apps/backend/src/swarm/skills/builtins/image-generation/SKILL.md
Generate images using Google Gemini (gemini-3-pro-image-preview). Requires GEMINI_API_KEY.
npx skillsauth add a-mart/forge image-generationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Generate images using Google Gemini (gemini-3-pro-image-preview).
Run from this skill directory:
node ./generate.js \
--prompt "a cute robot bee in a garden" \
--output "/path/to/output.png"
--prompt (required): text description of the image to generate--output (required): output file path (extension auto-detected when omitted)--aspect-ratio (optional): aspect ratio like 16:9, 1:1, 4:3--size (optional): image size, default 1KThe script prints JSON:
{ "ok": true, "file": "/path/to/output.png", "mimeType": "image/png" }{ "ok": false, "error": "..." }data-ai
Use when substantial manager-led work needs durable visible progress, worker evidence links, review gates, blocker tracking, or handoff across pauses, stops, compaction, restart, or model changes. Do not use for quick answers or routine one-step work.
tools
Author repo-root .forge project resources, including skills, specialists, reference docs, Project Agent definitions, Forge extensions, and Pi extensions/settings.
tools
Use when creating, refining, or validating reusable global, project, or repository skills, including trigger wording, templates, helper scripts, and validation checks.
tools
Create, update, list, and delete global slash commands.