Translate natural language image descriptions into detailed, structured DALL-E prompts with subject, style, composition, lighting, and mood specifications.
Image prompt crafting skill.
Use this skill when you need to construct a prompt for generate_image from a user's description. Always activate this before calling generate_image.
Parse the user's description for:
If any of these are missing and matter for the result, ask the user.
Recall style preferences and brand guidelines:
recall("style_preference")
recall("brand_guideline")
Apply any saved preferences unless the user's current request explicitly overrides them.
Construct the prompt using this structure:
[Subject description], [style], [composition], [lighting], [mood], [details]
Rules for effective prompts:
Choose the right parameters for the use case:
| Use case | Size | Style | Quality |
|---|---|---|---|
| Social media post | 1024x1024 | vivid | standard |
| Blog header | 1792x1024 | natural | hd |
| Phone wallpaper | 1024x1792 | vivid | hd |
| Logo / icon | 1024x1024 | natural | hd |
| Quick concept | 1024x1024 | natural | standard |
Show the user:
Wait for approval before generating.
After the user sees the result: