A sophisticated AI pipeline that reimagines your personal photos as surrealist masterpieces using a multi-model workflow and deep macOS integration.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install photo-alchemy
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install photo-alchemy using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is photo-alchemy?
photo-alchemy is a powerful tool designed to breathe new life into your digital photography. By leveraging a dual-model pipeline, it first utilizes Claude to interpret your image and craft a unique surrealist narrative and detailed prompt. Subsequently, Google Gemini takes this creative spark to generate a brand-new high-fidelity image in one of over 35 distinct visual styles.
This skill is particularly optimized for the Apple ecosystem, featuring seamless integration with macOS Photos. It allows users to pull from existing albums, apply character mappings for personalized storytelling, and even automate the creation of a living art gallery for Apple TV. As a standout entry in the Openclaw Skills library, it bridges the gap between raw AI generation and practical home automation.
photo-alchemy Use Cases
- Creating a dynamic, ever-changing Apple TV screensaver from personal photo libraries.
- Generating unique, stylized social media content from standard mobile uploads.
- Automating creative art production for digital signage or home displays.
- Experimenting with 35+ artistic styles like Vaporwave, Ukiyo-e, and Neon Noir on personal portraits.
How photo-alchemy Works
- The tool resizes the input image to a maximum of 1024px to ensure optimal processing speed while maintaining the original aspect ratio.
- The resized image is sent to Claude, which analyzes the visual content to write a surrealist story and a structured image prompt.
- A visual style is selected, either randomly from the built-in library or via user specification.
- The story, style, and original image context are passed to Gemini to generate the final reimagined artwork.
- Run metadata, including timing and prompts, is logged to a local SQLite database for history tracking.
- The final output is optionally exported to a designated macOS Photos album or local directory.
photo-alchemy Setup
Install the tool instantly using uvx without a full environment setup:
uvx imagemine path/to/photo.jpg
For a permanent installation on your system, use the following command:
curl -LsSf uvx.sh/imagemine/install.sh | sh
After installation, configure your Anthropic and Google Gemini API keys:
imagemine --config
photo-alchemy Data Schema & Taxonomy
The skill manages its operations through a local SQLite database located at ~/.imagemine.db. This database tracks the following attributes for every generation:
| Data Point | Description |
|---|---|
| Input Path | The source file location or Photos ID |
| Generated Story | The unique narrative created by Claude |
| Style Used | The specific artistic filter applied to the run |
| Timing Data | Millisecond-level performance metrics for each pipeline step |
| Output Path | The location of the final generated AI art |
photo-alchemy Advanced Features
- Launchd Integration: Automate the tool to run every N minutes for continuous art generation.
- Character Mapping: Rename recognized faces (e.g., 'John' to 'Captain America') before they are processed by the AI.
- Interactive Style Mixing: Blend multiple artistic styles together by selecting custom combinations via the CLI.
- Shared Album Sync: Automatically push generated images to Shared Albums for instant Apple TV screensaver updates.
- Session SVGs: Generate styled SVG snapshots of the terminal session alongside the art for developer logging.
SKILL.md
Loading
Related Openclaw Skills
WeChat Message and File Sender
A comprehensive communication skill for Openclaw Skills that enables AI agents to query WeChat sessions and actively send text messages or various file types to contacts.
podcast-intel
Turns your Overcast listening history into a structured knowledge base to surface AI-driven insights from recent episodes.
Chinese Chess
A specialized skill for retrieving comprehensive real-time information, history, and rankings for Chinese Chess.
China Country Information Assistant
A comprehensive AI-powered guide for real-time information on China travel, economy, culture, and government policy.
wsl2-local-ai
A high-performance LLM development stack for Windows users utilizing WSL2, NVIDIA GPU passthrough, and Ollama Herd routing.
Windows AI Local Inference Cluster
A powerful tool to turn your Windows PCs into a private, high-performance AI cluster for local LLM inference, image generation, and embeddings.
Featured*
