Automate the generation and downloading of AI images by driving ChatGPT through Playwright browser automation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install chatgpt-image-generation
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 chatgpt-image-generation 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 ChatGPT Image Generation Skill?
The ChatGPT Image Generation skill leverages Playwright to programmatically interact with the ChatGPT web interface. It allows developers to bypass manual prompt entry for DALL-E 3 by feeding a list of prompts directly into the chat UI. This Openclaw Skills contribution is ideal for users who need to generate high volumes of visual assets without constant manual intervention, ensuring each generated image is captured and indexed locally.
By automating the web browser, this skill handles the heavy lifting of waiting for generation processes and capturing the final output. It is a powerful tool for developers looking to integrate ChatGPT's visual capabilities into their existing pipelines without relying on limited API access.
ChatGPT Image Generation Skill Use Cases
- Bulk generating visual assets for marketing campaigns using Openclaw Skills automation.
- Scaling AI-assisted art creation for game development or storyboarding.
- Automating consistent prompt testing across multiple DALL-E 3 iterations.
- Creating a local archive of ChatGPT-generated images for research or design projects.
How ChatGPT Image Generation Skill Works
- Launches a Chromium browser instance via Playwright and navigates to the ChatGPT web portal.
- Iterates through a provided JSON prompt file to input generation commands sequentially into the chat box.
- Monitors the chat response in real-time to detect when the DALL-E 3 image generation process completes.
- Identifies the generated image element within the page DOM and downloads the file to the specified output directory.
- Saves a log of the execution status and prompt-to-image mapping for auditing.
- Repeats the cycle automatically for all prompts in the queue.
ChatGPT Image Generation Skill Setup
First, ensure you have the required browser automation dependencies installed:
npm install playwright
npx playwright install chromium
To execute the generation process, use the following command structure:
node generate.js --prompts prompts.json --output ./images
Note: On your first run, the browser will open for you to perform a one-time manual login. The session is saved for all subsequent Openclaw Skills runs.
ChatGPT Image Generation Skill Data Schema & Taxonomy
The skill organizes its output into a designated folder with clear metadata mapping:
| File Type | Pattern | Description |
|---|---|---|
| Images | 001.png, 002.png |
Sequentially numbered image files generated by DALL-E 3. |
| Metadata | results.jsonl |
A JSON Lines log containing the prompt and the file path of the resulting image. |
| Input | prompts.json |
A JSON file containing either a simple array of strings or a prompts object. |
ChatGPT Image Generation Skill Advanced Features
- Headless mode support using the
--headlessflag for background execution on servers. - Resume functionality via the
--startflag to pick up generation from a specific prompt index after an interruption. - Automatic session persistence to bypass login screens in future Openclaw Skills sessions.
- Flexible input parsing that supports multiple JSON prompt structures.
SKILL.md
Loading
Related Openclaw Skills
Performance Marketing Agent
An AI-powered performance marketing agent that automates campaign management, keyword research, and cross-platform reporting for major ad networks.
Adspirer Ads Agent
An AI-powered advertising agent for managing multi-channel ad campaigns across Google, Meta, LinkedIn, and TikTok using natural language.
Meta-Research
An autonomous research copilot that manages the full scientific lifecycle from brainstorming to final reporting with a focus on reproducibility.
Huangdi Health Timer
An AI-driven wellness assistant that provides health advice based on the 12 Traditional Chinese Medicine meridian energy cycles.
ClawHub Skill Scanner
A mandatory security gatekeeper that performs deep code analysis to detect malicious patterns before installing any Openclaw Skills.
Tasker Task Management
A sophisticated task management skill for Openclaw Skills that translates natural language into structured docstore commands for lists, boards, and planning.
METADATA
Featured*
