Image Generation Skills for AI Agents
Image generation skills cover the full pipeline an agent needs to produce and refine visual assets: text to image, editing and inpainting, model selection, style control, upscaling and restoration, and brand asset work. The practical order of operations is prompt, model, style control, then edit and upscale — and editing often matters more than generation, because most real jobs start from an existing image rather than a blank canvas. Use the ranked list by matching your task to a sub-topic first, then read each entry for the model and control surface it exposes. If you need a finished asset, favor skills that cover editing and upscaling alongside generation; if you need volume or a specific look, prioritize style control and model coverage.
8 to start with24 top options
Start with these.
Image work is prompt, model, style control, then edit and upscale — editing often matters more than generation.
These are the closest matches for this work. Start with the first one and open it to install.
- Rank 01View Agent SkillDirect
imagegen
OfficialGenerate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas.
- Rank 02View Agent SkillDirect
ai-image-generation
NotableGenerate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, i
142,155 · popularity - Rank 03View Agent SkillDirect
baoyu-image-gen
Generates images via multiple providers (OpenAI GPT Image, Azure, Google, OpenRouter, DashScope, Seedream, Replicate) with text-to-image, reference images, aspect ratios, and batch generation from prompt files.
33,010 · popularity - Rank 04View Agent SkillDirect
gpt-image-2
GPT Image 2 generation/editing skill with 80+ structured prompt templates across posters, UI, product, infographics, comics, and storyboards, operating in local, host-native, or advisor modes.
5,237 · popularity - Rank 05View Agent SkillDirect
eachlabs-image-edit
Edits, transforms, upscales, and enhances images using 130+ EachLabs models, covering style transfer, background removal, inpainting, face swap, and upscaling.
762 · popularity - Rank 06View Agent SkillDirect
nano-banana-pro-openrouter
Generates and edits images via OpenRouter with the Gemini 3 Pro Image model, supporting prompt-only generation, single-image edits, multi-image compositing, and 1K/2K/4K output.
9,886 · popularity - Rank 07View Agent SkillDirect
image-generation
Generates images from structured JSON prompts with optional reference images for style and composition, via a bundled Python script.
2,886 · popularity - Rank 08View Agent SkillDirect
image
NotableWhen the user wants to create, generate, edit, or optimize images for marketing — blog heroes, social graphics, product mockups, profile banners, listing visuals, or brand assets. Also use when the user mentions 'AI image generation,' 'generate an image,' 'create a graphic,' 'product mockup,' 'hero image,' 'social media graphic,' 'banner image,' 'cover photo,' 'profile banner,' 'listing screenshot,' 'Flux,' 'Flux Kontext,' 'Midjourney,' 'DALL-E,' 'GPT Image,' 'ChatGPT Images,' 'Ideogram,' 'Gemini image,' 'Nano Banana,' 'Recraft,' 'Stable Diffusion,' 'Canva,' 'Figma,' 'image optimization,' 'com
69,825 · popularity
Explore 16 more Agent Skills
- Rank 09View Agent SkillDirect
p-image
Generates and edits images with Pruna P-Image models via the inference.sh CLI, covering text-to-image, LoRA styles, image editing, and multi-image compositing.
10 · popularity - Rank 10View Agent SkillDirect
gpt-image-2-style-library
Turns image-generation intent into production-ready GPT-Image2 prompts using a repository-backed style library of templates, categories, style tags, and example cases.
3,804 · popularity - Rank 11View Agent SkillDirect
ai-image-prompts-skill
Recommends curated prompts from a 10,000+ real-world image generation prompt library, working with any text-to-image model and including sample images.
1,060 · popularity - Rank 12View Agent SkillDirect
muapi-nano-banana
Reasoning-driven image generation using structured creative briefs (Gemini 3 style) via muapi.ai, with logic-based prompting, text rendering, and optical directives.
