Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/fluentlc/shiny-skillsnpx agentmods add skills/fluentlc/shiny-skills/image-creation-prompt-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fluentlc/shiny-skills/image-creation-prompt-skill)<a href="https://agentmods.dev/skills/fluentlc/shiny-skills/image-creation-prompt-skill"><img src="https://agentmods.dev/badge/skills/fluentlc/shiny-skills/image-creation-prompt-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fluentlc/shiny-skills/image-creation-prompt-skill"><img src="https://agentmods.dev/badge/skills/fluentlc/shiny-skills/image-creation-prompt-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00079 | $0.02309 |
| Opus 5 | $0.00039 | $0.01154 |
| Sonnet 5 | $0.00016 | $0.00462 |
| Haiku 4.5 | $0.00008 | $0.00231 |
Grade A, and why
image-creation-prompt-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shiny Image Creation Prompt Skill
Overview
Transforms simple image creation requests into detailed, structured prompts optimized for AI image generators (Banana2, Banana Pro, Midjourney, DALL-E, Stable Diffusion, etc.). Style templates are stored in styles/ and loaded on demand — only the matched style enters context.
Input Parsing
User input format (flexible): [topic], [style], [aspect ratio]
Examples:
生成一张从Function Call到MCP到SKILL的发展历程图片，哆啦A梦风格，16:9创建一张微服务架构图，黑板报风格，4:3画一张AI学习路线，手绘涂鸦风格
Parse into:
- topic: The subject/concept to visualize
- style: Match against the Style Registry below
- aspect_ratio: Default
16:9if not specified
Generation Process
- Parse user input → extract topic, style, aspect ratio
- Match style name/keywords → find entry in Style Registry
- Load the matched style file using the Read tool
- Decompose topic into 3–5 logical steps or content sections
- Fill template with topic-specific content (labels, descriptions, visuals, dialogue)
- Output the complete structured prompt as a single code block
Style Registry
| Style Name | Keywords | File |
|---|---|---|
| 哆啦A梦风格 (Doraemon) | 哆啦A梦、doraemon、藤子、漫画角色 | styles/doraemon.md |
| 简约手绘涂鸦插画风格 (Doodle) | 手绘、涂鸦、doodle、插画、素描 | styles/doodle.md |
| 黑板报风格 (Chalkboard) | 黑板、粉笔、chalkboard、黑板报 | styles/chalkboard.md |
| 吉伊卡哇风格 (Chiikawa) | 吉伊卡哇、chiikawa、ちいかわ、治愈 | styles/chiikawa.md |
| 蜡笔小新搞怪涂鸦风格 (Shin-chan) | 蜡笔小新、小新、shin-chan、搞怪涂鸦 | styles/shinchan.md |
| 复古怀旧手绘插画风格 (Vintage Sketchnote) | 复古、怀旧、vintage、sketchnote、手绘插画 | styles/vintage-sketchnote.md |
| 黏土定格动画风格 (Claymation) | 黏土、定格动画、claymation、clay | styles/claymation.md |
| 美式波普漫画风小红书插图风格 (Pop Art Xiaohongshu) | 波普、漫画、小红书、pop art、xiaohongshu | styles/pop-art-xiaohongshu.md |
| 美式超级英雄漫画风格 (Superhero Comic) | 超级英雄、漫威、DC、marvel、superhero、comic | styles/superhero-comic.md |
| 动漫人物手捧本尊手办风格 (Anime Figurine) | 手办、cosplay、figurine、本尊手办 | styles/anime-figurine.md |
| 物品爆炸视图风格 (Exploded View) | 爆炸视图、结构解析、exploded view、拆解 | styles/exploded-view.md |
| 赛博朋克风科普插图风格 (Cyberpunk) | 赛博朋克、cyberpunk、霓虹、未来科技 | styles/cyberpunk.md |
| 白板手绘风格科普插画风格 (Whiteboard) | 白板、whiteboard、马克笔、手绘白板 | styles/whiteboard.md |
| 吉卜力风格科普插画 (Ghibli) | 吉卜力、宫崎骏、ghibli、miyazaki、龙猫 | styles/ghibli.md |
| 可爱卡哇伊贴纸风 (Kawaii Sticker) | 卡哇伊、kawaii、贴纸、sticker、可爱 | styles/kawaii-sticker.md |
| 人物角色设定图 (Character Design Sheet) | 角色设定、设定图、character design、设定稿 | styles/character-design-sheet.md |
| 撕纸分层特效 (Torn Paper Effect) | 撕纸、分层特效、torn paper、纸层 | styles/torn-paper.md |
| 柔和简洁信息图表风格 (Soft Infographic) | 柔和、简洁、信息图表、soft infographic、信息架构 | styles/soft-infographic.md |
| 小清新风格插画模板 (Fresh Minimalist) | 小清新、清新、fresh、扁平插画、治愈系 | styles/fresh-minimalist.md |
| 卡通流程图风格模板 (Cartoon Flowchart) | 卡通流程图、3D卡通、floating island、游戏关卡 | styles/cartoon-flowchart.md |
| 城市窗外风景照 (City Window View) | 城市窗外、窗边风景、window view、室内外 | styles/city-window-view.md |
| 日系黑白少年漫 (Shounen Manga) | 少年漫、黑白漫画、shounen、manga、分镜 | styles/shounen-manga.md |
| 街景 AR 标注图 (AR Annotation) | AR标注、街景标注、ar annotation、导览图 | styles/ar-annotation.md |
| 日系人物九宫格大头贴 (Photo Booth Strip) | 九宫格、大头贴、purikura、photo booth | styles/photo-booth-strip.md |
| 电影主题复古邮票 (Vintage Stamp) | 复古邮票、vintage stamp、邮票、postal | styles/vintage-stamp.md |
