw. If missing, infer from context; if it cannot be inferred, ask only this one question.
2. Title / theme: covers and posters usually need it; body illustrations can use a concept; interior redraws may not need a title.
3. Aspect ratio: if unspecified, default to 4:5 for covers, 16:9 for body illustrations, 2:3 for posters, and follow the reference image or 16:9 for interior redraws.
4. Reference image: if the user uploads an interior photo, prioritize interior redrawing and preserve the original image's spatial structure.

If the user actively specifies aspect ratio, main title, color scheme, whether to retain text, etc., the user's choice takes precedence; but it must not damage style purity or medium boundaries.

Workflow

1. Parse intent: determine the use case:article-cover、inline-illustration、poster、interior-redesign choose one of four.
2. Select modules: according to module-library.md assign one value to each slot: aspect ratio, key visual, color, text mode, material/space rules, prohibitions.
3. Compile prompt: output one English art direction in the field order of compile-contract.md . Parse out all {}、/ options and Chinese annotations; title text is the exception.
4. Output: one finished prompt + one line of rationale for the selection + one line for the closest preset. Do not output the module menu, reasoning process, self-check list, or multiple version options.

Routing Rules

• Article cover: title area, geometric layout, visual center of gravity, whitespace, short text control.
• Body illustration: concept explanation, structural diagram, geometric relationships, low noise, little or no text.
• Column/event poster: exhibition poster feel, strong title, integrated text and image, stronger compositional tension.
• Interior photo redraw: preserve the original image's viewpoint, proportions, doors and windows, walls, and main furniture positions; change only materials, furniture language, lighting, color, and spatial atmosphere.

Output Format

Unless necessary input is missing and a follow-up question is required, output only:

1. the complete finished prompt.
2. 选型理由：...
3. 最接近预设：...

Usage Examples

These requests should directly trigger this skill:

生成一张 4:5 包豪斯风格文章封面，标题是：结构比装饰更重要。

生成一张 16:9 包豪斯风格正文配图，主题是：提示词不是描述风格，而是组织结构。

生成一张 2:3 包豪斯风格活动海报，标题是：FORM FOLLOWS FUNCTION。

参考我上传的室内照片，把这个房间重绘成包豪斯风格工作室。

Quality Gates

• The output must not retain {变量}, slash menus, Chinese comments, or multiple sets of options.
• Choose only one main visual each time; do not list multiple engines side by side.
• Negative items are placed together in AVOID。
• Do not stuff poster layout rules into interior redraws, and do not stuff furniture or glass curtain walls into article covers.
• Interior redraws must explicitly preserve the original spatial structure; the reference photo must not be completely redrawn into an unrelated model room.
• Do not fabricate image generation results; this skill only produces prompts.