This skill should be used when the user asks to "generate an image", "create an image", "edit an image", "modify an image", "make a picture", "create an icon", "design a logo", "make a mockup", "create a banner", "generate a thumbnail", "make an illustration", "create a transparent PNG", or discusses image generation, DALL-E, GPT-Image, visual assets, or image editing using the imagegen MCP tools.
From imagegennpx claudepluginhub thorrak/imagegen-plugin --plugin imagegenThis skill uses the workspace's default tool permissions.
examples/image-editing-example.mdexamples/text-to-image-example.mdreferences/parameters.mdGuides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Details PluginEval's skill quality evaluation: 3 layers (static, LLM judge), 10 dimensions, rubrics, formulas, anti-patterns, badges. Use to interpret scores, improve triggering, calibrate thresholds.
Use the two MCP tools provided by the imagegen server:
Generate new images from text prompts.
Required parameters:
text: The generation promptoutputPath: Absolute path where the image file should be savedOptional parameters:
model: gpt-image-1 (default), dall-e-2, or dall-e-3size: Dimensions (default 1024x1024)quality: auto (default), standard, or hdoutput_format: png (default), jpeg, or webpstyle: vivid (default) or natural (DALL-E 3 only)background: auto (default), transparent, or opaquen: Number of images (default 1)moderation: low (default) or autooutput_compression: 0-100 (default 100)Edit existing images using text instructions.
Required parameters:
images: Array of absolute file paths to source imagesprompt: Description of the desired editsoutputPath: Absolute path where the edited image should be savedOptional parameters:
mask: Path to a PNG mask (transparent areas indicate where to edit)model: gpt-image-1 (default) or dall-e-2size: Dimensions (default 1024x1024)quality: auto (default) or standardoutput_format: png (default), jpeg, or webpn: Number of variations (default 1)output_compression: 0-100 (default 100)Always save generated images to a generated-images/ directory in the current project:
<project-root>/generated-images/<descriptive-filename>.<format>generated-images/ directory with mkdir -p before calling the toolhero-banner.png, app-icon-512.png)icon-1.png, icon-2.pngAfter generation, confirm the file path to the user so they can find the image.
Choose the model based on the use case:
gpt-image-1 (recommended default):
dall-e-3:
style parameter (vivid/natural) and hd qualitydall-e-2:
| Model | Allowed Sizes |
|---|---|
| gpt-image-1 | 1024x1024, 1536x1024, 1024x1536, auto |
| dall-e-3 | 1024x1024, 1792x1024, 1024x1792 |
| dall-e-2 | 256x256, 512x512, 1024x1024 |
Always verify the requested size is valid for the chosen model. If the user requests a size not supported by their chosen model, suggest the closest available size.
When crafting prompts for image generation:
background: "transparent" and use PNG or WebP formatTo generate images with transparent backgrounds:
background to "transparent"output_format of "png" or "webp" (JPEG does not support transparency)gpt-image-1When editing images with image-to-image:
promptgpt-image-1 and dall-e-2 support editingOPENAI_API_KEY environment variable is setFor quick access, users can use the /generate-image and /edit-image slash commands instead of describing the task conversationally.
For edge cases involving parameter validation or uncommon parameter combinations, consult the full parameter reference at ${CLAUDE_PLUGIN_ROOT}/skills/image-generation/references/parameters.md.
For complete tool call examples, see ${CLAUDE_PLUGIN_ROOT}/skills/image-generation/examples/.