メニュー
Generate images from text with RubyLLM. Use this skill for creating images with DALL-E 3, GPT Image 1, Imagen, editing existing images, and working with masks for constrained editing.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Enforces idiomatic Ruby 4.0 code generation. This skill should be used whenever writing, reviewing, or refactoring Ruby code in a Ruby 4.0+ project. It ensures modern idioms (hash shorthand, `it` block param, endless methods, Data.define, pattern matching) are used by default and prevents generation of removed APIs (RJIT, pipe-based open, ObjectSpace._id2ref, old Ractor API, SortedSet, full CGI) and pre-4.0 patterns that have cleaner modern equivalents.
Use the bttf CLI for datetime arithmetic, formatting, timezone conversion, and duration calculation. Reach for this instead of doing date math mentally — LLMs are unreliable for datetime computation, especially across DST boundaries and leap years.
Apply SOLID as design judgment for Ruby, not as a mechanical rulebook. Use this skill when deciding WHETHER a SOLID refactor is warranted, when a class "feels wrong" but you're not sure splitting helps, when reviewing code for over-application (anemic models, service-object sludge, concern drawers, over-injection), or when reasoning about how Ruby's open classes, duck typing, and protocols change what each principle actually buys you. Complements the solid-principles skill, which covers detection heuristics and refactoring mechanics.
Convert speech to text with RubyLLM. Use this skill for transcribing meetings, podcasts, lectures, interviews with support for speaker diarization, timestamps, and multiple languages.
ActiveSupport::Notifications instrumentation for RubyLLM. Use this skill when building custom monitoring, logging, or analytics for RubyLLM usage. Publishes events for chat completions, tools, embeddings, images, moderation, and transcription.
One beautiful Ruby API for GPT, Claude, Gemini, and more. Use this skill when building AI-powered applications with RubyLLM - chatbots, AI agents, RAG applications, content generators, vision/audio analysis, embeddings, image generation, and Rails integration. Supports 15+ providers with a unified interface. v1.16 adds concurrent tool execution (threads or fibers), built-in instrumentation, and per-provider API base URL overrides.
| name | rubyllm-image-generation |
| description | Generate images from text with RubyLLM. Use this skill for creating images with DALL-E 3, GPT Image 1, Imagen, editing existing images, and working with masks for constrained editing. |
Create images from text descriptions using AI models like DALL-E 3 and Imagen.
# Generate image
image = RubyLLM.paint("A photorealistic red panda coding Ruby")
# Access result
if image.url
puts "URL: #{image.url}"
image.save("red_panda.png") # Save locally
end
if image.base64?
puts "MIME: #{image.mime_type}"
File.write("image.png", Base64.decode64(image.data))
end
# Revised prompt (some models optimize your prompt)
puts image.revised_prompt if image.revised_prompt
| Model | Provider | Size | Price/Image |
|---|---|---|---|
| dall-e-3 | OpenAI | 1024x1024 | $0.040 |
| dall-e-3 | OpenAI | 1024x1792 | $0.080 |
| gpt-image-1 | OpenAI | Various | Supports editing |
| imagen-3 | Various | Base64 output |
# DALL-E 3
RubyLLM.paint("Sunset", model: 'dall-e-3')
# GPT Image 1 (supports editing)
RubyLLM.paint("Edit logo", model: 'gpt-image-1', with: 'logo.png')
Edit existing images:
# Basic editing
image = RubyLLM.paint(
"Turn the logo green",
model: 'gpt-image-1',
with: 'logo.png'
)
# Edit with mask (constrain which parts change)
image = RubyLLM.paint(
"Change background to blue",
model: 'gpt-image-1',
with: 'photo.jpg',
mask: 'mask.png' # White areas get edited
)
# Provider-specific params
chat = RubyLLM.chat.with_params(
size: '1024x1024',
quality: 'hd',
style: 'vivid'
)
image = RubyLLM.paint("Sunset", **chat.params)
class GeneratedImage < ApplicationRecord
has_one_attached :file
end
image = RubyLLM.paint("Sunset")
record = GeneratedImage.create!
if image.base64?
record.file.attach(
io: StringIO.open(Base64.decode64(image.data)),
filename: "sunset.png",
content_type: image.mime_type
)
elsif image.url
# Download and attach
response = Faraday.get(image.url)
record.file.attach(
io: StringIO.new(response.body),
filename: "sunset.png",
content_type: response.headers['content-type']
)
end
# Vague
RubyLLM.paint("A dog")
# Specific
RubyLLM.paint("A golden retriever puppy sitting in a sunny meadow, photorealistic, warm lighting")
# Artistic styles
RubyLLM.paint("City skyline, watercolor style, soft pastels")
RubyLLM.paint("Portrait, oil painting, renaissance style")
RubyLLM.paint("Abstract composition, cubist, bold colors")
# Photography styles
RubyLLM.paint("Product photo, studio lighting, white background")
RubyLLM.paint("Landscape, golden hour, dramatic clouds")