Imagen
Generate UI mockups, icons, and illustrations via Google Gemini image APIs without leaving your agent workflow.
Overview
imagen is an agent skill most often used in Validate (also Build) that generates images with Google Gemini for mockups, icons, and illustrations.
Install
npx skills add https://github.com/nexu-io/open-design --skill imagenWhat is this skill?
- Google Gemini image-generation API for raster visuals
- Trigger phrases include gemini image, imagen, google image gen, illustration, and icon
- Open Design catalogue entry points to full upstream @sanjay3290/imagen bundle
- Suited for UI mockups, icons, illustrations, and general visual assets
- Upstream category: image-generation (mode: image)
- 5 frontmatter trigger phrases
- upstream category image-generation
Adoption & trust: 791 installs on skills.sh; 61.4k GitHub stars.
What problem does it solve?
You need believable visuals for a prototype or UI pass but lack time or budget for a full design pipeline.
Who is it for?
Solo builders validating UI direction or stocking early screens with icons and illustrations via API.
Skip if: Teams needing pixel-perfect brand systems, print-ready assets, or guaranteed rights metadata without reviewing upstream licensing yourself.
When should I use this skill?
User mentions gemini image, imagen, google image gen, illustration, or icon for visual asset work.
What do I get? / Deliverables
You get Gemini-generated mockups and asset images ready to drop into specs, landings, or frontend work after installing the upstream imagen bundle.
- Generated image files or URLs for mockups, icons, and illustrations
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Prototype and landing validation need visual artifacts fast; this skill is shelved in Validate where mockups and icons unblock scope decisions before heavy Build work. Prototype subphase is where solo builders swap placeholder art for believable UI mockups, app icons, and marketing illustrations.
Where it fits
Generate a three-screen SaaS mockup set before committing to a component library.
Produce hero illustration variants for an A/B landing test.
Create consistent toolbar icons for a React dashboard.
Draft social preview images that match your in-app UI tone.
How it compares
Use for API-driven raster generation instead of hand-prompting in a separate chat with no skill packaging.
Common Questions / FAQ
Who is imagen for?
Solo and indie builders using Claude Code, Cursor, or similar agents who want Gemini image generation wired into skill discovery for mockups and icons.
When should I use imagen?
During Validate when you need prototype mockups or landing visuals; during Build when you want icons and illustrations for frontend screens; whenever trigger phrases like gemini image or icon match your task.
Is imagen safe to install?
Treat it like any third-party skill: review the Security Audits panel on this Prism page and inspect the upstream imagen repo before adding API keys or running bundled scripts.
SKILL.md
READMESKILL.md - Imagen
# imagen > Curated from @sanjay3290. ## What it does Generate images using Google Gemini's image generation API for UI mockups, icons, illustrations, and visual assets. ## Source - Upstream: https://github.com/sanjay3290/imagen - Category: `image-generation` ## How to use This catalogue entry advertises the skill in Open Design so the agent discovers it during planning. To run the full upstream workflow with its original assets, scripts, and references, install the upstream bundle into your active agent's skills directory: ```bash # Inspect the upstream README for exact paths open https://github.com/sanjay3290/imagen ``` Then ask the agent to invoke this skill by name (`imagen`) or with one of the trigger phrases listed in this skill's frontmatter.