Scene Distillation Zine Poster
Zeejay0/gathered-scenes-zine-skill
Turns a supplied photo into a minimal zine-style poster with a clear artistic idea, empty space, saturated color and authored typography.
Generate original one-ink or controlled two-ink editorial images from any theme, sentence, article idea, object, or reference photo.
$ npx skills add yanliudesign/mono-color-skill --skill mono-color -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install yanliudesign/mono-color-skill mono-color --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "mono-color" agent skill from https://github.com/yanliudesign/mono-color-skill/tree/main into .claude/skills/mono-color/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mono-color", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yanliudesign/mono-color-skill --skill mono-color -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install yanliudesign/mono-color-skill mono-color --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mono-color" agent skill from https://github.com/yanliudesign/mono-color-skill/tree/main into .agents/skills/mono-color/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mono-color", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yanliudesign/mono-color-skill --skill mono-color -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install yanliudesign/mono-color-skill mono-color --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "mono-color" agent skill from https://github.com/yanliudesign/mono-color-skill/tree/main into .cursor/skills/mono-color/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mono-color", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yanliudesign/mono-color-skill --skill mono-color -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install yanliudesign/mono-color-skill mono-color --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "mono-color" agent skill from https://github.com/yanliudesign/mono-color-skill/tree/main into .gemini/skills/mono-color/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mono-color", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install yanliudesign/mono-color-skill mono-colorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add yanliudesign/mono-color-skill --skill mono-color -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "mono-color" agent skill from https://github.com/yanliudesign/mono-color-skill/tree/main into .github/skills/mono-color/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mono-color", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yanliudesign/mono-color-skill --skill mono-color -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install yanliudesign/mono-color-skill mono-color --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "mono-color" agent skill from https://github.com/yanliudesign/mono-color-skill/tree/main into .opencode/skills/mono-color/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mono-color", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
mono-colorGenerate original one-ink or controlled two-ink editorial images from any theme, sentence, article idea, object, or reference photo.
Mono Color is an agent skill from yanliudesign/mono-color-skill. Generate original one-ink or controlled two-ink editorial images from any theme, sentence, article idea, object, or reference photo. Always use this skill when the user asks for 单色海报、双色印刷、单色调视觉、蓝色/绿色孔版印刷、risograph、网点照片、复古或当代编辑排版、zine poster, monochrome editorial poster, duotone print, or asks to use the mono-color style. It uses an adaptive white, gray, or pale-beige substrate, no more than two printing inks, active negative space, terse human language, and strong serif/grotesk/mono typography without making…
Its SKILL.md is about 8.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 74 other files, including scripts (for example `.github/workflows/validate.yml`, `ASSET-LICENSE.md` and `CHANGELOG.md`).
It sits in Media & Creative, covering Typography and Generative and creative coding. The repository describes itself as: One-ink editorial print image skill — warm paper, halftone photography, active negative space, and restrained typography. The licence is MIT.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit c8ff705. It shows what the files ask for, not the result of running them.
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.
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
claudeFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Mono Color loads about 8.5k tokens when it runs. Until then it costs about 183 tokens; SKILL.md has 4,429 words of instructions outside code blocks.
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.
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.
The full file from yanliudesign/mono-color-skill at commit c8ff705, republished under its MIT licence (© yanliudesign). 4,429 words, ~8,473 tokens.
.claude/skills/mono-color/SKILL.md (or your agent's skills folder). This skill also uses 70 other files; get the full folder from GitHub.Turn any user theme or image into an original printed editorial artifact with one stable visual language:
adaptive neutral substrate + one or two inks + reproduced image + typographic tension + concise human voice
Do not imitate any one reference. Recombine the system below into a new composition every time.
Create:
Save generated files under ~/Desktop/Claude skills/mono-color/ when a file path is available. Create the folder if needed. Stop at prompt-only only when the user explicitly asks for it or no image-generation capability is available.
Extract four things before composing:
For a complex topic, choose one concrete visual metaphor. Do not illustrate every point.
When the user supplies an image, preserve its identity and core factual content. In faithful reproduction, crop, isolate, enlarge, simplify, or convert it to halftone. In abstract symbol extraction, preserve 2-4 identifying anchors while replacing photographic description with simplified masses, contours, repeated marks, and exposed paper. Never replace the subject or invent branded details.
Before writing the generation prompt, resolve the input into this manifest. Do not skip fields and do not expose the manifest unless the user asks for process details.
