Photo Revival skill
A Codex skill that redraws your photo as a watercolor illustration on white paper, with wide margins and a handwritten caption
- 601 ★ on the repository
- Last commit
- MIT
Minimal access
Why this level
- The skill is made of text instructions and runs nothing, but the photo goes to whichever image service your agent has connected
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/photo-revivalDetects 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 is made of text instructions and runs nothing, but the photo goes to whichever image service your agent has connected
This is third-party code. Review the repository files before installing.
What it does
Photo Revival is a Codex skill that turns an ordinary snapshot into a small illustration on a white sheet. The agent first picks one to three memorable elements in the frame: the main subject, the pose, how things are arranged, the mood. It then redraws the scene with image generation: pencil line, watercolor wash, dry brush, wax pastel, a light riso-style grain. The composition is fixed. The page is vertical, 3:4, on white or near-white paper. The drawing takes 10–16% of the sheet, 18% at most, and 80–88% of the paper stays empty. Color stays inside the small illustration. The caption is short and handwritten: in the author's examples it is a line in Chinese and an English note such as a date or a field-note title. The skill itself supplies the judgment calls, a prompt template and the order of work. The picture is drawn by whatever image tool your environment offers. If the subject comes out larger than 18% of the page or the text repeats, the skill asks for a regeneration.
Who it is for. For designers and social media authors who want to turn casual snapshots (a cat, a cup, a window, an old shop, a street corner) into soft illustrations for posts.
Good fit when
- You have a casual shot, such as a cat on a bed, a cup, a window or a street corner, and want an illustration that keeps the subject and the mood
- You need a page with a lot of empty space: the subject takes 10–16% of the sheet and the rest stays white paper
- You want to try the style on several photos at once: the request lists the photos and each gets its own drawing on white paper
- You want a short handwritten caption and a dated note built into the image itself
- Material from trips and city life: bridges, courtyards, trees, old buildings, everyday objects and folk crafts
Not a fit when
- You need portrait retouching or studio photography of a person
- You need a commercial product poster or a flyer with a large headline
- You need a full-bleed collage or a dense infographic with a lot of text
- You need to restore the original photo pixel for pixel: the skill redraws the frame and pixel-exact copies are out of scope
Example request
Use $photo-revival: redraw this photo as a watercolor illustration on white paper, the subject should take about 12% of the sheet, with a single short caption lineLimitations
The skill is a set of text instructions. It has no image service, account or generation quota; the drawing is made by the tool connected in your environment, so quality and cost depend on it. The author warns that identical results from run to run should not be expected and that the examples only show the direction of the style.
The texts and sample captions in the repository are Chinese and English. The author says nothing about Russian captions, so you have to check how Cyrillic renders in the picture yourself.
The tested install path is described for Codex CLI and the IDE. For ChatGPT and other hosts the author points to their own rules for loading skills. If the skill is missing from the list after installing, the author suggests opening a new task.
How to disable. Delete the photo-revival folder from the Codex skills directory: ~/.agents/skills/ for the user or .agents/skills/ in the project.
FAQ
How do I install Photo Revival in Codex?
Download the ZIP of the main branch, unpack it and put the repository root, where SKILL.md sits, into a skills directory. Name the folder photo-revival so the entry file is photo-revival/SKILL.md. That is ~/.agents/skills/ for the user, .agents/skills/ for a project and %USERPROFILE%\.agents\skills\ on Windows. Invoke it in a session with $photo-revival.
Does Photo Revival work in Claude Code?
The tested install path in the repository is described only for Codex. For ChatGPT and other hosts the author points to their rules for loading skills. SKILL.md has name and description fields, but there are no checks in other agents.
Does the skill include image generation?
No. The skill organizes the design decisions, the prompt and the order of work, and the picture is made by an image tool in your environment. An image service, an account and a generation quota are not part of the installation.
What if the drawing is too large, the text is broken or the result looks like a filter?
Regenerate with a stricter wording. For size the author suggests demanding that the subject take 10–16% of the sheet, 18% at most, and 80–88% of the paper stay blank. For text keep one caption line and a date. For the filter look, demand that the image be redrawn from scratch as an illustration. If the color spreads, say it must stay inside the small drawing.
Can I process several photos at once?
Yes. The author gives a request where the skill is applied to several shots in a row, and each gets a small drawing on white paper with a short caption.
Discussion
No questions or reviews yet.
Related
SkillsA 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
A skill that generates one-ink and two-ink editorial posters: paper substrate, halftone, negative space and restrained type
A skill that turns your photo or description into a hand-drawn character and uses it for diagrams, knowledge cards and slides
A skill that turns Chinese story copy or a set of ordered images into a vertical hand-drawn animation, a silent diary-comic picture track
A Codex marketplace with three creative plugins: black-pen drawing, animated pixel particles and deadpan watercolor doodles
A skill that turns photos of buildings, streets and local culture into art-directed editorial posters via an image model
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Repository stars | Main difference |
|---|---|---|---|
| Photo Revival (this entry) | no | 601 | |
| hand-drawn-styles | no | 2,571 | builds prompts for drawing in various hand techniques from a list of styles |
| Ian Handdrawn PPT | no | 1,497 | turns articles and notes into picture pages in a hand-drawn style |
| LabArt | no | 292 | a Codex marketplace with three creative plugins |
README in short
The description, in Chinese and English, opens with a sample request and a table: an everyday snapshot goes in, a 3:4 page with a small drawing and wide margins comes out. Then come installation, a list of effects, suitable and unsuitable tasks, a seven-step workflow and a general English prompt template with slots to fill. At the end are sample captions, a gallery of works and answers to common problems: a subject that is too large, repeated text and too much color fill.
README badge
Original SKILL.md
--- name: photo-revival description: Turn ordinary photos or everyday snapshots into poetic hand-drawn illustrations with large white-paper negative space, vivid localized color, subtle collage accents, and tiny handwritten captions. Use when a user wants a real photo reimagined as an illustration rather than filtered, beautified, or photorealistically edited. --- # Photo Revival ## Core idea Keep the subject and scene recognizable, but redraw the image as a fresh illustration on white paper. Default to: - 3:4 vertical composition - large white-paper negative space - a tiny subject or focal cluster occupying about 10-16% of the page - delicate hand-drawn texture - vivid local color only where it matters - tiny handwritten text, dates, or short captions ## Workflow 1. Identify the photo's main subject, setting, and one or two memorable details. 2. Preserve those details in simplified form; do not copy the photo literally. 3. Rebuild the scene as an illustration with paper texture, brush marks, pencil edges, or watercolor softness. 4. Leave 80-88% of the page as blank white paper. 5. Add text only as a small note, label, date, or poetic fragment. ## Style rules - Use white or very light paper as the base. - Keep the illustration area small and concentrated: default 10-16% of the page, absolute maximum 18%. - Keep the strongest color inside that small illustrated area; do not let color spread into the blank field. - Favor vivid but controlled color in a limited area. - Let the drawing feel handmade, not filtered. - Allow subtle collage, stamp, or clipping hints only when they stay tiny and integrated. ## Avoid - Full-bleed image fills - Photo-filter looks - Heavy poster typography - Dense layouts - Subject areas larger than 18% of the page - Flat vector treatment - Large collage blocks - Overly realistic retouching ## Output prompt shape When directing image generation, describe: - what must be preserved from the photo - what should become illustrated - the paper base and empty space - the tiny text treatment - the desired color accents Keep the instruction short and focused.