Skip to content
Back to search

photo-abstract-editorial

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.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/zzzlc0405--photo-abstract-editorial/badge.svg)](/listings/zzzlc0405--photo-abstract-editorial)

HTML

<a href="/listings/zzzlc0405--photo-abstract-editorial"><img src="/api/listings/zzzlc0405--photo-abstract-editorial/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

SKILL.md · Manifest · 35 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. ---
  2. name: photo-abstract-editorial
  3. description: 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.
  4. ---
  5. # Photo Abstract Editorial
  6. 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.
  7. ## Workflow
  8. 1. 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.
  9. 2. 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.
  10. 3. 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.
  11. 4. 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.
  12. 5. 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.
  13. 6. 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.
  14. 7. Return only the completed composition. Do not add commentary, analysis, title options, labels, dates, logos, or watermarks.
  15. ## Guardrails
  16. - Treat the uploaded photo as the sole content source.
  17. - Keep the panel background flat, continuous, and neutral ivory; exclude gradients, paper texture, grain, glow, shadows, vignettes, stains, collage artifacts, and scan effects.
  18. - Make every abstract mark traceable to a visual fact in the source photo.
  19. - Preserve people as irregular continuous short vertical marks or gently tapered blocks, never illustrated heads, limbs, faces, or clothing.
  20. - Preserve landmark architecture with at most one to three identity cues; omit architectural surface detail.
  21. ## Reference Prompt
  22. Read the appropriate full prompt before producing the image:
  23. - Chinese: [references/photo-abstract-editorial-prompt.zh-CN.md](references/photo-abstract-editorial-prompt.zh-CN.md)
  24. - English: [references/photo-abstract-editorial-prompt.en.md](references/photo-abstract-editorial-prompt.en.md)
  25. Use [assets/examples](assets/examples) as visual input examples only. Do not reuse their subject matter, colors, or composition unless the user supplies that exact image.
README.md · README · 229 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <div align="center">
  2. # 🎨 Photo Abstract Editorial
  3. **将一张照片转化为「原始摄影区域 + 抽象记忆面板 + 诗意英文标题」的竖向编辑作品**
  4. [![Codex Skill](https://img.shields.io/badge/Codex-Skill-000000?style=for-the-badge&logo=openai&logoColor=white)](https://github.com/ZzzLc0405/photo-abstract-editorial)
  5. [![License](https://img.shields.io/badge/License-CC%20BY--NC--SA%204.0-lightgrey?style=for-the-badge)](./LICENSE.md)
  6. [![Language](https://img.shields.io/badge/🌐_中文-English-blue?style=for-the-badge)](#)
  7. </div>
  8. ---
  9. ## ⚠️ 声明
  10. > **Free for personal, educational and non-commercial use.**
  11. > Commercial use is not allowed.
  12. >
