Pony Image Agent is a professional-grade AI tool for generating commercial product photography, replicating visual styles, and creating cohesive image suites.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install pony-image
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 pony-image 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 Pony Image Agent?
Pony Image Agent is a specialized skill designed to automate high-end commercial imagery within the Openclaw Skills ecosystem. It provides developers and businesses with a streamlined workflow for creating visual assets that require strict adherence to brand aesthetics. By supporting three distinct modes—direct generation, style replication, and suite planning—it bridges the gap between raw AI potential and professional marketing requirements.
The tool utilizes state-of-the-art models like Gemini 2.5 Flash for rapid prototyping and Gemini 3 Pro for high-resolution 4K production. Whether you are building an e-commerce platform or a digital marketing automation pipeline, this agent handles the complexities of prompt engineering, lighting consistency, and composition analysis to deliver studio-quality results.
Pony Image Agent Use Cases
- Generating professional e-commerce main images with clean, studio-quality backgrounds.
- Replicating a specific brand aesthetic by analyzing reference images and applying the style to new products.
- Creating a unified set of marketing assets, including detail shots and lifestyle scenes, for a product launch.
- Producing high-resolution social media content tailored to specific aspect ratios like 9:16 for TikTok or 1:1 for Instagram.
How Pony Image Agent Works
- The agent receives a user request and determines the appropriate workflow: direct generation, style replication, or suite creation.
- In style replication mode, the agent first calls an analysis endpoint to extract visual metadata such as color systems and photography styles.
- For suite generation, it creates an overall design plan to ensure visual harmony across multiple images.
- The agent constructs a highly detailed prompt based on the user's input and the analyzed design plan.
- A POST request is sent to the Supabase-hosted backend, which processes the image generation via advanced AI models.
- The resulting image is returned as a Base64 string for immediate integration into the user's workflow.
Pony Image Agent Setup
To integrate this skill into your Openclaw Skills environment, you must configure the following environment variable:
export PONY_SUPABASE_ANON_KEY="your_jwt_anon_key"
All requests are routed through the fixed base URL: https://vecarpahagopuqbwxbjh.supabase.co/functions/v1. Ensure your client provides the correct Authorization header using the Bearer token format.
Pony Image Agent Data Schema & Taxonomy
The agent operates using structured JSON payloads to maintain consistency. Below are the primary data structures:
| Object | Key Attributes | Purpose |
|---|---|---|
Plan |
styleAnalysisSummary, colorSystem, photographyStyle |
Stores visual DNA for style replication. |
SuitePlan |
overallDesign, images[] |
Defines the theme and individual scene descriptions for a set of images. |
Request |
prompt, style, ratio, model |
The standard input schema for image generation. |
Response |
imageUrl, prompt |
Returns the Base64 image data and the final enhanced prompt used. |
Pony Image Agent Advanced Features
- Advanced style replication that decouples visual analysis from image production for iterative design.
- Intelligent suite planning that automates the creation of main images, detail shots, and comparison charts.
- Support for multiple aspect ratios including 21:9 for cinematic banners and 2:3 for vertical posters.
- High-resolution Pro mode supporting 2K and 4K output for professional print-ready assets.
- Multi-model switching between speed-optimized and quality-optimized AI engines.
SKILL.md
Loading
Related Openclaw Skills
EVE Online Item Search
A technical utility for querying EVE Online item database details through local script execution and API calls.
Word to PDF Converter
A Python-powered utility for converting Word documents to PDF with full support for Chinese characters, emojis, and original document styling.
Web Pilot
An API-free web searching and interactive browsing toolset powered by Playwright for AI agents.
Railil
A powerful CLI tool designed to fetch Israel Rail train schedules with fuzzy station matching and machine-readable output formats.
VS Code Tunnel
A specialized skill for launching and managing VS Code Remote Tunnels within Docker containers for seamless remote terminal access.
CCAPI Unified AI Gateway
A unified API gateway providing OpenAI-compatible access to over 60 multimodal AI models across text, image, video, and audio.
Featured*
