Agent skill · Design & Presentation

image-generation

Generate or edit images with Gemini Pro. Use when user says "generate an image", "create a picture", "make me a logo", "edit this image", "remove the background", "change the style", "combine these images", "add text to image", "style transfer", "make a sticker", "product mockup", or any image creation/manipulation request. Handles t2i (text-to-image), i2i (image-to-image editing), and multi-reference composition.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill image-generation-gupsammy-claude-setup-2 --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 9 KB
Bundled scripts: none
Path: skills/ai-llm/image-generation-gupsammy-claude-setup-2/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Image Generation Generate and edit images using Google's Gemini Pro Image API. Requires `GEMINI_API_KEY` environment variable. ## Default Output & Logging When the user doesn't specify a location, save images to: ``` /Users/samarthgupta/Documents/generated images/ ``` Every generated image gets a companion `.md` file with the prompt used (e.g., `logo.png` → `logo.md`). When gathering parameters (aspect ratio, resolution), offer the option to specify a custom output location. --- ## Core Prompting Principle **Describe scenes narratively, don't list keywords.** Gemini has deep language understanding—write prompts like prose, not tags. ``` ❌ "cat, wizard hat, magical, fantasy, 4k, detailed" ✓ "A fluffy orange tabby sits regally on a velvet cushion, wearing an ornate purple wizard hat embroidered with silver stars. Soft candlelight illuminates the scene from the left. The mood is whimsical yet dignified." ``` ### The Formula ``` [Subject + Adjectives] doing [Action] in [Location/Context]. [Composition/Camera]. [Lighting/Atmosphere]. [Style/Media]. [Constraint]. ``` Not every prompt needs every element—match detail to intent. ### Prescriptive vs Open Prompting **Prescriptive** (user h

What's inside
Steps it walks through
  1. Default Output & Logging
  2. Core Prompting Principle
  3. The Formula
  4. Prescriptive vs Open Prompting
  5. Capability Patterns
  6. Photorealistic Scenes
  7. Product Photography
  8. Logos & Text
  9. Stylized Illustration
  10. Editing Images
  11. Multi-Image Composition
  12. Character Consistency
  13. Invoking Aesthetics Through Naming
  14. Configuration
Ships with 1 file
  • metadata.json
Commands it runs
Text-to-image (t2i)
uv run {baseDir}/scripts/generate.py --prompt "A serene mountain lake at dawn" --output landscape.png
Image-to-image editing (i2i)
uv run {baseDir}/scripts/generate.py --prompt "Make it sunset colors" --input photo.png --output edited.png
Multi-reference composition (up to 14 images)
With options
uv run {baseDir}/scripts/generate.py --prompt "Logo for 'Acme Corp'" --output logo.png --aspect 1:1 --resolution 2K
With Google Search grounding
uv run {baseDir}/scripts/generate.py --prompt "Current weather in Tokyo visualized" --output weather.png --grounding
Batch generation (up to 4 images, 2 parallel requests)
More from claude-skill-registry
All skills →
About this skill
What does the image-generation skill do?

Generate or edit images with Gemini Pro. Use when user says "generate an image", "create a picture", "make me a logo", "edit this image", "remove the background", "change the style", "combine these images", "add text to image", "style transfer", "make a sticker", "product mockup", or any image creation/manipulation request. Handles t2i (text-to-image), i2i (image-to-image editing), and multi-reference composition.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill image-generation-gupsammy-claude-setup-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going