← 返回 Skills 市场

Chatgpt Image Generation

Name: Chatgpt Image Generation
Author: amian

作者 Anum Mian · GitHub ↗ · v1.0.3

cross-platform ⚠ suspicious

455

总下载

当前安装

版本数

在 OpenClaw 中安装

/install chatgpt-image-generation

功能描述

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

使用说明 (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

安全使用建议

This skill is mostly coherent but exercise caution before running it. Things to consider: - Playwright will download and run a browser on your machine; ensure you trust the environment where you run it. - The script opens a browser and requires you to manually log into your ChatGPT account; contrary to the README, logins will not persist unless you modify the script to use a persistent user data directory (launchPersistentContext or userDataDir). If you want persistent sessions, add that intentionally and inspect the code. - The script navigates to https://chatgpt.com/ — verify that this is the intended target (you may prefer chat.openai.com). Confirm it matches the service you expect. - The script fetches images by URL found in the page; those resources are fetched over the network and written to disk. Only run with prompts and output directories you control. - Review and test the code locally before giving it access to any sensitive account. If you want persistent login, modify the script explicitly (and inspect any added code) rather than relying on the current misleading README statement. - Be aware that automating a web UI may violate the service’s terms of use; check OpenAI/ChatGPT TOS if applicable.

功能分析

Type: OpenClaw Skill Name: chatgpt-image-generation Version: 1.0.3 The skill utilizes Playwright (`scripts/generate.js`) to automate the ChatGPT web interface, which involves high-risk capabilities such as browser manipulation, network requests, and local file system writes. While the script's logic is consistent with its stated goal of image generation and lacks evidence of intentional malice, the use of automated browser sessions for handling authenticated pages and the lack of path sanitization for output files represent significant security surfaces. Additionally, the installation instructions in SKILL.md involve downloading external browser binaries via npx, which is a common but high-privilege operation.

能力评估

ℹ Purpose & Capability

The code and SKILL.md align: both automate a browser with Playwright, send prompts, and save images. However, SKILL.md claims the login session is saved for future runs while the script launches Chromium without a persistent user data directory (so logins will not persist by default). The script also navigates to https://chatgpt.com/ rather than the commonly used chat.openai.com — this could be benign but is worth verifying.

✓ Instruction Scope

Instructions and code stay within the stated purpose: they read a prompts file, open a browser, interact with the ChatGPT web UI, extract or fetch generated images, write numbered PNGs and a results.jsonl log, and prompt the user to press Enter after a manual login. The code does not reference unrelated files or extra environment variables.

✓ Install Mechanism

No install spec in the registry; SKILL.md asks you to run 'npm install playwright' and 'npx playwright install chromium', which is normal for a Playwright-based script. That will download browser binaries to the machine — expected but noteworthy.

✓ Credentials

The skill requests no environment variables or credentials. It performs browser automation and network requests only, which are proportionate to the stated functionality.

ℹ Persistence & Privilege

The skill is not always-enabled and does not request elevated privileges. However, the SKILL.md's claim that the session is saved across runs contradicts the code (no userDataDir/persistent profile is used). If you expect persistent login, the script must be changed to launch a persistent context or provide a user data directory.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install chatgpt-image-generation
安装完成后，直接呼叫该 Skill 的名称或使用 /chatgpt-image-generation 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.3

Simplified - no profile selection, cross-platform

v1.0.2

Improved code quality and documentation

v1.0.1

Removed references to other skills

v1.0.0

- Initial release of chatgpt-image-generation. - Automates ChatGPT.com image generation via Playwright scripting. - Supports prompt batch processing, resume, custom Chrome profile, and headless mode. - Implements robust completion checks to ensure high-quality, fully-generated image downloads. - Organizes output as sequentially numbered image files and logs details to `results.jsonl`. - Allows login/session persistence with browser profile support.

元数据

Slug chatgpt-image-generation

版本 1.0.3

许可证 —

累计安装 0

当前安装数 0

历史版本数 4

常见问题