Minimal Zine Poster Generator
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.
Create premium collectible Gunpla model-photography posters through a guided, language-aware interview and image-generation workflow.
The automated check flagged lines worth reading first. See the safety section below.
$ npx skills add agentara/skills --skill gunpla-poster -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install agentara/skills gunpla-poster --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/agentara/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/aigc/gunpla-poster .claude/skills/gunpla-poster && rm -rf skills-srcUse ~/.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/
Install the "gunpla-poster" agent skill from https://github.com/agentara/skills/tree/main/skills/aigc/gunpla-poster into .claude/skills/gunpla-poster/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gunpla-poster", 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.
$skill-installer install https://github.com/agentara/skills/tree/main/skills/aigc/gunpla-posterType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add agentara/skills --skill gunpla-poster -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install agentara/skills gunpla-poster --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentara/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/aigc/gunpla-poster .agents/skills/gunpla-poster && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "gunpla-poster" agent skill from https://github.com/agentara/skills/tree/main/skills/aigc/gunpla-poster into .agents/skills/gunpla-poster/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gunpla-poster", 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 agentara/skills --skill gunpla-poster -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install agentara/skills gunpla-poster --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentara/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/aigc/gunpla-poster .cursor/skills/gunpla-poster && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "gunpla-poster" agent skill from https://github.com/agentara/skills/tree/main/skills/aigc/gunpla-poster into .cursor/skills/gunpla-poster/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gunpla-poster", 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.
$ gemini skills install https://github.com/agentara/skills.git --path skills/aigc/gunpla-poster--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add agentara/skills --skill gunpla-poster -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install agentara/skills gunpla-poster --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentara/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/aigc/gunpla-poster .gemini/skills/gunpla-poster && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "gunpla-poster" agent skill from https://github.com/agentara/skills/tree/main/skills/aigc/gunpla-poster into .gemini/skills/gunpla-poster/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gunpla-poster", 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 agentara/skills gunpla-posterInstalls 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 agentara/skills --skill gunpla-poster -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/agentara/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/aigc/gunpla-poster .github/skills/gunpla-poster && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "gunpla-poster" agent skill from https://github.com/agentara/skills/tree/main/skills/aigc/gunpla-poster into .github/skills/gunpla-poster/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gunpla-poster", 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 agentara/skills --skill gunpla-poster -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install agentara/skills gunpla-poster --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentara/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/aigc/gunpla-poster .opencode/skills/gunpla-poster && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "gunpla-poster" agent skill from https://github.com/agentara/skills/tree/main/skills/aigc/gunpla-poster into .opencode/skills/gunpla-poster/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gunpla-poster", 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.
gunpla-posterCreate premium collectible Gunpla model-photography posters through a guided, language-aware interview and image-generation workflow.
Gunpla Poster is an agent skill from agentara/skills. Create premium collectible Gunpla model-photography posters through a guided, language-aware interview and image-generation workflow. Use this skill whenever a user asks for a Gundam, Gunpla, mobile-suit model, MG, RG, PG, MGEX, or collector-catalog poster, portrait, showcase image, or studio photograph. Ask for the mobile suit, crop, pose, environment, and aspect ratio one at a time, then generate a faithful, polished poster with restrained technical typography.
Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Requires an image-generation tool. Web access is helpful when exact official mobile-suit specifications need verification.
It sits in Media & Creative, covering Image generation and Typography. The repository describes itself as: Original and practical skills for AI builders. The licence is MIT.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 950e1bf. 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.
No scripts in the folder and no shell commands in SKILL.md.
From 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.
Requires an image-generation tool. Web access is helpful when exact official mobile-suit specifications need verification.
From compatibility in the SKILL.md frontmatter.
Gunpla Poster loads about 2.9k tokens when it runs. Until then it costs about 120 tokens; SKILL.md has 1,260 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 patterns that need a careful read before installing.
known, generate the poster immediately. Do not ask for confirmation unless an essential answer is genuinely ambiguous.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); files beside SKILL.md are not scanned.
