Generate and edit images with Gemini models via CLI scripts or inline code.
npx skills add https://github.com/nawwwal/dex --skill generate-image-nawwwal
Please help me install this Agent Skill. Skill: generate-image Source: https://github.com/nawwwal/dex/tree/main/plugins/tools/skills/generate-image Command: npx skills add https://github.com/nawwwal/dex --skill generate-image-nawwwal
This Skill enables rapid image creation and editing by providing both natural-language, inline-code workflows and deterministic CLI scripts that leverage Gemini image models, reducing context switching and setup time for design tasks.
Provide a prompt and any optional editing instructions to generate or modify an image, then save the resulting output to a file.
High-intent search queries and answers about installing and using this skill.
To generate and edit images via CLI, this Skill uses Gemini models with configurable prompts, aspect ratios, and output sizes. You provide a prompt and optional source images, then save the resulting output directly to disk for asset pipelines.
Yes, you can automate marketing visuals using deterministic CLI scripts. This Skill provides repeatable workflows for design assets and prototypes, reducing context switching by leveraging Gemini image models directly within your engineering pipelines.
Yes, the image generation tool supports flexible parameters including custom aspect ratios, output sizes, and modalities. You can configure these settings alongside your prompts to generate traceable outputs grounded via Google or image searches.
The best way to create product visuals is using the dual surfaces provided: natural-language inline code for interactive usage or script-based CLI for deterministic pipelines. Both leverage Gemini models to rapidly generate and modify images.
Yes, there are Gemini model options for higher quality image generation. The Skill defaults to the gemini-3.1-flash-image-preview model but provides an explicit path to gemini-3-pro-image-preview when you need higher quality outputs.
Image generation handles grounding by optionally integrating Google or image searches. This ensures the generated or edited images are accurate and traceable, enforcing configurable prompts and modalities for reliable design results.
tense-iGenerate or edit images from prompts using the Google Gemini API.
rezosndConvert files across CSV, JSON, YAML, XML, Markdown, and image formats.
pacphiStream outputs between sequential steps in multi-agent workflows.
jitenkr2030Edit and transform images via the z-ai-web-dev-sdk with base64 outputs.