Use the machine-readable catalogs in design-system/ as the source of truth for palette IDs, typography roles, composition geometry, carrier signals, visual rhythm, and controlled print imperfections. Read only the relevant catalog for the current decision. The prose below explains intent; when an exact value differs, the catalog wins.
subject: <one recognizable subject>
intent: <one intent from Input Reading>
exact_text: <user text, generated 2-8 word phrase, or none>
text_language: <language of supplied text, otherwise English>
representation: <faithful reproduction or abstract symbol extraction>
ratio: <explicit ratio or 3:4>
carrier: <one carrier ID from design-system/carriers.json or none>
substrate: <one substrate ID and exact hex from design-system/colors.json>
mode: <pure one-ink, chromatic + black, complementary duotone, or overprint duotone>
palette: <one palette ID from design-system/colors.json>
inks: <the palette's named ink or approved pair with exact hex values>
plate_roles: <one explicit role per ink plate>
layout: <one composition ID from design-system/compositions.json>
empty_paper: <explicit percentage>
visual_tension: <relaxed, balanced, or assertive from design-system/rhythm.json>
focal_event: <one strong visual event from design-system/rhythm.json>
release_zone: <one deliberately quiet region that gives the focal event room>
unresolved_edge: <one optional edge behavior from design-system/rhythm.json or none>
image_treatment: <one mechanical reproduction process>
type_hierarchy: <one role ID from design-system/typography.json>
disruption: <one deliberate disruption>
imperfection_seed: <stable hash derived from the resolved recipe>
imperfections: <0-2 restrained effect IDs for contemporary work, or 2-3 for tactile/vintage work>Use these defaults whenever the user has not made the choice:
3:4;faithful reproduction, unless the user asks for abstract, artistic, loose, experimental, less realistic, or less photographic treatment;#FAFAF7, Cool Gray #E9E9E5, or Pale Beige #F5F1E8 according to the subject, image values, and ink contrast. Neutral White is the unspecified default; never assume beige or aged paper merely because the work uses halftone or risograph language;#2148B8 + #C65F38 for an unspecified subject, then select the closest approved pair for the subject. The dominant plate carries 70%-85% and the accent plate carries 15%-30%. Switch to pure one-ink only when the user explicitly requests one ink, monochrome, or one named ink without a second color;35%;relaxed for reflective, travel, summer, leisure, lifestyle, and unspecified cultural subjects; balanced for ordinary events and editorial information; assertive only when the user requests a forceful declaration or the phrase itself is the subject;design-system/typography.json. Use Literary for intimate or quiet subjects, Cultural Grotesk for music and contemporary culture, Condensed Civic for public events, Programmatic when dates or structured facts lead, Rotated Display for bold covers, Handwritten Interjection only as a secondary human voice, and Typographic Object when the phrase itself is the image;Explicit user choices override defaults unless they violate the two-ink limit or the originality firewall. For identical inputs, resolve the same manifest; do not vary palette, layout, percentages, or process merely for novelty. This stabilizes the design procedure while image-generation details may still vary.
Resolve generic color words consistently: blue to Cobalt, green to Botanical Green, orange to Terracotta Orange, red to Signal Red, purple to Aubergine, and black to Charcoal. For generic green + black, use Mint Green + Charcoal. For generic blue + orange, use Cobalt + Terracotta. Exact named inks always take precedence over these aliases.
Default to controlled two-ink. Give the dominant and accent plates separate content roles before composing; never use the second ink merely to decorate the page. Switch to pure one-ink when the user explicitly requests one ink, monochrome, or one named ink without a second color. The paper substrate does not count as an ink.
#FAFAF7, Cool Gray #E9E9E5, or Pale Beige #F5F1E8. White suits crisp cultural, social, event, and colorful image-led work; cool gray suits architecture, technology, charcoal-led systems, and restrained branding; pale beige suits tactile, food, travel, intimate, archival, or explicitly nostalgic subjects.#2148B8, the default for technology, knowledge, cities, music, and cultural subjects.#2058D4, a brighter branch for youth culture, fashion, movement, and energetic editorial pages.#008A4B, for botanical, ecological, archival, and explicitly green subjects.#5EB783, for observation journals, soft natural subjects, and quiet editorial photography.#C65F38, for classical art, food, travel, summer, and tactile objects.#C83232, for declarations, music, events, and civic or public-culture subjects.#63365F, for literature, cinema, night, and intimate cultural subjects.#30343A, for architecture, photography, research, and restrained publications.Use a known pair rather than improvising arbitrary colors:
#9EB8D3 + #C83232 for guides, announcements, and information-heavy editorial pages.#2148B8 + #C65F38 for travel, summer, food, and lifestyle subjects.#008A4B + #8F3434 for plants, natural wine, bookstores, and archives.#30343A + #C83232 for architecture, exhibitions, reports, and conceptual work.#173AE3 + #242321 for high-contrast cultural events and image-led editorial pages.#5EB783 + #302D2E for journals, essays, observations, and long-form reading.#263E99 + #E55D2B for movement, objects, youth culture, and active urban subjects.#159DDA + #B64032 for repeated products, exhibitions, and playful information systems.#E46C2D + #4773A5 for markets, festivals, illustrated notices, and large typographic compositions.Assign each plate a role before composing. Never scatter two colors as arbitrary decoration. These constraints keep the result mechanically printed rather than digitally color-graded.
