Make Photo Stamp Archive logo

Make Photo Stamp Archive

Community
Dlcccc71913
make-photo-stamp-archive

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.

Overview

PublisherDlcccc71913
Repositoryskill-make-photo-stamp-archive
Skill namemake-photo-stamp-archive
Stars
376
Forks
18
Bundled files
4
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Dlcccc71913 on GitHub. Read the source before you install it.

Installation

Install the Make Photo Stamp Archive AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Dlcccc71913/skill-make-photo-stamp-archive/tree/main
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Dlcccc71913/skill-make-photo-stamp-archive.git \
  .claude/skills/make-photo-stamp-archive
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Make Photo Stamp Archive in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Make Photo Stamp Archive on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Make Photo Stamp Archive is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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 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

  • Make the seal visually compressed rather than a miniature pasted photograph.
  • Let ink loss and halftone erosion affect the print, not the main panel seam.
  • For a square seal, show a complete unmistakably square border on all four sides. Allow slight broken ink, worn corners, uneven pressure, and misregistration; never use a clean digital frame or photo mat.
  • For a circular seal, keep the contour visibly circular while allowing restrained dry-ink gaps.
  • For a custom silhouette, preserve the subject's defining outline without enclosing it in a generic rectangle.
  • Keep signs, numbers, faces, and essential structural features legible enough to identify the source.

Revision Mapping

  • 方形边框 / square border: add one complete worn square ink frame around the existing seal motif; preserve scale and position unless asked otherwise.
  • 圆形图章 / circular seal: recast only the seal within a circular hand-pressed boundary.
  • 缩小 10%: scale the seal-and-caption group down by 10%; preserve all other layout values.
  • 移动到左上/右上/左下/右下: move only the seal-and-caption group within the paper panel.
  • 纸张不要那么旧: reduce yellowing, stains, cracks, and damage; retain subtle warm-white fibers.
  • 不要那么规整: roughen the ink boundary with restrained missing ink and halftone erosion; do not create a torn-paper collage.
  • 保留原来的颜色: strengthen recognizable source hue relationships while keeping the ink system muted.
  • 左右拼接 / 上下拼接: change only the two-panel orientation and reflow the stamp group; keep the boundary straight.

Guardrails

  • Produce one flat composite, not a book mockup, scrapbook, poster presentation, or before/after board.
  • Never use a gradient, dissolve, feather, page turn, gutter, overlap, diagonal split, or decorative separator between the two main panels.
  • Do not change the source photo to make the seal easier to design.
  • Do not let the seal dominate the paper panel or eliminate the quiet negative space.
  • Do not add decorative labels, logos, watermarks, dense copy, or invented objects.
  • For multiple photos, return one independent finished asset per photo and report every saved path.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Make Photo Stamp Archive AI skill do?

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.

Why use Make Photo Stamp Archive on TypingMind?

Because you install it once and use it with any model. Make Photo Stamp Archive is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Make Photo Stamp Archive in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Dlcccc71913/skill-make-photo-stamp-archive/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Make Photo Stamp Archive?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Make Photo Stamp Archive?

As many as you like. As long as a model supports skills, you can use Make Photo Stamp Archive with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Make Photo Stamp Archive AI skill free?

Yes. It is published on GitHub by Dlcccc71913 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