一个照片编辑风 skill：保留照片，从照片派生抽象面板
装好之后怎么用
什么时候会用上它：Create a clean, vertical editorial artwork that preserves an uploaded photograph as the original image and pairs it with a restrained, photo-derived abstract memory panel and poetic English title. Use when asked to transform a photo into an abstract editorial diptych, photo-plus-abstraction composition, visual memory panel, or minimalist archival poster without redrawing or stylizing the source photo.
怎么用：在 AI 工具里直接描述任务即可自动触发。显式调用的写法各端不同：Claude Code / Cursor 等用 /photo-abstract-editorial，Codex 用 $photo-abstract-editorial，Kimi Code 用 /skill:photo-abstract-editorial，ZCODE 用 $photo-abstract-editorial，Gemini CLI 以自动激活为主。
一个照片编辑风 skill。
它把一张上传的照片，做成一张干净的竖版编辑风格作品：照片作为上部或主要部分，下方配一个从照片派生的克制抽象记忆面板，再加一个诗意的英文标题。
工作流：
- 检查照片，找出 3-6 个决定性的空间事实（主体关系、比例、轴向、方向、间距、重叠、深度、节奏、光线、色彩角色、留白）
- 保留照片作为上部或主要部分，只允许等比缩放或轻微裁剪，绝不重绘、扩展、替换、修图、加滤镜
- 在下方用稀疏的抽象母题重建保留的关系——不是缩略图、描摹、插图、矢量图标或风格迁移
- 组成竖版作品：下部是未加纹理的均匀象牙色面板
- 用一个主要标记家族，最多两个辅助家族；从照片中提取柔和调色板；大量留白
- 创建 2-5 个词的原创英文标题，只放在抽象面板上，用克制的编辑衬线字体
护栏：
- 上传的照片是唯一内容来源
- 面板背景保持平坦、连续、中性象牙色
- 每个抽象标记都能追溯到源照片中的视觉事实
- 人物用不规则的连续短竖线或轻微收窄的块表示
- 地标建筑最多保留 1-3 个身份线索
适合谁：
- 做海报、做个人作品集、做展示的科研小组成员
- 想把照片做成有艺术感作品的人
- 想学“从照片提取关系，用抽象标记重建”的人
用法： 把 SKILL.md 内容复制到你的 AI 工具里，上传一张照片就行。
技能内容
SKILL.md版本与文件 ›Photo Abstract Editorial
Create one finished image from one uploaded photograph. Keep the photograph faithful; derive the lower abstract panel only from the photograph's observed spatial, tonal, and color relationships.
Workflow
- Inspect the photograph internally. Identify three to six decisive spatial facts: subject relationships, scale, axes, direction, intervals, overlap, depth, rhythm, light, color roles, and negative space.
- Keep the photo as the upper or principal section. Permit only proportional scaling or a slight crop needed for the composition. Never redraw, extend, replace, retouch, apply a filter to, or otherwise alter its content.
- Reconstruct the retained relationships below as a sparse abstract motif—not a thumbnail, trace, illustration, vector icon, or style transfer. Prefer relationships over silhouettes and preserve only the minimum recognition cues needed for distinctive subjects.
- Compose a vertical work with an untextured, uniform ivory lower panel. Adapt the photo/panel proportions to the photograph rather than splitting the image mechanically in half. Join both sections directly with no frame, shadow, collage, tape, or mockup effect.
- Use one primary mark family and no more than two supporting families. Extract a muted palette solely from the photo; use generous whitespace and avoid invented decorative elements, colors, symbols, and symmetry.
- Create one original English title of two to five words, grounded in visible facts. Place it only on the abstract panel in a restrained editorial serif face. Add a short subtitle only when it adds meaning.
- Return only the completed composition. Do not add commentary, analysis, title options, labels, dates, logos, or watermarks.
Guardrails
- Treat the uploaded photo as the sole content source.
- Keep the panel background flat, continuous, and neutral ivory; exclude gradients, paper texture, grain, glow, shadows, vignettes, stains, collage artifacts, and scan effects.
- Make every abstract mark traceable to a visual fact in the source photo.
- Preserve people as irregular continuous short vertical marks or gently tapered blocks, never illustrated heads, limbs, faces, or clothing.
- Preserve landmark architecture with at most one to three identity cues; omit architectural surface detail.
Reference Prompt
Read the appropriate full prompt before producing the image:
- Chinese: references/photo-abstract-editorial-prompt.zh-CN.md
- English: references/photo-abstract-editorial-prompt.en.md
Use assets/examples as visual input examples only. Do not reuse their subject matter, colors, or composition unless the user supplies that exact image.
评论 0
更多
登录后可点赞、收藏、评论和举报。
还没有评论，先发起一个具体问题。