跳到正文
cccskills
免费在 GitHub 公开

gouache-travel-still-life

Turn travel photos into 3:4 opaque-gouache posters using a split photo/still-life layout, a full-canvas object still life, or a full-scene gouache redraw.

中文简介正在准备中。当前显示原文说明。

实测评分 未实测

查看安装方法

包含的文件(5)

  • SKILL.md2.2 KB
  • agents/openai.yaml301 B
  • references/full-canvas-still-life.md801 B
  • references/full-scene-painting.md939 B
  • references/split-still-life.md814 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Gouache Travel Still Life

Delivery and mode selection

  • Produce one standalone 3:4 vertical poster per source image. Never combine photos.
  • Offer three modes when the user has not already chosen:
    1. Split still life — real source photo above, extracted gouache still life below.
    2. Full-canvas still life — the entire poster becomes a recomposed object archive.
    3. Full-scene painting — preserve the source composition and repaint the complete scene in opaque gouache.
  • Use one mode for all uploaded photos unless the user maps modes per image.
  • Read only the selected guide: split-still-life.md, full-canvas-still-life.md, or full-scene-painting.md.
  • Return a ready-to-use prompt only when explicitly requested; otherwise use the available image generation or editing capability.

Shared visual rules

Use truly opaque, matte, high-coverage gouache with restrained acrylic and dry-brush texture. Derive the palette entirely from the current source image; never impose a fixed color card or add unrelated bright hues. Preserve visible bristles, paint-thickness variation, modest dry gaps, rough handmade edges, a few searching lines, exposed paper, and paper-white highlights without becoming dirty or chaotic.

Keep subjects immediately recognizable and never invent objects, places, brands, signs, people, animals, or scenery. Text, when the selected mode includes it, must be locked before rendering from visible facts only: a short English title, a simple study identifier, and a brief observation. Never guess a location, date, brand, relationship, or attribution.

Avoid

Transparent watercolor, photo filters, same-crop low-resolution redraws, photoreal painting, smooth gradients, airbrush, vectors, oil impasto, plastic 3D, cartoons, children's coloring-book styling, copied signs, fake labels, unreadable type, polished floating digital text, excessive decoration, logos, QR codes, watermarks, and garbled text.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Turn travel photos into restrained 3:4 charcoal memory studies that physically fade into clean paper, with split comparison or full-canvas composition.

中文简介正在准备中。当前显示原文说明。

GZ-L/photo-to-poster-skills342026年8月28日 更新

Turn photos into quiet 3:4 editorial posters using pure black ink masses, controlled stippling, pristine ivory paper, and either split comparison or full-canvas composition.

中文简介正在准备中。当前显示原文说明。

GZ-L/photo-to-poster-skills342026年8月28日 更新

Turn travel photos with recognizable architecture or human-made landmarks into 3:4 folk ink-and-color posters, with either a photo comparison layout or a full-canvas redraw. Do not use when no landmark is recognizable.

中文简介正在准备中。当前显示原文说明。

GZ-L/photo-to-poster-skills342026年8月28日 更新

Turn uploaded photos into full-canvas 3:4 impasto miniature-landscape posters. Use for sculptural oil-paint dioramas, tactile impasto scenes, or when this skill is invoked.

中文简介正在准备中。当前显示原文说明。

GZ-L/photo-to-poster-skills342026年8月28日 更新

Turn uploaded photos into full-canvas 3:4 isometric healing-block sculpture posters. Use for rounded modular sculptures, gentle isometric block art, or when this skill is invoked.

中文简介正在准备中。当前显示原文说明。

GZ-L/photo-to-poster-skills342026年8月28日 更新

Turn photos with a clearly isolated landmark into two-color 3:4 kraft-paper stencil posters, in split comparison or full-canvas mode. Do not use when no single landmark is recognizable.

中文简介正在准备中。当前显示原文说明。

GZ-L/photo-to-poster-skills342026年8月28日 更新

查看 GZ-L 的全部技能

报告此技能的问题