Agent skill

Minimal Zine Poster

by boraoztunc in boraoztunc/skills

Compile a theme, sentence, object, mood, article idea, or photo into a quiet Japanese/Korean zine-style editorial poster — tall aged paper, large negative space, one small image anchor, experimental…

Apache-2.0Auto-check passedWriting & Content

Install Minimal Zine Poster

skills CLI
$ npx skills add boraoztunc/skills --skill minimal-zine-poster -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install boraoztunc/skills minimal-zine-poster --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/boraoztunc/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/minimal-zine-poster .claude/skills/minimal-zine-poster && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
minimal-zine-poster
GitHub stars
398
Token cost
~2.5k tokens
SKILL.md length
1,303 words
Files
3 (incl. scripts)
Skills in repo
52
Repo updated
First seen
Licence
Apache-2.0

At a glance

Compile a theme, sentence, object, mood, article idea, or photo into a quiet Japanese/Korean zine-style editorial poster — tall aged paper, large negative space, one small image anchor, experimental…

  • Works in 9 steps: Canvas — What is the output frame and… → Attention geometry — Where does the eye… → Image anchor — What is the one imageable… → …
  • Asked for a zine poster
  • SKILL.md covers Prompt Compiler, Color Engine, Variation Engine and Prompt Shape, plus 6 more sections
  • Runs Shell scripts from its folder; needs GEMINI_API_KEY

What it does

Minimal Zine Poster is an agent skill from boraoztunc/skills. Compile a theme, sentence, object, mood, article idea, or photo into a quiet Japanese/Korean zine-style editorial poster — tall aged paper, large negative space, one small image anchor, experimental typography, one high-chroma accent, print/scan defects — then generate the image. Use when asked for a zine poster, a minimal editorial poster, a paper-texture poster, a riso/xerox/letterpress poster, cover art for an essay or newsletter, or a poster "in that quiet Japanese zine style."

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `README.md` and `scripts/generate.sh`).

It sits in Writing & Content, covering Newsletters and Typography. The repository describes itself as: Claude Code skills for copywriting, SEO, design, and more. The licence is Apache-2.0.

When your agent uses it

  • Asked for a zine poster
  • A minimal editorial poster
  • A paper-texture poster
  • A riso/xerox/letterpress poster

Example prompts

  • “in that quiet Japanese zine style.”
  • “/minimal-zine-poster”

Requirements

  • A Bash shell
  • A credential in GEMINI_API_KEY

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. Canvas — What is the output frame and base surface?
  2. Attention geometry — Where does the eye go, and how much is empty?
  3. Image anchor — What is the one imageable subject?
  4. Anchor treatment — What material process makes the anchor belong to the paper?
  5. Typography — How does text behave visually?
  6. Color logic — What is the accent strategy?
  7. Reproduction texture — What print/scan process defines the whole image?
  8. Emotional temperature — What should the viewer feel before identifying the object?
  9. Hard avoids — See Negative Constraints.

What it can do on your machine

Read from SKILL.md and the folder at commit 645553c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • GEMINI_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Minimal Zine Poster loads about 2.5k tokens when it runs. Until then it costs about 127 tokens; SKILL.md has 1,303 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~127
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from boraoztunc/skills at commit 645553c, republished under its Apache-2.0 licence (© boraoztunc). 1,303 words, ~2,505 tokens.

Download SKILL.mdSave it as .claude/skills/minimal-zine-poster/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
minimal-zine-poster
description
Compile a theme, sentence, object, mood, article idea, or photo into a quiet Japanese/Korean zine-style editorial poster — tall aged paper, large negative space, one small image anchor, experimental typography, one high-chroma accent, print/scan defects — then generate the image. Use when asked for a zine poster, a minimal editorial poster, a paper-texture poster, a riso/xerox/letterpress poster, cover art for an essay or newsletter, or a poster "in that quiet Japanese zine style."

Minimal Zine Poster

Turn the user's content into a compiled image prompt, then generate the image from it.

Two failure modes dominate this style, and every rule below exists to prevent one of them:

  • Density creep — the poster fills up and stops being a poster. Guarded by the negative-space and cluster-size ratios.
  • Accent washout — the model reads "minimal, aged, muted" and desaturates the one color that carries the image. Guarded by the Color Engine and the banned-wording list.

Prompt Compiler

Compile only what becomes pixels. Every prompt must answer these nine questions, in this order.

  1. Canvas — What is the output frame and base surface?

    • Tall vertical paper poster; full-frame aged paper; no border, no mockup.
    • Describe the surface, not the dimensions. The aspect ratio is set through the API, not the prompt text.
  2. Attention geometry — Where does the eye go, and how much is empty?

    • 70–90% plain paper. One visual cluster occupying 8–25%. Placed center, upper-middle, lower-middle, lower-left, or upper-right. Never edge-hugging.
  3. Image anchor — What is the one imageable subject?

