# Image Generation > Use when the user wants a new generated image, drawing, render, visual concept, or image prompt; do not use for describing or analyzing existing images. - Skill: `tomevault-io/image-generation-8` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/image-generation-8` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/image-generation-8/raw - Safety review: pending (external: skill-scanner PASS, skillspector PASS) - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: AI & ML - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/image-generation-8 --- Use this skill when the user's primary intent is to create a new image or visual concept. Do not use this skill when the user only asks to analyze, describe, compare, caption, or ask questions about an existing image. Workflow: - Convert the user's request into a clear image prompt. - Preserve concrete subject, style, composition, and constraints from the user. - Ask for missing details only when the request is impossible or unsafe without them. - If the user gives a broad idea, choose a coherent visual direction and proceed. - Do not trigger image generation for metaphorical words like "imagine" unless the user clearly wants an image. - Do not claim an image was generated unless the image generation handler succeeds. --- > Source: [Javis603/Discord-AIBot](https://github.com/Javis603/Discord-AIBot) — distributed by [TomeVault](https://tomevault.io).