3:4 vertical poster. Respect a user-specified ratio.Negative space is active pacing, not leftover room.
Read design-system/rhythm.json whenever the user asks for relaxed, loose, effortless, casual, quiet, breezy, or understated work, or when the default intent maps to relaxed. Treat relaxation as a compositional decision, not a soft-focus mood.
Relaxation is uneven energy, not low energy. For relaxed work, choose exactly one strong focal event: oversized type, an extreme crop, one giant object or detail, a concentrated overprint collision, or one abnormal scale relationship. Let it feel decisive. Then release the rest of the page with open paper, pale screening, sparse support type, or one quiet alignment. Do not make every element tasteful, small, or equally calm.
The reference set shares an object-and-type construction, not a generic retro mood. Build every page from these four moves:
Choose one dominant object and one dominant typographic event before adding secondary information. If either is missing, simplify rather than filling the page with mood-setting decoration.
Convert photographs and illustrations into the selected ink plate or plates plus substrate. Choose reproduction intensity from the subject instead of automatically aging every image:
When no source image is supplied, do not default to a polished photorealistic hero person or a complete stock-photo figure. Prefer 2-4 identifying anchors such as a hand on a handlebar, one bent leg, a wheel arc, loose fabric, or hair direction. Build the subject from a partial editorial crop, simplified screened fragment, and one ordinary in-between gesture. For movement subjects, the object or cropped body relationship may carry the focal event while the person remains incomplete. Avoid advertising poses, victory gestures, athletic hero angles, catalog-style full bodies, and the safe headline-left/photo-right split unless the user asks for them.
When representation is abstract symbol extraction, transform the supplied image into a small visual vocabulary instead of applying a stylized filter to the whole photograph:
For complementary duotone abstraction, assign the dominant ink to structure and rhythm, and reserve the accent ink for one identity anchor or one annotation. Do not distribute the accent evenly across the page.
Keep composition, wording, palette, and hierarchy deterministic. Introduce looseness only in the reproduction layer. Contemporary work selects 0-2 restrained effects; tactile, vintage, or archival-aging work selects 2-3 effects from design-system/imperfections.json with the resolved recipe's stable seed.
Use one dominant image zone occupying 45%-80% of the page, 1-3 isolated specimens whose combined area stays in that range, or one repeated object system. A ruled information poster may reduce the image zone to 32%-55% only when real supplied information needs the space. Dense overlap is allowed only in the overprint collage family; it must still read as two printing plates rather than scrapbook decoration.
Typography is a responsive cast, not a fixed house font. Read design-system/typography.json and choose one primary display skeleton from the subject, wording, and information structure. A series may move between literary serif, wide cultural grotesk, compressed civic sans, engineered program type, rotated display, and word-as-object typography. Consistency across a set comes from ink, spacing, plate logic, and disciplined microtype; do not force every image into the same serif-plus-mono treatment.
Build each image with one primary display voice and one functional support voice. A third voice is allowed only as one short handwritten interjection. Handwriting supplies human interruption, never dates, locations, essential facts, or long copy.
Choose at most one typographic behavior per image:
Do not repeat the same display category across every item in a multi-scene request unless the user explicitly asks for a unified typographic campaign.
Rules:
relaxed work, create a clear strength difference: one typographic move may be audacious while all supporting type becomes sparse and functional.Write like an independent cultural poster, field journal, or community print notice:
For summer, movement, travel, leisure, music, and night subjects, make romantic freedom the default emotional register. Express it through a physical sensation, an open direction, an unhurried gesture, or a small relationship between subject and space. Favor fresh English fragments such as an observation or invitation, never a generic motivational slogan. For factual, civic, scientific, or archival subjects, let clarity override this romantic default.
If text must be invented, prefer an English observation, plain declaration, object label, or small contradiction. Never reuse wording visible in reference images or repeat a stock phrase across unrelated outputs.
For romantic, intimate, nostalgic, or poetic prompts, express feeling through one observable relationship: two figures sharing one edge, an object carrying signs of use, a crop that implies closeness, or a small distance between forms. Do not default to string lights, wine glasses, fluttering fabric, stars, flowers, sunset silhouettes, or cinematic haze. Those props describe a romance category; a specific relationship creates romance while preserving the reference set's graphic directness.
Choose the layout from the content, not at random. Walk this list from top to bottom and use the first matching rule unless the user explicitly requests a layout:
Write the final prompt in five compact paragraphs, in this order:
Describe only visible outcomes. Do not mention reference artists, studios, sample posters, or “in the style of.”
