Image Gen
Generate images from text prompts through OpenAI (gpt-image-2.5), Google Gemini (gemini-3-pro-image), Higgsfield, Black Forest Labs FLUX, or any OpenAI-compatible endpoint such as xAI Grok or Recraft. Use when the user asks to generate, create, render, or make an image, hero image, illustration, logo concept, OG image, poster, thumbnail, or social card, when a project has placeholder images to replace, or when the user names an image model or asks which image providers are available.
Install
npx skills add behzadsp/claude-code-image-gen --skill image-gengit clone --depth 1 https://github.com/behzadsp/claude-code-image-gen.git /tmp/claude-code-image-gen
mkdir -p ~/.claude/skills
cp -r /tmp/claude-code-image-gen/. ~/.claude/skills/image-genPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Image Generation
One CLI over every configured image provider. Picks the first provider whose
credentials exist, saves a PNG, prints JSON.
## Quick start
If `imagegen` is on PATH, use it from anywhere. Otherwise run `scripts/generate.py`
from this skill's base directory, which Claude Code prints when the skill loads.
```bash
imagegen \
--prompt "Minimalist 3D illustration of floating geometric shapes, deep purple to electric blue gradient, soft glow, website header" \
--aspect 16:9 \
--out ./generated-images/hero.png
```
Output:
```json
{"success": true, "filePath": "/abs/path/hero.png", "provider": "openai", "model": "gpt-image-2.5-sunburst", "bytes": 1217131}
```
Errors go to stderr as `{"success": false, "error": "..."}` with exit code 1.
## Instructions
1. **Craft the prompt before calling.** Use `[Style] [Subject] [Composition] [Atmosphere]`.
Name the palette when the image has to match an existing design. Vague prompts
("make it look good") waste a paid call.
2. **Pick the aspect ratio from where the image will be used**, not by default:
| Ratio | Use for |
|-------|---------|
| `16:9` | Hero images, headers, slides, OG images |
| `1:1` | Avatars, thumbnails, social tiles |
| `9:16` | Mobile stories, vertical banners |
| `4:3` / `3:2` | Blog body images, photo-style content |
3. **Let the provider default unless there is a reason.** Omit `--provider` and theDetails
- Skill name
image-gen- Repository
- behzadsp/claude-code-image-gen
- License
- MIT
- Repo updated
- 14 September 2026
FAQ
What does the Image Gen skill do?
Generate images from text prompts through OpenAI (gpt-image-2.5), Google Gemini (gemini-3-pro-image), Higgsfield, Black Forest Labs FLUX, or any OpenAI-compatible endpoint such as xAI Grok or Recraft. Use when the user asks to generate, create, render, or make an image, hero image, illustration, logo concept, OG image, poster, thumbnail, or social card, when a project has placeholder images to replace, or when the user names an image model or asks which image providers are available.
How do I install the Image Gen skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add behzadsp/claude-code-image-gen --skill image-gen. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Image Gen popular?
It lives in behzadsp/claude-code-image-gen, which has 5 GitHub stars and 0 forks.
Related skills
Image Studio
5ai-agents-for-agencies-coaches/image-studio
Render high-quality static images (ad creatives, posters, social posts, OG images, blog headers) by writing modern HTML/CSS and screenshotting with headless Chromium. Use whenever the user asks for a Canva-style static graphic, ad image, social post, carousel slide, OG image, hero image, or marketing poster — anything that isn't AI-generated photography. Output rivals Canva because the browser renders the design with full CSS, Tailwind, Google Fonts, gradients, blend modes, SVG, and effects. Triggers: "create an ad image", "make a social post", "design a poster", "OG image", "hero image", "sta
Hyper3d Documentary
5xiaohuailabs/hyper3d-documentary
用 Hyper3D（Rodin Gen-2.5）把一个科普题材做成可分享的单文件网页 3D 纪录片：需求问答 → 写脚本 → 生参考图 → 生成 3D 模型 → 模型库审核 → 动画成片，外加一个项目总览管理页。
Launch Video Maker
5SigmaMatrix-AI/launch-video-maker
Use when the user asks for an autonomous product launch video or promo from product materials, a website, screenshots, recordings, or source code, or to continue, edit, or review such a film project.
Grok Video Editing
5AlizayAyesha/grok-video-editing-skill
Record a product demo on a Linux desktop, cut it into feature clips, and render an on-brand 1080p motion-graphics promo video entirely with code (ffmpeg + HTML Canvas + headless Chromium via Playwright + a procedural audio mix). Use when asked to make a product demo, launch video, or social promo themed to a website's colors and fonts.
Melies
5melies-co/melies-cli
AI filmmaking CLI with 148 built-in actors, 98 visual styles, and smart model selection. Generate images, videos, posters, and thumbnails without prompt engineering. Text-to-image, text-to-video, image-to-video pipeline, upscaling, background removal. Use --actor, --art-style, --lighting, --mood flags instead of writing prompts.
Drawing Review Cn
5Wonggeff/drawing-review-cn
中国建筑工程施工图图纸会审（图纸自审）专家技能。用于对一整套施工图（建筑/结构/给排水/电气/ 暖通/智能化/室内装修/景观园林/海绵/基坑支护/亮化等专业）开展系统性自审，产出可直接上会签认的 图纸会审问题清单与记录表。 适用场景： (1) 用户说“帮我做图纸会审”“图纸自审”“审图”“挑图纸问题”“出问题清单”“会审记录” (2) 一次性给出一个装满施工图的文件夹（PDF/DWG），要求找出各专业图纸问题 (3) 要求列出“哪个专业、哪张图纸、哪个部位、什么问题、怎么解决”并做跨专业比较 (4) 需要生成图纸会审记录表（Word/Excel，含设计回复/处理结果/闭环状态列） (5) 需要核查图纸集完整性：图纸目录、图号体系、版本冲突、签章有效性 (6) 仿古建筑 / 木结构 / 文旅 / 文物遗址类项目的专项会审
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.