2,700 · popularity - Rank 13View Agent SkillDirect
guizang-material-illustration
Generates Guizang-style material illustrations, labeled explanatory visuals, and data-first editorial images from articles, notes, or chart data, with prompt plans and image generation.
1,659 · popularity - Rank 14View Agent SkillDirect
baoyu-danger-gemini-web
Generates images and text via a reverse-engineered Gemini Web API, supporting prompts, reference images, and multi-turn conversations.
27,566 · popularity - Rank 15View Agent SkillDirect
generate-reference-inspired-brand-worlds
Generates original brand campaign worlds from a visual reference, controlling similarity and avoiding protected signature elements, with originality-safe image prompts.
1,100 · popularity - Rank 16View Agent SkillDirect
brandkit
NotablePremium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.
297,293 · popularity - Rank 17View Agent SkillPossible
imagegen-frontend-web
Generates premium website design reference images, one per section, with composition variety and consistent palette for landing pages and marketing sites.
346,401 · popularity - Rank 18View Agent SkillPossible
imagegen-frontend-mobile
Generates premium mobile app screen and flow images for iOS/Android concepts, with phone mockup framing and controlled palettes.
340,357 · popularity - Rank 19View Agent SkillPossible
photo-abstract-editorial
Creates a vertical editorial diptych pairing an uploaded photo with a photo-derived abstract memory panel and poetic title.
719 · popularity - Rank 20View Agent SkillPossible
book-cover-design
Creates genre-appropriate book covers with AI image generation, covering genre conventions, typography, sizing, and thumbnail testing.
- Rank 21View Agent SkillPossible
app-store-screenshots
Creates App Store and Google Play screenshots and preview videos with platform specs, device mockups, and gallery ordering.
- Rank 22View Agent SkillPossible
prompt-master
Generates optimized prompts for AI tools including image and video AI, routing by target tool and extracting intent.
3,300 · popularity - Rank 23View Agent SkillPossible
hatch-pet
OfficialCreate, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker Codex pet workflow, a non-pixel custom pet style, a prospect or company mascot pet, or a full 8x9 animated pet atlas with transparent unused cells, QA contact sheets, and pet.json packaging. This skill composes the installed $imagegen system skill for visual generation and uses bundled scripts for deterministic spritesheet assembly.
Needs (stated): Credentials
- Rank 24View Agent SkillPossible
codex-pet
Builds Codex-compatible pet spritesheets from a reference image using GPT Image 2 edit and ImageMagick assembly.
Frequently asked questions
- What is the difference between text to image and editing and inpainting skills?
- Text to image skills create a new image from a prompt, while editing and inpainting skills modify an existing one, filling or replacing regions. In practice, editing often matters more than generation, since most work continues from an image you already have.
- Why do model and style control skills appear separately from generation skills?
- Model skills determine which image model an agent calls, and style control skills govern the look of the output. They are listed separately because the same generation workflow can be paired with different models and style controls.
- How is the ranked list ordered?
- The list is ranked by observed search demand, with direct matches to the topic placed first and a cap on any single publisher. Work down it until a skill covers the sub-topic you need.
- When should I reach for upscale and restore skills?
- After generation or editing, when the asset needs more resolution or repair. They sit at the end of the prompt, model, style control, edit, and upscale sequence.
How to install an Agent Skill
Start with the first skill on this page. Claude Code reads a SKILL.md once it is in the skills directory:
- Claude Code — copy the SKILL.md for imagegen into ~/.claude/skills/imagegen/ for yourself, or .claude/skills/imagegen/ to share it with a project.
- From the registry — run npx skills add openai/skills@imagegen.
- Or download imagegen from its source and place that SKILL.md in the directory above.
How to choose Check the source and the skill’s own instructions before you install. Official and Notable describe where a skill comes from.
For agents To find skills for a job, install find-skills-for-the-job. It includes this catalog’s topics. npx skills add geekfoxcharlie/find-skills-for-the-job