The reference is evidence for a visual grammar, never a layout to trace.
Before generation, change at least four of these from any supplied reference:
Never reproduce a reference's exact object arrangement, line breaks, labels, dates, logos, border system, or distinctive slogan. Never include fake signatures or publication marks. If the user's source image contains protected or branded material, transform only the user's provided material and avoid presenting the result as an official artifact.
Always exclude:
**生成图**

**最终 Prompt**
```text
[prompt used for generation]
```
**本次配方**
- Mode: [pure one-ink / chromatic + black / complementary duotone / overprint duotone]
- Ink: [exact one- or two-ink palette and hex values]
- Layout: [layout family]
- Type: [editorial voice + utility voice]
- Process: [halftone/risograph/cyanotype/photocopy treatment]
- Originality: [one sentence naming the major structural departures from references]© yanliudesign, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 70 other files (scripts) in the repository root of yanliudesign/mono-color-skill.
Open the folder on GitHubat commit c8ff705
Mono Color 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Mono Color this skillyanliudesign/mono-color-skill | 3.4k | — | ~8.5k | Automated safety check: Pass | MIT | |
| Scene Distillation Zine PosterZeejay0/gathered-scenes-zine-skill | 5.4k | — | ~7.5k | Automated safety check: Pass | Custom licence | |
| Video Poster DesignMagicCube/agentara | 516 | 1 repos | ~2.5k | Automated safety check: Pass | None | |
| Algorithmic Art with p5.jsanthropics/skills | 180k | 38 repos | ~4.9k | Automated safety check: Pass | Apache-2.0 | |
| Canvas Designanthropics/skills | 180k | 52 repos | ~3k | Automated safety check: Pass | Apache-2.0 | |
| Anthropic Brand Stylinganthropics/skills | 180k | 30 repos | ~559 | Automated safety check: Pass | Apache-2.0 |
Zeejay0/gathered-scenes-zine-skill
Turns a supplied photo into a minimal zine-style poster with a clear artistic idea, empty space, saturated color and authored typography.
MagicCube/agentara
Create cinematic movie poster concepts and final poster images from a user's brief, existing video plan, storyboard, character design, or project context.
anthropics/skills
Creates original generative art in two steps: a written algorithmic philosophy, then a p5.js sketch with seeded randomness and an interactive viewer for exploring parameters.
anthropics/skills
Creates original posters and static art as PNG or PDF by first writing a short design philosophy, then expressing it visually on a canvas.
anthropics/skills
Applies Anthropic's brand colors and fonts to artifacts such as PowerPoint slides, using fixed hex values for text and accents, Poppins headings and Lora body text.
LiamGvchi/gc-minimal-zine-poster
Creates or analyzes quiet, paper-texture zine posters with big negative space, one color accent and experimental type, returning an image prompt and the generated poster.
Categories
Generate original one-ink or controlled two-ink editorial images from any theme, sentence, article idea, object, or reference photo. Mono Color is an agent skill from yanliudesign/mono-color-skill. Generate original one-ink or controlled two-ink editorial images from any theme, sentence, article idea, object, or reference photo.
Mono Color fits situations like: the user asks for 单色海报、双色印刷、单色调视觉、蓝色/绿色孔版印刷、risograph、网点照片、复古或当代编辑排版、zine poster; monochrome editorial poster; asks to use the mono-color style.
Run `npx skills add yanliudesign/mono-color-skill --skill mono-color -a claude-code`. Or copy the skill folder (the yanliudesign/mono-color-skill repository) into .claude/skills/mono-color in your project. Claude Code loads it when a task matches its description.
Run `npx skills add yanliudesign/mono-color-skill --skill mono-color -a codex`. Or copy the skill folder (the yanliudesign/mono-color-skill repository) into .agents/skills/mono-color in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add yanliudesign/mono-color-skill --skill mono-color -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mono-color, .gemini/skills/mono-color, .github/skills/mono-color and .opencode/skills/mono-color in your project.
Going by SKILL.md and its folder, Mono Color needs the command-line tools its instructions call (claude).
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
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.
Mono Color is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 8.5k tokens (SKILL.md is roughly 34k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Mono Color: Scene Distillation Zine Poster (Zeejay0/gathered-scenes-zine-skill, 5.4k stars), Video Poster Design (MagicCube/agentara, 516 stars), Algorithmic Art with p5.js (anthropics/skills, 180k stars) and Canvas Design (anthropics/skills, 180k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
yanliudesign (a GitHub user) maintains it in yanliudesign/mono-color-skill, which has 3,385 GitHub stars. The repository was last updated on September 2, 2026.
Source: yanliudesign/mono-color-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.