make-photo-stamp-archive skill

A Codex skill that turns a photo into an archive collage: the original shot beside paper with a hand-pressed stamp.

  • 381 ★ on the repository
  • Last commit
  • MIT
Skill

Minimal access

Why this level

  • Instructions only: the skill runs nothing, and the agent's image model processes the photos.
All reasons and checks

dlcccc71913/skill-make-photo-stamp-archive

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/make-photo-stamp-archive

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Minimal accessThe tool runs nothing and makes no network calls.

  • Instructions only: the skill runs nothing, and the agent's image model processes the photos.

This is third-party code. Review the repository files before installing.

What it does

The `make-photo-stamp-archive` skill turns each supplied photograph into one flat finished image. On the left the original shot stays unchanged: faces, objects, text and colours are preserved. On the right lies a sheet of warm off-white paper with a small stamp and a tiny faded typewriter caption beside it. The skill picks the stamp shape from the subject: circle, square frame, panoramic silhouette, arch or the outline of the building itself. The impression imitates dry ink, uneven pressure and slight registration error. By default the image is split horizontally, about 55% photo and 45% paper, though a top-bottom split is possible. Several photos produce separate finished images rather than one shared collage.

Who it is for. Designers and social media authors who want a calm archival look for travel and family photos without assembling it by hand in a graphics editor.

Good fit when

  • A building photo should be framed with a contour stamp on a sheet of paper.
  • A series of travel photos gets one look while each image stays a separate file.
  • In a finished piece only the stamp must change: shrink it by 10% and move it to the top right.
  • You want a typewriter caption of one to three words next to the stamp and a warm paper tone.

Not a fit when

  • You need a collage of several photos on one sheet: each photo gets its own image.
  • You require a book mock-up, scrapbook or before-and-after board.
  • The agent cannot read or generate images: the skill only describes the workflow.
  • You need exact fonts or logos: the stamp artwork is drawn by an image model.

Example request

Use $make-photo-stamp-archive to turn this photo into an archive image with a round stamp and a typewriter caption.

Limitations

The skill draws nothing itself: it needs an environment where the agent can read images and create or edit them. Output quality and fidelity of the source photo depend on the host's image model. The package holds no API keys, external fonts, scripts or extra downloads. The caption is one to three English words in capitals. The result is always a flat image, with no book, scrapbook or poster mock-up.

How to disable. Delete the `make-photo-stamp-archive` folder from `${CODEX_HOME:-$HOME/.codex}/skills`. Created images stay with you and are deleted separately.

FAQ

How do I call the make-photo-stamp-archive skill?

With a phrase like "Use $make-photo-stamp-archive to turn this photo into an archive piece with a custom stamp". If the skill does not appear after installation, restart Codex.

Can I change only part of a finished result?

Yes. Ask to keep the photograph unchanged and adjust the stamp: shape, border, size, position, ink colour, caption, paper age or splice direction.

What happens with several photos?

Each yields a separate finished image. The skill does not merge them into one collage.

Are faces and text in the photo preserved?

Yes. The skill locks people, faces, objects, buildings, signs and colour relationships of the source photo and adds or removes nothing in the photographic part.

Do I need API keys or fonts?

No. The package holds no keys, external fonts or scripts. An agent that reads and creates images is required.

Discussion

No questions or reviews yet.

Skills

A Codex skill that redraws your photo as a watercolor illustration on white paper, with wide margins and a handwritten caption

SkillMinimal access610Repository stars

A Codex skill that turns a photograph into a vertical composition with an abstract memory panel and an English title

SkillMinimal access6.1KRepository stars

A skill turns an image into a postage stamp with a perforated edge and transparent background, and tiles stamps into a sheet.

SkillMinimal access154Repository stars

A skill that makes an editorial poster from a photo: the shot stays unchanged, with an abstract panel and a local title beside it.

SkillMinimal access128Repository stars

Travel Photo Abstraction turns a photo into an editorial abstraction tied to the shape, count and position of its subjects.

SkillMinimal access800Repository stars

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

SkillMinimal access7.5KRepository stars

README in short

The README in three languages describes the visual system: photo and paper shares, stamp and caption size, blank space. Examples, environment requirements, install commands and the repository structure follow.

README badge

Original SKILL.md

---
name: make-photo-stamp-archive
description: Transform one or more supplied photos into clean direct-splice archival artworks that pair a faithfully preserved photograph with a warm-white paper panel containing a compact hand-pressed custom seal or stamp. Use for requests mentioning 图章、印章、stamp、seal、照片加图章、照片档案、左右拼接、清爽纸张、圆形章、方形章、异形章、建筑轮廓章、主体缩小、移动到角落, or iterative changes to stamp shape, border, scale, position, ink color, caption, paper age, or splice orientation.
---

# Make Photo Stamp Archive

Create one finished raster composite per source photo: a faithful photographic panel directly joined to a quiet paper panel with a compact subject-specific seal.

Read [references/prompt-template.md](references/prompt-template.md) before generating or revising an image.

## Workflow

1. Inspect every local source image with `view_image`.
2. Identify the subject, distinctive silhouette, original color memory, viewpoint, scene geometry, important text, objects, people, animals, occlusions, and visual weight.
3. Lock invariants:
   - preserve the photographic panel faithfully;
   - add, remove, duplicate, recolor, reshape, or relocate nothing;
   - preserve people, faces, age, expressions, hands, clothing, poses, and relationships;
   - preserve signs, numbers, architecture, object counts, and defining markings.
4. Choose the composition:
   - default to a landscape left/right direct splice;
   - use approximately 55% photograph and 45% paper;
   - obey an explicit top/bottom or alternate ratio request;
   - keep the main seam perfectly straight and edge-to-edge.
5. Compose the paper panel:
   - use clean warm off-white paper with subtle fibers and light scan residue;
   - keep it gently archival, not heavily yellowed, dirty, cracked, burned, or antique;
   - reserve about 70% as quiet blank paper;
   - keep the seal-and-caption group at about 30% of the paper panel;
   - place the group in a balancing corner, never centered unless explicitly requested.
6. Choose a subject-specific seal shape:
   - circle or oval for compact rounded subjects, faces, icons, or ceremonial motifs;
   - square frame for signage, dense architecture, storefronts, or when explicitly requested;
   - panoramic ridge for rows, processions, coastlines, or wide landscapes;
   - arch for windows, doors, portals, and vaulted subjects;
   - irregular silhouette for distinctive buildings, vehicles, trees, statues, or objects.
7. Render the seal with dry ink, worn halftone, broken edges, uneven pressure, and slight registration error. Preserve the source's hue relationships with one dominant localized spot color and restrained supporting inks.
8. Add a small faded typewriter caption near, never over, the seal:
   - title: 1–3 uppercase English words;
   - subtitle: 2–4 lowercase image words separated by ` / `.
9. Use the built-in image generation/editing tool. Issue one call per source photo. For revisions, edit the latest accepted composite and change only the requested property.
10. Inspect every result. Verify source fidelity, subject count, seal shape, border completeness, scale, corner, straight seam, paper age, text spelling, color memory, and absence of invented content.

## Seal Rules

Report a problem