The full file from agentara/skills at commit 950e1bf, republished under its MIT licence (© agentara). 1,260 words, ~2,942 tokens.
.claude/skills/gunpla-poster/SKILL.md (or your agent's skills folder).Create a premium Gunpla model-photography poster that feels like an official high-end Gundam collector catalog page.
Write this workflow's user-facing questions, option labels, brief explanations, and final response in the language the user is currently using. If the user changes language, follow the language used in their latest message. Keep proper nouns, model numbers, grades, and official product or mobile-suit names in their canonical form when appropriate.
The skill instructions and the image-generation prompt remain in English. Translate user answers into precise English prompt language internally when helpful, but do not force the user to answer in English.
Collect these five fields in order:
mobile_suitframingposeenvironmentaspect_ratioAsk exactly one unanswered question per turn and wait for the user's answer before asking the next one. Briefly acknowledge the selection, then ask the next question. Do not show later questions early.
If the user supplies one or more answers before being asked, save them and do not ask for them again. Continue with the earliest unanswered field. Treat “default,” “recommended,” or its equivalent in the user's language as acceptance of the stated default for the current question.
After the fifth field is known, generate the poster immediately. Do not ask for confirmation unless an essential answer is genuinely ambiguous.
Ask which Gunpla or Gundam the user wants. Offer at least five concrete candidates, all represented as MG-class or higher-end collector builds. Always allow the user to enter another mobile suit or an exact kit/grade.
Use a concise selection such as:
State that the default assumption is MG or a higher-end build. When the user names only a mobile suit, choose the most suitable MG-or-higher collector interpretation without changing the canonical design. If the requested suit has no literal MG-or-higher retail kit, render it with premium master-grade model craftsmanship while preserving the official design; do not falsely claim that a nonexistent retail kit exists.
Ask the user to choose one:
Use Bust portrait when the user chooses the default without naming an option.
Ask the user to choose one:
Keep the pose physically plausible for a premium articulated scale model. Avoid exaggerated animation, floating, or action-scene effects unless the user explicitly requests them.
Ask the user to choose one:
Studio Grey should remain the visual benchmark: light neutral gray, refined, coherent across a series, and neither pure white nor black. For other choices, keep the setting subordinate to the Gunpla and avoid clutter.
Ask this last. Offer:
Use 2:3 portrait when the user chooses the default without naming an option.
Build the final image around these priorities, in order:
Adapt the composition to the selected framing:
Faithfully reproduce the selected mobile suit's official head, antenna or V-fin, faceplate, eye shape, chest armor, shoulder armor, color blocking, vents, emblems, and signature structures. Do not redesign, kitbash, add original armor, invent weapons, or mix in parts from other mobile suits.
Use the requested kit or grade as a craftsmanship and detailing reference, but do not import features from a different variant. Distinguish variants carefully, such as Ver.Ka, EW, Destroy Mode, Full Armor, or specific color editions.
When exact model numbers, faction names, or technical specifications are uncertain, verify them using authoritative official sources if web access is available. If verification is unavailable, omit uncertain numeric specifications rather than inventing them.
Render the subject as a real, meticulously assembled collectible plastic model photographed in a professional studio:
Avoid battle damage, weathering, rust, dust, scratches, chipped paint, stains, heavy bloom, excessive lens flare, toy-like plastic, cheap product-shot styling, anime cel shading, video-game CGI, concept-art rendering, full-scale live-action robot scale, or a busy cinematic battlefield.
Place a restrained technical-information column on the right side when the composition permits. Include:
Use a low-saturation palette derived from the mobile suit's theme colors and faction identity. Keep typography, rules, insignia, and logo treatment elegant, minimal, and secondary to the model. Preserve generous negative space and a premium editorial grid.
