Photo Abstract Editorial skill
A Codex skill that turns a photograph into a vertical composition with an abstract memory panel and an English title
- 6,118 ★ on the repository
- Last commit
Minimal access
Why this level
- The skill reads the uploaded photo and creates a new image, using no commands or network
- The result needs a manual check against the photo and the license
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/photo-abstract-editorialDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill reads the uploaded photo and creates a new image, using no commands or network
- The result needs a manual check against the photo and the license
This is third-party code. Review the repository files before installing.
What it does
Photo Abstract Editorial is a Codex skill that builds a vertical editorial piece from a single photo. The upper part keeps the original photograph without redrawing, filters or retouching, allowing only scaling and a slight crop. The lower part is a flat ivory panel with a sparse abstract motif derived from the spatial relationships, rhythm and colors of the shot itself. The skill first finds three to six key facts in the photo: intervals, axes, depth, light zones, color roles. People become short irregular vertical strokes and architecture keeps one to three recognizable cues. The palette comes only from the shot, and a title of two to five English words is set in a restrained serif on the panel only. The full prompt comes in two versions, Chinese and English, and works as a prompt for an image generator.
Who it is for. Photographers and content designers who lay out shots for a portfolio, an exhibition or social media and work in Codex.
Good fit when
- A series of personal shots becomes a unified set of vertical cards for a portfolio
- Trip photos are laid out as an archival poster with a short title
- A shared visual language is wanted for posts where the photo stays untouched with an abstraction beside it
- The prompt from the `references` folder is moved to another image generator
Not a fit when
- The shot itself must be processed: retouching, filters or stylization are forbidden by the skill's rules
- The result goes into commercial work: the author does not allow commercial use
- A title in Russian or another language is required: the skill produces one English title
Example request
Use photo-abstract-editorial: turn this shot into a vertical piece with an abstract panel and a short English titleLimitations
The license is CC BY-NC-SA 4.0: the project is free for personal, educational and non-commercial use, commercial use is forbidden, and the author asks for attribution. The skill is written for Codex and expects the agent to be able to create images, so the result depends on the generator. The pictures in `assets/examples` show the expected kind of input and their subjects, colors and composition must not be reused in new work. The skill has no scripts or checks: a person judges the result. The repository also holds the author's payment QR codes, which have nothing to do with how the skill works.
How to disable. Delete the `photo-abstract-editorial` folder from `~/.codex/skills/`. Images created earlier are not affected.
FAQ
How do I install the skill in Codex?
Copy the whole `photo-abstract-editorial` folder into the Codex skills directory, for example `~/.codex/skills/`, and open a new conversation. Upload a photo and ask for the skill by name.
Does the skill change the original photograph?
No. The photo stays in the upper or main area, with only proportional scaling and a slight crop allowed. Redrawing, extending, replacing and retouching are forbidden.
What can be adjusted in the prompt?
The photo to panel ratio, colors, abstraction forms, title position and typeface and how recognizable subjects stay. Two principles are best kept: the photo is the only source of content, and every panel element must trace back to a fact in the shot.
Can the prompt be used without Codex?
Yes, the prompt files in Chinese and English sit in the repository and work as a prompt for an image generator. The Chinese one is `photo-abstract-editorial-prompt.zh-CN.md` and the English one is `photo-abstract-editorial-prompt.en.md`.
Can I sell works made with this skill?
No, the author permits only personal, educational and non-commercial use and asks for attribution. Commercial work needs a separate arrangement with the author.
Discussion
No questions or reviews yet.
Related
SkillsA skill that makes an editorial poster from a photo: the shot stays unchanged, with an abstract panel and a local title beside it.
A Codex skill that redraws your photo as a watercolor illustration on white paper, with wide margins and a handwritten caption
Travel Photo Abstraction turns a photo into an editorial abstraction tied to the shape, count and position of its subjects.
A skill that turns photos of buildings, streets and local culture into art-directed editorial posters via an image model
A Codex skill that turns a theme, phrase or photo into a paper-zine editorial poster, a ready image prompt or a reusable set of style rules
Skill that turns a photo into an original 3:4 art poster: scene analysis, a fitting medium, palette and typography
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| Photo Abstract Editorial (this card) | no | 6,118 | |
| Photo Revival | no | 610 | a skill for reviving old shots and not for abstract compositions |
| GPT-Image2-Skill | no | 6,086 | a general image generation skill without the untouched-photo rule |
README in short
The README is in Chinese with English inserts: it describes the skill, shows six example works and gives two ways to use it, through Codex and as a prompt. There is a table of parameters for manual tuning, two core principles and the folder structure. The author separately notes that the project gets copied and resold.
README badge
Original SKILL.md
--- name: photo-abstract-editorial 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. --- # 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 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. 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. 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. 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. 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. 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. 7. 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](references/photo-abstract-editorial-prompt.zh-CN.md) - English: [references/photo-abstract-editorial-prompt.en.md](references/photo-abstract-editorial-prompt.en.md) 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.