Image Generation skills for Claude Code and Codex
These skills let an agent turn a text prompt or a reference picture into a finished image. They wrap image models such as GPT Image, Gemini image models, FLUX, Bria and Venice, and a few teach prompt structure so the first render lands closer to the brief.
Highest-scoring image generation skills in the October 22, 2026 snapshot: seo-image-gen from AgriciDaniel/claude-seo (88/100), create-image-fal from gooseworks-ai/goose-skills (86/100) and vgl from Bria-AI/bria-skill (82/100). Scores come from the Suede Skill Check.
- 16 listed skills
- 9 repositories
- 9 with full pages
4 from official publishers. 10 bundle scripts. 9 connect to an outside service. Listed in Video, Image, Audio and Creative (16).
All 16 image generation skills
No matching skills. Try fewer words or clear your search.
| Skill | Repository | What it does |
|---|---|---|
| bria-ai 80/100 · B | Bria-AI/bria-skill | Generates images from text prompts, edits them with natural language, removes backgrounds for transparent PNGs, and creates product lifestyle shots through the Bria.ai API. |
| create-image-fal 86/100 · B | gooseworks-ai/goose-skills | Generates or edits images with FAL image models such as nano-banana edit, gpt-image and flux, billed through the fal-proxy. |
| create-image-gpt-image-fal 83/100 · B | gooseworks-ai/goose-skills | Generates a single photoreal or designed image with OpenAI gpt-image through fal.ai, using the edit variant when a reference image is provided. |
| nano-banana-pro 70/100 · C | swarmclawai/swarmclaw | Generates or edits images with Gemini 3 Pro Image, supporting text-to-image generation, single-image editing, and composition of up to 14 images. |
| openai-image-gen 73/100 · C | swarmclawai/swarmclaw | Generates images through the OpenAI Images API with GPT Image, DALL-E 3, or DALL-E 2, supporting batch generation and HTML gallery output. |
| prompt-images 72/100 · C | replicate/skills | Teaches prompting techniques for AI image generation and editing models on Replicate, for writing prompts or building image generation features. |
| remix-graphic-ad-from-reference 83/100 · B | gooseworks-ai/goose-skills | Recreates a static graphic ad from a reference image with a new product and copy, keeping its layout, via GPT Image 2. |
| seo-image-gen 88/100 · B | AgriciDaniel/claude-seo | Generates AI images for SEO assets such as social preview images, blog hero images, product photos, and infographics, using Gemini through the nanobanana server. |
| vgl 82/100 · B | Bria-AI/bria-skill | Controls AI image generation by writing structured VGL JSON that sets object placement, lighting direction, camera angle, lens focal length, composition, and color scheme. |
| generate-image 74/100 · C | github/awesome-copilot | Generate images using AI. Use when asked to generate, create, or make images, textures, icons, sprites, artwork, visual assets, or mockups. Supports… |
| generate-image 93/100 · A | K-Dense-AI/claude-scientific-skills | Generates or edits images with AI models through the OpenRouter Image API (Gemini, Seedream, Recraft, GPT-Image, Riverflow). Use for photos… |
| imagen 80/100 · B | sanjay3290/ai-skills | Generate images using Google Gemini's image generation capabilities. Use this skill when the user needs to create, generate, or produce images for… |
| infographics 89/100 · B | K-Dense-AI/claude-scientific-skills | Creates and reviews infographics with Nano Banana 2 via OpenRouter. Use for statistical summaries, timelines, comparisons, processes, and visual… |
| nano-banana-pro-openrouter 76/100 · C | github/awesome-copilot | Generate or edit images via OpenRouter with the Gemini 3 Pro Image model. Use for prompt-only image generation, image edits, and multi-image… |
| scientific-schematics 81/100 · B | K-Dense-AI/claude-scientific-skills | Generates scientific diagram drafts using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.7 Flash for quality review. Refines when… |
| venice-image-generate 70/100 · C | veniceai/skills | Generate images with Venice. Covers POST /image/generate (Venice-native), POST /images/generations (OpenAI-compatible), GET /image/styles (style… |
How to choose image generation skills
Pick by provider first. Most of these skills call one hosted API (OpenAI, Google Gemini, OpenRouter, fal.ai, Bria, Replicate or Venice) and expect that provider's key in an environment variable, so the right skill is usually the one for the account you already pay for.
If you switch models often, prefer a skill that routes through OpenRouter or fal.ai, since one key reaches several image models. If you need precise layout, lighting or camera control, look at the structured prompt skills such as Bria VGL and the Replicate prompting guide.
Check what the skill does with output. Some save files locally, some return URLs, and some build an HTML gallery. The Before you install panel lists bundled scripts and the variables their code reads.
Related topics
Image Editing 11Diagrams and Infographics 19Product Photography 5Social and Marketing Images 8Background Removal 5
Find your next useful skill
Explore Rising Skills with quality scores and source reports, or search from inside your agent.
Get Rising Skills by email · Read Rising Skills · Install the finder · State of Agent Skills