60 lines
2.8 KiB
Markdown
60 lines
2.8 KiB
Markdown
---
|
|
description: Generate a professional Gemini Flash Image prompt from free-form description
|
|
argument-hint: <description>
|
|
allowed-tools: [Read, Write, Glob, Grep, Bash]
|
|
---
|
|
|
|
Create a professional image generation prompt based on the user description: "$ARGUMENTS"
|
|
|
|
Follow these steps:
|
|
|
|
1. **Context Discovery**: Automatically search for and gather relevant context from the project files:
|
|
- Search for any mentioned characters in `/heroes/` directory
|
|
- Look for locations in `/locations/` or `/cities/` directories
|
|
- Find world information in `/worlds/` directory
|
|
- Identify items in `/items/` directory
|
|
- Check for creatures in `/creatures/` directory
|
|
- Find applicable settings in `/settings/` directory
|
|
|
|
2. **Entity Analysis**: Parse the description to identify:
|
|
- Characters mentioned (explicit or implied)
|
|
- Locations referenced
|
|
- Items involved
|
|
- Creatures present
|
|
- Scene context and actions
|
|
- Appropriate style settings to apply
|
|
|
|
3. **Prompt Generation**: Create a professional prompt following the guidelines in `@docs/prompting-guide.md`:
|
|
- Use narrative descriptions instead of keyword lists
|
|
- Apply appropriate template from the prompting guide based on content type
|
|
- Include world-specific style elements
|
|
- Reference character unique identifying features
|
|
- Integrate linked items and relationships naturally
|
|
- Specify lighting and atmosphere
|
|
- Include technical quality descriptors
|
|
- Maintain visual continuity with established universe
|
|
|
|
4. **Settings Integration**: Automatically apply appropriate settings based on context:
|
|
- Character clothing based on status, world, and scenario
|
|
- Transportation methods suitable for world and character
|
|
- Environmental styles matching location and world
|
|
- Weapon styles appropriate for character and scenario
|
|
- Magical effects suitable for character abilities
|
|
|
|
5. **Reference Images**: If the prompt requires reference images, include their file paths in markdown format.
|
|
|
|
6. **Validation**: Check the generated prompt against best practices:
|
|
- Ensure narrative structure (not keyword lists)
|
|
- Include lighting and atmosphere descriptions
|
|
- Specify technical quality requirements
|
|
- Maintain consistency with established character/location features
|
|
- Follow appropriate template from prompting guide
|
|
|
|
7. **Output**: Save the final prompt as a markdown file in `/prepared_prompts/` directory with:
|
|
- Timestamp and description in filename
|
|
- Complete prompt ready for Gemini 2.5 Flash Image
|
|
- Applied settings documentation
|
|
- Reference image paths if needed
|
|
- Validation results and suggestions
|
|
|
|
**Important**: The output must be in English regardless of input language. Follow the exact templates and best practices from `docs/prompting-guide.md` and respect the project framework defined in `CLAUDE.md`. |