Skills chatgpt-image-generation

Name: chatgpt-image-generation
Author: openclaw

Generate images from ChatGPT using Playwright browser automation. Opens ChatGPT, sends prompts, waits for generation, and saves the resulting images.

install

source · Clone the upstream repo

git clone https://github.com/openclaw/skills

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/amian/chatgpt-image-generation" ~/.claude/skills/openclaw-skills-chatgpt-image-generation && rm -rf "$T"

OpenClaw · Install into ~/.openclaw/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/skills/amian/chatgpt-image-generation" ~/.openclaw/skills/openclaw-skills-chatgpt-image-generation && rm -rf "$T"

manifest: skills/amian/chatgpt-image-generation/SKILL.md

ChatGPT Image Generation Skill

Use Playwright to automate ChatGPT web UI for image generation.

Prerequisites

npm install playwright
npx playwright install chromium

Usage

# Generate images from prompts file
node generate.js --prompts prompts.json --output ./images

# Resume from a specific index
node generate.js --prompts prompts.json --output ./images --start 5

# Run in headless mode
node generate.js --prompts prompts.json --output ./images --headless

Prompt File Format

["prompt 1", "prompt 2"]

{ "prompts": ["prompt 1", "prompt 2"] }

How It Works

Opens ChatGPT in a Chrome browser
Sends each prompt from the prompts file
Waits for the response to be generated
Finds the generated image in the page
Saves the image to the output directory
Repeats for all prompts

Output

Numbered image files:
```
001.png
```
,
```
002.png
```
, etc.
```
results.jsonl
```
— log of results per prompt

Login (One-Time)

If not logged into ChatGPT:

Run the script (browser will open visible)
Sign into ChatGPT
Session is saved for future runs