Prefer short, legible labels. Image models may struggle with dense text, so do not fill the panel with paragraphs or unverified microcopy. Never invent an official logo. Use a restrained typographic wordmark or neutral technical insignia when a verified official mark is unavailable.
For a nonportrait or especially tight ratio, adapt the right-side column into the clearest available side panel without covering the mobile suit. Preserve the user's selected ratio rather than forcing a 2:3 crop.
After collecting all five answers, construct a self-contained English prompt using this structure:
Create a premium collectible Gunpla model-photography poster of [MOBILE SUIT / EXACT KIT], in [ASPECT RATIO].
SUBJECT AND ACCURACY
Faithfully reproduce the canonical official design of [MOBILE SUIT AND VARIANT]: exact head, V-fin or antenna, faceplate, eyes, chest armor, shoulder armor, vents, color blocking, emblems, and signature mechanical structures. Do not redesign, kitbash, or mix elements from any other mobile suit. Present it as a meticulously assembled [GRADE / COLLECTOR INTERPRETATION] scale model, not a full-scale robot.
COMPOSITION
[FRAMING-SPECIFIC DESCRIPTION]. Use a three-quarter view where compatible with the selected pose. Pose: [POSE]. Prioritize facial identity, armor layering, panel separation, decals, and realistic model articulation.
MATERIAL AND LIGHTING
High-end physical Gunpla realism, clean precision paint, crisp panel lines, fine water-slide decals, subtle plastic and painted-material response, premium collector finish. Professional studio key, fill, and rim lighting, controlled highlights, sharp focus on the face and primary armor, restrained optical depth of field.
ENVIRONMENT
[ENVIRONMENT DESCRIPTION]. Keep the background coherent, refined, uncluttered, and secondary to the model.
GRAPHIC DESIGN
Add a restrained technical-information panel on the right with the verified mobile-suit name, model number, faction or affiliation, and a few concise verified specifications or equipment facts. Use elegant low-saturation typography and graphic accents derived from the suit's theme colors and faction style. Maintain generous negative space and an official premium collector-catalog layout. Keep text sparse and legible; do not invent official logos or specifications.
NEGATIVE CONSTRAINTS
No original redesign, no kitbash, no parts from other mobile suits, no incorrect signature geometry, no battle damage, no weathering, no rust, no dust, no scratches, no chipped paint, no grime, no cheap toy appearance, no anime cel shading, no video-game CGI, no concept-art look, no battlefield, no explosions, no heavy bloom, no excessive lens flare, no cluttered background, no illegible dense text, no pure-white or pure-black background unless explicitly requested.Make the prompt concrete rather than leaving bracketed placeholders. Include only verified technical facts.
Use the available image-generation tool once the prompt is ready. If the tool supports an explicit aspect ratio parameter, set it to the user's selection; otherwise state the ratio prominently at the start and end of the prompt.
Return the generated image with a short caption in the user's current language. Mention the chosen mobile suit, framing, pose, environment, and aspect ratio. Do not expose the entire internal prompt unless the user asks for it.
If image generation fails, explain the failure briefly in the user's language and offer to retry with the same saved selections. Do not restart the interview.
© agentara, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/aigc/gunpla-poster of agentara/skills.
Open the folder on GitHubat commit 950e1bf
Gunpla 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Gunpla Poster this skillagentara/skills | 602 | — | ~2.9k | Automated safety check: Warn | MIT | |
| Minimal Zine Poster GeneratorLiamGvchi/gc-minimal-zine-poster | 7.3k | — | ~2.9k | Automated safety check: Pass | MIT | |
| Image Prompt ReverseLunarXuan/image-prompt-reverse | 479 | — | ~678 | Automated safety check: Pass | GPL-3.0 | |
| Scene Distillation Zine PosterZeejay0/gathered-scenes-zine-skill | 5.3k | — | ~7.5k | Automated safety check: Pass | Custom licence | |
| Oriental Editorial Posterdacnay816y62-hub/fantasy-dongfang-jianyuehaibao | 120 | — | ~9.6k | Automated safety check: Pass | None | |
| Prompt To Designhassancs91/claude-image-generation | 101 | — | ~3.2k | Automated safety check: Pass | MIT |
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.
