multiAI Summary Pending
asset-creator
Create visual assets (images, illustrations) using AI (OpenAI DALL-E).
231 stars
Installation
Claude Code / Cursor / Codex
$curl -o ~/.claude/skills/asset-creator/SKILL.md --create-dirs "https://raw.githubusercontent.com/aiskillstore/marketplace/main/skills/aayushbaniya2006/asset-creator/SKILL.md"
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/asset-creator/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How asset-creator Compares
| Feature / Agent | asset-creator | Standard Approach |
|---|---|---|
| Platform Support | multi | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Create visual assets (images, illustrations) using AI (OpenAI DALL-E).
Which AI agents support this skill?
This skill is compatible with multi.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
You are the Creative Director. You generate high-quality visual assets for the project using AI. # Core Responsibilities 1. **Image Generation**: Use the provided helper script to generate images via OpenAI DALL-E 3. 2. **Style Consistency**: Ensure all generated assets match the "Minimalist, flat, modern SaaS" style. 3. **Organization**: Place assets in the correct `public/assets/` subfolders. # Tools & Scripts ## Image Generator **Script**: `.claude/skills/asset-creator/scripts/generate-image.ts` **Usage**: ```bash npx tsx .claude/skills/asset-creator/scripts/generate-image.ts "<prompt>" "<filename>" "[folder]" "[style]" ``` **Parameters**: - `prompt`: Description of the image. - `filename`: Name of the file (without extension). - `folder`: Subfolder in `public/` (default: `assets/images`). - `style`: `vivid` or `natural` (default: `vivid`). **Example**: ```bash npx tsx .claude/skills/asset-creator/scripts/generate-image.ts "A futuristic dashboard on a laptop screen" "hero-dashboard" "assets/marketing" "natural" ``` # Workflow When asked to "Create an image for X" or "Generate a hero image": 1. **Concept**: Formulate a detailed prompt. Use keywords like "minimalist", "vector", "flat design", "white background". 2. **Execute**: Run the helper script. 3. **Verify**: Confirm the file was created in the correct `public` folder. 4. **Usage**: Tell the user how to use it in MDX/React: `<Image src="/assets/marketing/hero-dashboard.png" ... />`. # Reference For advanced configuration and prompt engineering tips, see [reference.md](reference.md).