    • Convert the theme into a single object, fragment, photo crop, specimen, cutout, silhouette, old printed illustration, texture window, or small conceptual relation. One idea, not a scene.
  4. Anchor treatment — What material process makes the anchor belong to the paper?

    • Grayscale photos and paper fragments may take low contrast, photocopy softness, torn edge, halftone, scanline, risograph grain, xerox wear, ink bleed, or slight misregistration.
    • Never apply low saturation or low contrast to the color anchor.
  5. Typography — How does text behave visually?

    • Small serif, typewriter, or monospaced type. One short readable phrase. Optional tiny date/location/weather and a signature. Semi-legible microtext or fragmented letters. Text may drift, press against the image edge, blur, or misregister.
  6. Color logic — What is the accent strategy?

    • See Color Engine below.
  7. Reproduction texture — What print/scan process defines the whole image?

    • Flat orthographic scanned-paper appearance; matte absorbent paper; diffuse light; low-to-medium contrast; no hard shadow; no 3D depth.
  8. Emotional temperature — What should the viewer feel before identifying the object?

    • Quiet, poetic, nostalgic, sparse, diary-like, archival, distant, memory-like. Japanese/Korean indie zine or minimal editorial.
  9. Hard avoids — See Negative Constraints.

Color Engine

One visibly saturated, opaque chromatic ink anchor. Everything else is paper, gray, and black.

  • Word it concretely: fully saturated cobalt-blue risograph ink, opaque ultramarine cutout, vivid pear-green flat silhouette, clean tomato-red printed block.
  • Prefer cobalt or ultramarine. Rotate through cyan, violet, magenta-pink, lemon yellow, pear green, orange, tomato red.
  • The high-chroma area occupies roughly 0.8–2.5% of the canvas, or 15–35% of the visual cluster. It must survive being viewed as a thumbnail.
  • Color can carry the subject itself. Prefer a colored tree, fruit, shell, flower, geometric cutout, window, or poster fragment over a gray object with one colored registration tick. Do not automatically reduce the accent to a dot or a hairline.
  • Keep paper, grayscale photo, microtext, and secondary marks subdued. Preserve saturation in the anchor even while adding grain, halftone, ink bleed, or misregistration.
  • Apply low contrast and muted grayscale only to paper, photos, and secondary ink — never to the whole image.
  • One main hue per image. A tiny second hue is allowed only if it supports the subject and doesn't make the poster read as commercial.

Banned wording unless the user explicitly asks for monochrome, muted, or pastel output: near-monochrome, no strong accent, pale accent, muted accent, faded accent, pastel accent.

For batches: at least 60% of images must use a colored subject, cutout, or block. The rest may use dots, hairlines, or colored type for rhythm.

Variation Engine

Before writing the prompt, pick one from each axis. Randomness must change visual grammar, not just position. If recent outputs used the same layout or anchor, choose differently.

Layout family — center-fragment · lower-left-float · upper-right-block · dual-panel · irregular-cutout · type-led · dot-orbit · single-specimen

Image anchor — tiny faded photo · torn-paper clipping · flat silhouette · solid color block · old printed illustration · object specimen · translucent geometric overlay · abstract texture window

Typography mode — fragmented floating letters · short phrase pressed against image edge · archive microtext with date/weather · diagonal scattered words · low-contrast gray ghost text · headline-as-object with rough letterpress · text inside a color block · almost textless, one tiny caption

Texture mode — xerox softness · risograph grain · letterpress ink bleed · halftone degradation · film grain · scan noise and paper fibers · aged paper mottling · soft motion blur on selected text

Mood — quiet · summer · solitude · childhood · seaside · afternoon · night · memory · slight surrealism

Prompt Shape

Four compact paragraphs:

  1. Canvas + paper + negative space + cluster size and location
  2. Subject metaphor + anchor type + anchor treatment
  3. Typography + accent strategy + print defects
  4. Flat-scan mood + avoid-list

In paragraph 3, state the exact hue, its material form, and its approximate visual share.

Decisive beats exhaustive. Say where the anchor sits, how big it is, how the text behaves, what the accent is, how the scan looks. A concrete imageable prompt outperforms a long style essay. Specify exact in-image text only when it earns its place — image models distort long strings.

Show full SKILL.md (483 more words)Show less

Workflow

  1. Parse the content. Find the core subject, the mood, any exact text supplied, a possible visual metaphor, and the role of any reference image. For an article or complex argument, extract one central imageable idea — do not summarize the thesis. If no text is supplied, invent one short poetic phrase.

  2. Select a recipe. One pick per Variation Engine axis, then the hue via the Color Engine. Don't default to "tiny photo + blue dots + microtext" unless it genuinely fits. If the recipe gets dense, simplify typography or color treatment first.