LunarXuan/image-prompt-reverse
Analyze user-provided reference images and reverse-engineer high-fidelity AI image-generation prompts.
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.
dacnay816y62-hub/fantasy-dongfang-jianyuehaibao
Create finished Chinese cultural, fantasy, and minimalist text-material editorial posters or publication covers with mandatory Image 2 style image generation.
hassancs91/claude-image-generation
Generate a polished PNG graphic from a text prompt and an aspect ratio.
black-forest-labs/skills
Comprehensive guide for BFL FLUX image generation models. An agent skill from black-forest-labs/skills.
agentara/skills
Predict FIFA World Cup matches, full tournament paths, and champion probabilities through Codex-native subagents that analyze live news, weather, injuries, markets, Polymarket, tactics, and…
agentara/skills
Generate a premium 6-slide presentation design board as one single composite image.
agentara/skills
Turn a thesis, proposition, trend, question, or explainer topic into a citation-backed, image-rich, interactive website and deploy it with Vercel CLI.
agentara/skills
Turn any n reference images (with at least one person) into one exhaustively locked, always de-slopped, JSON-only AIGC image prompt whose every variable is pinned so each generation is nearly…
agentara/skills
Create AI image-generation prompts and image-generation workflows for torn-paper editorial collage style posters with layered ripped paper, rough typography, stamps, tape, stickers, cutout subjects…
agentara/skills
Render a markdown draft / any document in the conversation context into a single-file "paper proposal" HTML — serif body, monospace meta, numbered sections, inline SVG figures, callouts, tables…
Categories
Create premium collectible Gunpla model-photography posters through a guided, language-aware interview and image-generation workflow. Gunpla Poster is an agent skill from agentara/skills. Create premium collectible Gunpla model-photography posters through a guided, language-aware interview and image-generation workflow.
Gunpla Poster fits situations like: A user asks for a Gundam; mobile-suit model; collector-catalog poster; studio photograph.
Run `npx skills add agentara/skills --skill gunpla-poster -a claude-code`. Or copy the skill folder (skills/aigc/gunpla-poster in agentara/skills) into .claude/skills/gunpla-poster in your project. Claude Code loads it when a task matches its description.
Run `npx skills add agentara/skills --skill gunpla-poster -a codex`. Or copy the skill folder (skills/aigc/gunpla-poster in agentara/skills) into .agents/skills/gunpla-poster 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 agentara/skills --skill gunpla-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/gunpla-poster, .gemini/skills/gunpla-poster, .github/skills/gunpla-poster and .opencode/skills/gunpla-poster in your project.
SKILL.md names no scripts, command-line tools or credentials: Gunpla Poster is instructions for the agent only. Compatibility (from SKILL.md): Requires an image-generation tool. Web access is helpful when exact official mobile-suit specifications need verification..
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 flagged 1 warning(s): tells the agent its actions are pre-authorized / not to stop for confirmation. Read the flagged lines before installing; the check is not a guarantee either way.
Gunpla Poster is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.9k tokens (SKILL.md is roughly 12k 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 Gunpla Poster: Minimal Zine Poster Generator (LiamGvchi/gc-minimal-zine-poster, 7.3k stars), Image Prompt Reverse (LunarXuan/image-prompt-reverse, 479 stars), Scene Distillation Zine Poster (Zeejay0/gathered-scenes-zine-skill, 5.3k stars) and Oriental Editorial Poster (dacnay816y62-hub/fantasy-dongfang-jianyuehaibao, 120 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
agentara (a GitHub organization) maintains it in agentara/skills, which has 602 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on September 29, 2026.
Source: agentara/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.