Generate and edit images via Gemini 2.5 Flash Image from text prompts.
npx skills add https://github.com/boxp/dotfiles --skill generate-image-boxp
Please help me install this Agent Skill. Skill: generate-image Source: https://github.com/boxp/dotfiles/tree/main/.claude/skills/generate-image Command: npx skills add https://github.com/boxp/dotfiles --skill generate-image-boxp
This skill enables rapid generation and editing of images using Gemini 2.5 Flash Image from natural language prompts or reference images, reducing manual design work.
Use the generate-image skill to create an image from a prompt, for example: bb /home/boxp/.claude/skills/generate-image/generate-image.bb "夕焼けの海辺の風景" -a 16:9 -s 4K -m gemini-3-pro-image-preview -o banner.png You can also base an image on an existing file: bb /home/boxp/.claude/skills/generate-image/generate-image.bb -i ref.png "この画像をアニメ風にして"
High-intent search queries and answers about installing and using this skill.
To generate images from text prompts using Gemini 2.5, you provide a natural language description and configure the model, size, and aspect ratio flags to output a desired image file for banners or illustrations.
Yes, you can edit existing images by passing an input file with a reference image and providing a text prompt to apply transformations or styles, such as converting a photo into an anime-style illustration.
Yes, you must provide a valid GEMINI_API_KEY in your environment to access the Gemini API, as the skill relies on this key to authenticate and process your image generation and editing requests.
You can configure image generation by setting specific size and aspect ratio parameters, such as 4K for size and 16:9 for aspect ratio, tailoring the output for creative tasks like banners or avatars.
The best way to create a 16:9 banner from a text prompt is to use the generation command, specify your descriptive prompt, and apply the aspect ratio flag to format the output exactly as needed.
Limitations of using Gemini 2.5 Flash Image for image editing include relying entirely on the accuracy of the Gemini API for transformations and requiring an active API key, which may restrict usage without proper configuration.
sammyjoyceGenerate and edit images via the Gemini API with text prompts.
daymadeConvert PDFs, Word, PowerPoint, and Confluence exports to Markdown with Windows/WSL path handling.
plossonGenerates AI-powered logos/icons with iterative refinement and SVG vectorization.
aayushsoamGenerate and edit images with Gemini 3 Pro via a scripted CLI workflow.