  13. > If you build something with these Skills, attribution and **@AM.** are greatly appreciated.
  14. <details>
  15. <summary>💬 作者的话</summary>
  16. 在这里吐槽一下,真的很无语这几天,被人抄袭,甚至有人拿这个东西去卖,我真的无语!
  17. </details>
  18. ---
  19. ## 📖 关于本项目
  20. 这是一个 **Codex Skill**,它能将一张照片转化为「原始摄影区域 + 抽象记忆面板 + 诗意英文标题」的竖向编辑作品。
  21. - ✅ 保留照片的**真实内容**
  22. - ✅ 仅从照片本身提炼**空间关系、构图节奏和色彩关系**
  23. - ❌ 不是滤镜、照片重画或风格迁移
  24. > 📝 The skill includes the complete prompt in both **Chinese** and **English**.
  25. ---
  26. ## 🖼️ 示例作品
  27. > 原图均为本人拍摄
  28. <p align="center">
  29. <img src="./assets/examples/case-10.jpg" width="31%" align="top" alt="Case 3">
  30. <img src="./assets/examples/case-3.jpg" width="31%" align="top" alt="Case 1">
  31. <img src="./assets/examples/case-1.jpg" width="31%" align="top" alt="Case 7">
  32. <br><br>
  33. <img src="./assets/examples/case-11.jpg" width="31%" align="top" alt="Case 6">
  34. <img src="./assets/examples/case-9.jpg" width="31%" align="top" alt="Case 2">
  35. <img src="./assets/examples/case-6.jpg" width="31%" align="top" alt="Case 8">
  36. </p>
  37. ---
  38. ## 📋 目录
  39. - [使用方法](#-使用方法)
  40. - [可自由调整的部分](#-可自由调整的部分)
  41. - [核心原则](#-核心原则)
  42. - [内容结构](#-内容结构)
  43. - [许可证](#-许可证)
  44. ---
  45. ## 🚀 使用方法
  46. ### 方式一:作为 Codex Skill 使用
  47. 1. 将整个 `photo-abstract-editorial` 文件夹复制到你的 Codex skills 目录,例如 `~/.codex/skills/`
  48. 2. 开启新的 Codex 对话,上传一张希望处理的照片
  49. 3. 直接提出需求,例如:
  50. > 使用 `photo-abstract-editorial` 将这张照片制作成摄影与抽象面板组合的编辑作品。
  51. 4. Skill 会将原图保留在成品的上方或主要区域,并在下方创建由原图关系推导出的极简抽象面板。成品中只保留一个原创英文标题(可选副标题)。
  52. ### 方式二:作为提示词直接使用
  53. 也可以直接打开下列文件,并将其作为图像生成提示词使用:
  54. | 语言 | 文件 |
  55. | :---: | :--- |
  56. | 🇨🇳 中文 | [references/photo-abstract-editorial-prompt.zh-CN.md](references/photo-abstract-editorial-prompt.zh-CN.md) |
  57. | 🇬🇧 English | [references/photo-abstract-editorial-prompt.en.md](references/photo-abstract-editorial-prompt.en.md) |
  58. ---
  59. ## 🎛️ 可自由调整的部分
  60. 这套提示词应当被视为**高质量起点**,而不是不可变的版式规范。请按自己的审美和项目需求修改以下参数:
  61. | 参数 | 说明 |
  62. | :--- | :--- |
  63. | **📐 照片与面板的比例** | 可调整摄影区域和抽象面板的高度占比、画布比例,以及抽象母题的大小与留白 |
  64. | **🎨 颜色** | 可修改象牙色面板背景、照片提取色的饱和度、主色与强调色的数量和倾向 |
  65. | **✏️ 抽象形式** | 可选择或混合色块、柔和有机质量、弧形笔触、短条、层叠色带、简化建筑质量、细线、点状标记等形式 |
  66. | **📝 版式与文字** | 可调整母题位置、标题位置、字体气质、标题长度和是否使用副标题 |
  67. | **🔍 抽象程度** | 可根据题材在「关系优先」和「保留少量身份特征」之间调整,例如让地标建筑或小型物件保留更多辨识线索 |
  68. ---
  69. ## 💡 核心原则
  70. 调整时建议保留两条核心原则:
  71. 1. **上传照片始终是唯一内容来源** — 照片区域不应被重画、扩展或改写
  72. 2. **抽象面板可追溯** — 每个重要元素都应能追溯到原照片中真实存在的空间、色彩或结构事实
  73. ---
  74. ## 📁 内容结构
  75. ```text
  76. photo-abstract-editorial/
  77. ├── SKILL.md # Skill 工作流程与约束
  78. ├── agents/openai.yaml # Codex 界面元数据
  79. ├── references/
  80. │ ├── photo-abstract-editorial-prompt.zh-CN.md
  81. │ └── photo-abstract-editorial-prompt.en.md
  82. └── assets/examples/ # 示例图片
  83. ```
  84. > ⚠️ `assets/examples` 中的图片仅用于理解预期输入类型;除非用户上传该图片本身,否则不要将其中的主题、色彩或构图复用于新的作品。
  85. ---
  86. ## 📄 许可证
  87. 本项目采用 [LICENSE.md](./LICENSE.md) 中规定的许可证。
  88. ---
  89. <div align="center">
  90. **如果这个项目对你有帮助,欢迎 Star ⭐ 支持!**
  91. </div>
  92. 请作者充点Token(coffee)
  93. <p align="center">
