Generate and edit images from text prompts using Gemini.
npx skills add https://github.com/harperaa/bastionclaw --skill generate-image-harperaa
Please help me install this Agent Skill. Skill: generate-image Source: https://github.com/harperaa/bastionclaw/tree/main/container/skills/generate-image Command: npx skills add https://github.com/harperaa/bastionclaw --skill generate-image-harperaa
This skill streamlines the creation of visual assets by generating images from text prompts using Gemini, reducing manual design time and enabling rapid visuals for projects.
Provide a clear description of the image you want and the desired output path; the system will generate and save the image accordingly.
High-intent search queries and answers about installing and using this skill.
To generate architecture diagrams from text prompts, you provide a concise description and an output path to the skill, which then creates and saves the visual accordingly. It supports technical diagrams and branded graphics across software projects.
Yes, you can edit existing images by providing an input image along with an edit prompt. The skill supports optional aspect ratios to ensure the generated or updated visuals fit your specific layout requirements.
Yes, you need a GEMINI_API_KEY configured in your environment to generate images. The skill relies on Gemini's image model to process prompts and create technical visuals, blog headers, or branded graphics.
Automating visual design for software documentation is best handled by using prompt-driven image generation to rapidly create architecture diagrams and technical visuals, significantly reducing manual design time and enabling quick project iterations.
Yes, the image generation skill works in containerized environments and resolves script paths from multiple locations. This flexible deployment allows you to integrate automated visual asset creation into various development workflows.
Prompt-driven image generation fails without dotenv because the skill depends on it to load the required GEMINI_API_KEY from the environment. Without this dependency, the Gemini model cannot authenticate or process your image generation requests.
openaeonGenerate or edit PNG images from text prompts using Gemini 3 Pro Image API.
zircoteGenerate branded, accessible SVG graphics for blog content and diagrams.
DidierRLopesConvert Beehiiv newsletter posts into blog markdown files with front matter and images.
eachlabsGenerate images from text prompts using Flux, GPT Image, Gemini, and Imagen models.