  3. Compile the prompt into the four-paragraph shape.

  4. Generate the image — see below.

  5. Inspect at thumbnail scale. If the high-chroma anchor is absent, washed out, or reduced to an imperceptible mark, or if the poster obviously violates the recipe, tighten the prompt and regenerate once. Do not loop further; report what's still off instead.

  6. Return the image and the prompt.

Generating the Image

Run the bundled script. It writes a PNG and prints the absolute path.

bash
scripts/generate.sh "<compiled prompt>" [output-name]

The script uses Gemini 3 Pro Image and needs GEMINI_API_KEY in the environment. It renders 3:5 natively via aspectRatio, so do not restate pixel dimensions in the prompt — the canvas paragraph should describe the surface, not the resolution.

Images land in ./zine-posters/ under the current working directory unless the user names a path.

If the key is missing, the script exits with a message. Do not treat this as a task failure: return the compiled prompt and the recipe, state plainly that generation was skipped for lack of GEMINI_API_KEY, and note it can be set with export GEMINI_API_KEY=.... A prompt without an image is a partial result, and should be described as one.

Negative Constraints

Always avoid:

  • Full-bleed subject or scene
  • Commercial headline hierarchy, product ad layout, logo lockup, CTA, brand-campaign feeling
  • Clean digital UI background
  • Glossy paper mockup, heavy paper shadow
  • 3D rendering, cinematic lighting, hard shadows, depth of field, neon, cyberpunk
  • Cute cartoon, kawaii illustration, anime poster, fashion editorial drama
  • Too many objects, stickers, colors, captions, or decorative textures
  • High-resolution stock-photo realism
  • Long, clean, perfectly readable text blocks

Output Format

markdown
![Minimal zine poster](absolute-image-path)

**Prompt**

```text
[final prompt used for generation]
```

**Recipe** — layout / anchor / typography / accent / texture / mood

[one line on how the content was interpreted]

Quality Gate

Before finalizing:

  • Was a full recipe chosen — layout, anchor, typography, accent, texture, mood?
  • Is the structure materially different from recent outputs?
  • Does 70–90% read as bare paper?
  • Is the cluster roughly 8–25% of the canvas?
  • One visual metaphor, not an illustrated scene?
  • Does the anchor carry old-photo, clipping, print, scan, or specimen treatment?
  • Is typography part of the composition rather than a label on it?
  • One accent strategy only?
  • Is the high-chroma anchor visible at thumbnail size, at roughly 0.8–2.5% of canvas?
  • Did the prompt avoid the banned weakening words?
  • Did it avoid full-bleed, commercial, 3D, neon, cinematic, cartoon, and brand aesthetics?
  • Was the image actually generated — or was the skip explained?

Attribution

Adapted from LiamGvchi/gc-minimal-zine-poster (MIT). See NOTICE-liamgvchi.md in the repo root for changes made on adoption.

© boraoztunc, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in minimal-zine-poster of boraoztunc/skills.

  • SKILL.md
  • README.md
  • scripts/generate.sh

Open the folder on GitHubat commit 645553c

Compare with similar skills

Minimal Zine Poster next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Minimal Zine Poster compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Minimal Zine Poster this skillboraoztunc/skills398—~2.5kAutomated safety check: PassApache-2.0
Ultralytics Brandingfcakyon/claude-codex-settings1.2k—~1.3kAutomated safety check: PassApache-2.0
WeChat Article LayoutSpaceZephyr/design-buddy176—~1.2kAutomated safety check: PassNone
Email WriteAgriciDaniel/claude-email130—~2.8kAutomated safety check: PassMIT
Internal Communications Writeranthropics/skills180k38 repos~378Automated safety check: PassApache-2.0
Clarityaddyosmani/clarity2691 repos~1.9kAutomated safety check: PassMIT

Similar skills

  • Ultralytics Branding

    fcakyon/claude-codex-settings

    This skill should be used when creating Ultralytics-branded content of any kind, including PDF, PPTX, Canva, or Google Slides presentations, DOCX documents, marketing or newsletter HTML emails…

    1.2k GitHub stars~1.3k tokensUpdated 2 days ago
    Documents & OfficeAuto-check passed
  • WeChat Article Layout

    SpaceZephyr/design-buddy

    Turns an article into WeChat Official Account HTML with a local preview, a choice of three visual styles and a button that copies the rich HTML.

    176 GitHub stars~1.2k tokensUpdated 3 mo ago
    Writing & ContentAuto-check passed
  • Email Write

    AgriciDaniel/claude-email

    Compose high-converting emails using proven copy frameworks (PAS, AIDA, BAB, FAB, 4Ps).

