Generate Image
Turn natural-language prompts into images for mockups, icons, hero art, and social visuals without leaving the agent chat.
Overview
generate-image is an agent skill most often used in Build (also Launch distribution and Grow content) that creates pictures from natural-language prompts via Flux Klein when users ask to generate, draw, or make an image.
Install
npx skills add https://github.com/nicolasagardoy/flux-klein-image-gen --skill skill.mdWhat is this skill?
- Fires on plain phrases like “generate an image of”, “draw me a”, and “create an image”
- Backed by Flux Klein image generation for quick illustration and concept art
- Useful for placeholders, mood boards, and ship-ready creative without a separate design tool session
- Agent skill package—invoke from Claude Code, Cursor, or Codex when the user asks for a picture
- Output is generated image assets from a text description, not a static template file
What problem does it solve?
You know what scene or asset you want but lack time, a designer, or a separate image tool in the middle of a coding session.
Who is it for?
Solo builders who want on-demand illustrations, hero images, or quick visual concepts triggered by casual chat phrasing.
Skip if: Teams that need pixel-perfect brand kits, reproducible vector icons, or strict commercial licensing workflows without reviewing model terms.
When should I use this skill?
User asks to generate, create, draw, or make an image or picture—e.g. “generate an image of”, “make a picture of”, “create an image”, “draw me a”.
What do I get? / Deliverables
You get a generated image from your description so you can drop it into mockups, docs, or marketing drafts immediately.
- Generated raster image from the user’s prompt
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Solo builders most often pull generated images while shaping product UI and marketing surfaces during the build phase. Frontend and visual asset work is the canonical shelf because triggers fire when you need pictures for interfaces, landings, and feature demos.
Where it fits
Generate a rough app screenshot mood image before committing to a full UI kit.
Create placeholder hero art for a Next.js landing section while coding layout.
Produce a social post illustration from a one-line campaign brief.
Illustrate a changelog or blog header without opening a stock photo site.
How it compares
Use this skill package for chat-triggered raster generation—not an MCP design server or a manual Figma export loop.
Common Questions / FAQ
Who is generate-image for?
Indie developers and solo founders using AI coding agents who need images inline while building UIs, landing pages, or content—not full-time designers running a DAM.
When should I use generate-image?
Use it in Build when you need UI or marketing visuals; in Validate when you want prototype mood imagery; at Launch for social or store creatives; and in Grow when you need blog or newsletter art from a short prompt.
Is generate-image safe to install?
Review the Security Audits panel on this Prism page for upstream repo signals; image skills typically call external APIs and may send prompts off-device, so confirm keys, billing, and content policy before production use.
SKILL.md
READMESKILL.md - Generate Image
Use when user asks to generate, create, draw, or make an image or picture. Triggers on phrases like "generate an image of", "make a picture of", "create an image", "draw me a". # generate-image { "name": "generate-image", "description": "Use when user asks to generate, create, draw, or make an image or picture. Triggers on phrases like \"generate an image of\", \"make a picture of\", \"create an image\", \"draw me a\"." }