| 经典电影生成 PS1 游戏盒 (PS1 Game Case) | PS1、游戏盒、playstation、game case、retro game | styles/ps1-game-case.md |
| 珐琅徽章风格物品图 (Enamel Pin) | 珐琅徽章、enamel pin、徽章、pin badge | styles/enamel-pin.md |
| 复古报纸风格 (Vintage Newspaper) | 复古报纸、newspaper、报纸、newsprint | styles/vintage-newspaper.md |
| 黑白卡通科普插画风格 (Black & White Educational Comic) | 黑白卡通、科普插画、line art、children science | styles/black-white-educational-comic.md |
| 真实感手写笔记风格 (Handwritten Math Notes) | 手写笔记、math notes、notebook、academic handwriting | styles/handwritten-math-notes.md |
| 拼贴海报风格 (Urban Collage Poster) | 拼贴海报、collage poster、涂鸦、个人介绍 | styles/urban-collage-poster.md |
| 金色奢华盛典风格 (Luxury Event Poster) | 奢华盛典、luxury event、金色、颁奖典礼 | styles/luxury-event-poster.md |
| 国风山水意境风格 (Chinese Ink Landscape) | 国风山水、chinese ink、水墨、汉服 | styles/chinese-ink-landscape.md |
| 3D卡通手办风格 (3D Cartoon Collectible Figure) | 3D手办、collectible figure、桌面摆件、程序员手办 | styles/3d-cartoon-figure.md |
| 3D卡通手办盲盒风格 (3D Cartoon Blind Box Figure) | 盲盒、blind box、chibi、潮玩 | styles/3d-cartoon-blind-box.md |
| 科技光效海报风格 (Futuristic Neon Poster) | 科技海报、neon poster、新品发布、光效 | styles/futuristic-neon-poster.md |
| 科技蓝光粒子流风格 (Cyberpunk Particle Stream) | 粒子流、particle stream、大会海报、cyberpunk | styles/cyberpunk-particle-stream.md |
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- CONTRIBUTE.md 2.8 KB
- CONTRIBUTE.zh.md 2.5 KB
- examples/3d-cartoon-blind-box-example.md 1.3 KB
- examples/3d-cartoon-figure-example.md 1.5 KB
- examples/anime-figurine-example.md 1.7 KB
- examples/ar-annotation-example.md 1.8 KB
- examples/black-white-educational-comic-example.md 3.3 KB
- examples/cartoon-flowchart-example.md 2.6 KB
- examples/chalkboard-example.md 2.9 KB
- examples/character-design-sheet-example.md 1.5 KB
- examples/chiikawa-example.md 2.8 KB
- examples/chinese-ink-landscape-example.md 1.6 KB
- examples/city-window-view-example.md 1.3 KB
- examples/claymation-example.md 2.6 KB
- examples/cyberpunk-example.md 3.4 KB
- examples/cyberpunk-particle-stream-example.md 1.3 KB
- examples/doodle-example.md 2.4 KB
- examples/doraemon-example.md 3.9 KB
- examples/enamel-pin-example.md 1.2 KB
- examples/exploded-view-example.md 1.9 KB
- examples/fresh-minimalist-example.md 2.9 KB
- examples/futuristic-neon-poster-example.md 1.3 KB
- examples/ghibli-example.md 3.4 KB
- examples/handwritten-math-notes-example.md 1.9 KB
- examples/kawaii-sticker-example.md 2.4 KB
- examples/luxury-event-poster-example.md 1.6 KB
- examples/photo-booth-strip-example.md 1.4 KB
- examples/pop-art-xiaohongshu-example.md 3.3 KB
- examples/ps1-game-case-example.md 1.3 KB
- examples/shinchan-example.md 3.3 KB
- examples/shounen-manga-example.md 1.3 KB
- examples/soft-infographic-example.md 2.2 KB
- examples/superhero-comic-example.md 3.9 KB
- examples/torn-paper-example.md 2.9 KB
- examples/urban-collage-poster-example.md 1.8 KB
- examples/vintage-newspaper-example.md 3.0 KB
- examples/vintage-sketchnote-example.md 3.3 KB
- examples/vintage-stamp-example.md 1.5 KB
- examples/whiteboard-example.md 3.4 KB
- gallery/3d-cartoon-blind-box.png 1105 KB
- gallery/3d-cartoon-figure.png 1406 KB
- gallery/anime-figurine.png 2402 KB
- gallery/ar-annotation.png 6380 KB
- gallery/black-white-educational-comic.png 877 KB
- gallery/cartoon-flowchart.png 5085 KB
- gallery/chalkboard.png 5832 KB
- gallery/character-design-sheet.png 2422 KB
- gallery/chiikawa.png 4617 KB
- gallery/chinese-ink-landscape.png 1806 KB
- gallery/city-window-view.png 6867 KB
- gallery/claymation.png 2374 KB
- gallery/cyberpunk-particle-stream.png 1142 KB
- gallery/cyberpunk.png 2857 KB
- gallery/doodle.png 4327 KB
- gallery/doraemon.png 5205 KB
- gallery/enamel-pin.png 6749 KB
- gallery/exploded-view.png 2145 KB
- gallery/fresh-minimalist.png 1755 KB
- gallery/futuristic-neon-poster.png 1782 KB
- gallery/ghibli.png 3795 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 105 lines · 79 tokens per session scan A 4f1d2c526a9d
image-creation-prompt-skill is a skill published in the GitHub repository fluentlc/shiny-skills (16 stars, last pushed 3mo ago), licensed MIT. It adds 79 tokens to every session and 2,309 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…