    130 GitHub stars~2.8k tokensUpdated 4 mo ago
    Writing & ContentAuto-check passed
  • Official

    A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill…

    180k GitHub starsUsed in 38 repos~378 tokens
    Writing & ContentAuto-check passed
  • Clarity

    addyosmani/clarity

    Draft, rewrite, or review reader-facing prose so it is specific, useful, and recognizably the author's without inventing facts or performing humanness.

    269 GitHub starsUsed in 1 repo~1.9k tokens
    Writing & ContentAuto-check passed
  • News Aggregator Skill

    cclank/news-aggregator-skill

    Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 44+ sources including Hacker News, Lobsters, Dev.to, GitHub, arXiv, Hugging Face Papers, AIHOT, TLDR…

    1.3k GitHub stars~2.1k tokensUpdated 4 mo ago
    Writing & ContentAuto-check passed

More from boraoztunc/skills

All 52 skills in this repo
  • Gsap

    boraoztunc/skills

    GSAP animation reference for HyperFrames. An agent skill from boraoztunc/skills.

    398 GitHub starsUsed in 5 repos~1.9k tokens
    Auto-check passed
  • Hyperframes

    boraoztunc/skills

    Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML.

    398 GitHub starsUsed in 9 repos~7.6k tokens
    Auto-check passed
  • Remotion To Hyperframes

    boraoztunc/skills

    Translate an existing Remotion (React-based) video composition into a HyperFrames HTML composition.

    398 GitHub stars~2.2k tokensUpdated 1 mo ago
    Auto-check passed
  • Animejs

    boraoztunc/skills

    Anime.js adapter patterns for HyperFrames. An agent skill from boraoztunc/skills.

    398 GitHub starsUsed in 2 repos~828 tokens
    Auto-check passed
  • Beam Glow States

    boraoztunc/skills

    Create React loading, processing, selected, current, focus, and pressed states with the border-beam package's animated edge glow.

    398 GitHub starsUsed in 2 repos~3.2k tokens
    Auto-check passed
  • Beautiful Shadows

    boraoztunc/skills

    Apply exact Tailwind arbitrary shadow utilities for polished, layered neutral elevation.

    398 GitHub starsUsed in 2 repos~635 tokens
    Auto-check passed

Questions about Minimal Zine Poster

What does Minimal Zine Poster do?

Compile a theme, sentence, object, mood, article idea, or photo into a quiet Japanese/Korean zine-style editorial poster — tall aged paper, large negative space, one small image anchor, experimental…. Minimal Zine Poster is an agent skill from boraoztunc/skills. Compile a theme, sentence, object, mood, article idea, or photo into a quiet Japanese/Korean zine-style editorial poster — tall aged paper, large negative space, one small image anchor, experimental typography, one high-chroma accent, print/scan defects — then generate the image.

When should I use Minimal Zine Poster?

Minimal Zine Poster fits situations like: asked for a zine poster; A minimal editorial poster; A paper-texture poster; A riso/xerox/letterpress poster.

How do I install Minimal Zine Poster in Claude Code?

Run `npx skills add boraoztunc/skills --skill minimal-zine-poster -a claude-code`. Or copy the skill folder (minimal-zine-poster in boraoztunc/skills) into .claude/skills/minimal-zine-poster in your project. Claude Code loads it when a task matches its description.

How do I install Minimal Zine Poster in Codex?

Run `npx skills add boraoztunc/skills --skill minimal-zine-poster -a codex`. Or copy the skill folder (minimal-zine-poster in boraoztunc/skills) into .agents/skills/minimal-zine-poster in your project. Codex loads it when a task matches its description.

Can I use Minimal Zine Poster in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add boraoztunc/skills --skill minimal-zine-poster -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/minimal-zine-poster, .gemini/skills/minimal-zine-poster, .github/skills/minimal-zine-poster and .opencode/skills/minimal-zine-poster in your project.

What does Minimal Zine Poster need to run?

Going by SKILL.md and its folder, Minimal Zine Poster needs a shell for the scripts in its folder and credentials named GEMINI_API_KEY. Our summary lists: A Bash shell; A credential in GEMINI_API_KEY.

Does Minimal Zine Poster access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Minimal Zine Poster safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Minimal Zine Poster use?

Minimal Zine Poster is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Minimal Zine Poster use?

About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Minimal Zine Poster?

Skills that share tags, products or a category with Minimal Zine Poster: Ultralytics Branding (fcakyon/claude-codex-settings, 1.2k stars), WeChat Article Layout (SpaceZephyr/design-buddy, 176 stars), Email Write (AgriciDaniel/claude-email, 130 stars) and Internal Communications Writer (anthropics/skills, 180k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Minimal Zine Poster?

boraoztunc (a GitHub user) maintains it in boraoztunc/skills, which has 398 GitHub stars. The repository holds 52 skills in this directory. The repository was last updated on August 15, 2026.

Source: boraoztunc/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.