  94. <img src="./pay/AliPay.jpg" width="32%">
  95. <img src="./pay/WechatPay.jpg" width="32%">
  96. </p>
  97. <!--
  98. ## 声明
  99. Free for personal, educational and non-commercial use. Commercial use requires prior authorization. If you build something with these Skills, attribution and @AM. are greatly appreciated.
  100. 商业授权已不被允许,请不要私自商用,谢谢!
  101. douyin: 12919593 xiaohongshu: Cclz_9
  102. 在这里吐槽一下,真的很无语这几天,被人抄袭,甚至有人拿这个东西去卖,我真的无语!
  103. # Photo Abstract Editorial
  104. 将一张照片转化为“原始摄影区域 + 抽象记忆面板 + 诗意英文标题”的竖向编辑作品的 Codex Skill。它保留照片的真实内容,并仅从照片本身提炼空间关系、构图节奏和色彩关系;它不是滤镜、照片重画或风格迁移。
  105. The skill includes the complete prompt in both Chinese and English.
  106. ## 示例图片(原图均为本人拍摄)
  107. <table>
  108. <tr>
  109. <td><img src="./assets/examples/case-3.jpg" width="100%"></td>
  110. <td><img src="./assets/examples/case-1.jpg" width="100%"></td>
  111. <td><img src="./assets/examples/case-7.jpg" width="100%"></td>
  112. </tr>
  113. <tr>
  114. <td><img src="./assets/examples/case-2.jpg" width="100%"></td>
  115. <td><img src="./assets/examples/case-6.jpg" width="100%"></td>
  116. <td><img src="./assets/examples/case-8.jpg" width="100%"></td>
  117. </tr>
  118. </table>
  119. <p align="center">
  120. <img src="./assets/examples/case-3.jpg" width="32%">
  121. <img src="./assets/examples/case-1.jpg" width="32%">
  122. <img src="./assets/examples/case-7.jpg" width="32%">
  123. <br>
  124. <img src="./assets/examples/case-6.jpg" width="32%">
  125. <img src="./assets/examples/case-2.jpg" width="32%">
  126. <img src="./assets/examples/case-8.jpg" width="32%">
  127. </p>
  128. ## 使用方法
  129. 1. 将整个 `photo-abstract-editorial` 文件夹复制到你的 Codex skills 目录,例如 `~/.codex/skills/`。
  130. 2. 开启新的 Codex 对话,上传一张希望处理的照片。
  131. 3. 直接提出需求,例如:
  132. > 使用 `photo-abstract-editorial` 将这张照片制作成摄影与抽象面板组合的编辑作品。
  133. 4. Skill 会将原图保留在成品的上方或主要区域,并在下方创建由原图关系推导出的极简抽象面板。成品中只保留一个原创英文标题(可选副标题)。
  134. 也可以直接打开下列文件,并将其作为图像生成提示词使用:
  135. - 中文版:[references/photo-abstract-editorial-prompt.zh-CN.md](references/photo-abstract-editorial-prompt.zh-CN.md)
  136. - English version: [references/photo-abstract-editorial-prompt.en.md](references/photo-abstract-editorial-prompt.en.md)
  137. ## 可自由调整的部分
  138. 这套提示词应当被视为高质量起点,而不是不可变的版式规范。请按自己的审美和项目需求修改以下参数:
  139. - **照片与面板的比例**:可调整摄影区域和抽象面板的高度占比、画布比例,以及抽象母题的大小与留白。
  140. - **颜色**:可修改象牙色面板背景、照片提取色的饱和度、主色与强调色的数量和倾向。
  141. - **抽象形式**:可选择或混合色块、柔和有机质量、弧形笔触、短条、层叠色带、简化建筑质量、细线、点状标记等形式。
  142. - **版式与文字**:可调整母题位置、标题位置、字体气质、标题长度和是否使用副标题。
  143. - **抽象程度**:可根据题材在“关系优先”和“保留少量身份特征”之间调整,例如让地标建筑或小型物件保留更多辨识线索。
  144. 调整时建议保留两条核心原则:
  145. 1. 上传照片始终是唯一内容来源,照片区域不应被重画、扩展或改写。
  146. 2. 抽象面板中的每个重要元素都应能追溯到原照片中真实存在的空间、色彩或结构事实。
  147. ## 内容结构
  148. ```text
  149. photo-abstract-editorial/
  150. ├── SKILL.md # Skill 工作流程与约束
  151. ├── agents/openai.yaml # Codex 界面元数据
  152. ├── references/
  153. │ ├── photo-abstract-editorial-prompt.zh-CN.md
  154. │ └── photo-abstract-editorial-prompt.en.md
  155. └── assets/examples/ # 5 张示例图片
  156. ```
  157. `assets/examples` 中的图片仅用于理解预期输入类型;除非用户上传该图片本身,否则不要将其中的主题、色彩或构图复用于新的作品。
  158. -->

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.