← 返回 Skills 市场
130
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install openai-image-gen-andy27725
功能描述
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
安全使用建议
This skill appears to do what it says: it uses your OPENAI_API_KEY to call api.openai.com and save generated images and an index.html gallery locally. Things to consider before installing: 1) network access and API usage costs—each run invokes the OpenAI Images API and may consume billable credits; 2) it writes files to your home directory (~/Projects/tmp/openai-image-gen-<ts> or ./tmp), so ensure you are comfortable with those outputs and have disk space; 3) moderation/streaming features are not implemented in the script, so generated content is not auto-moderated by this tool — exercise normal content caution; 4) verify the OPENAI_API_KEY you provide has appropriate permissions and is stored securely. If you want extra assurance, review the remaining (truncated) portion of scripts/gen.py to confirm it only downloads image URLs returned by the API and doesn't send data to any other endpoints.
功能分析
Type: OpenClaw Skill
Name: openai-image-gen-andy27725
Version: 1.0.0
The skill provides a Python script to batch-generate images using the OpenAI API and creates a local HTML gallery for viewing. It correctly handles API authentication via environment variables, implements XSS protection in the generated HTML using html.escape, and lacks any indicators of data exfiltration, persistence, or malicious execution. Files analyzed: SKILL.md, scripts/gen.py, and scripts/test_gen.py.
能力评估
Purpose & Capability
Name/description (batch-generate images via OpenAI Images API) matches the code and declared requirements. The only required binary is python3 and the only required env var is OPENAI_API_KEY, both appropriate for this task.
Instruction Scope
SKILL.md instructs running the included Python script and opening the generated index.html. The runtime instructions and flags map to the script's behavior. The instructions do not ask the agent to read unrelated files or extra environment variables; they note increasing exec timeout for long-running image generation.
Install Mechanism
Install spec is a single Homebrew formula (python). This is a standard, low-risk install mechanism and appropriate because the code requires python3.
Credentials
The skill requires a single credential (OPENAI_API_KEY) which is necessary to call the OpenAI Images API. No unrelated credentials, config paths, or broad secrets are requested.
Persistence & Privilege
The skill does not request always: true and is user-invocable as expected. It does write output files to a user-local directory (~/Projects/tmp or ./tmp), which is consistent with generating images and a gallery.
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 openai-image-gen-andy27725 - 安装完成后，直接呼叫该 Skill 的名称或使用
/openai-image-gen-andy27725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
v1.0.0
- Initial release of openai-image-gen: batch-generate images using the OpenAI Images API with random structured prompts.
- Includes a Python script for custom image parameters (model, prompt, count, size, quality, format, background, style).
- Supports GPT image models, DALL-E 3 (with auto count-limiting), and DALL-E 2, with model-specific defaults and features.
- Generates output images, a prompts mapping JSON, and an `index.html` thumbnail gallery for easy browsing.
- Full command-line usage documentation and parameter breakdown included in SKILL.md.
元数据
常见问题
Openai Image Gen Andy27725 是什么？
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 130 次。
如何安装 Openai Image Gen Andy27725？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openai-image-gen-andy27725」即可一键安装，无需额外配置。
Openai Image Gen Andy27725 是免费的吗？
是的，Openai Image Gen Andy27725 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Openai Image Gen Andy27725 支持哪些平台？
Openai Image Gen Andy27725 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Openai Image Gen Andy27725？
由 Andy27725（@andy27725）开发并维护，当前版本 v1.0.0。
推荐 Skills