← 返回 Skills 市场
168
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install aiznt-images
功能描述
通用图生图（OpenAI 风格）与 Gemini generateContent 文生图。Use when: 文生图、异步出图、Gemini 图像模型。
使用说明 (SKILL.md)
图生图 (aiznt-images)
命令
node scripts/images.js sync --body '{"prompt":"...","model":"..."}'
node scripts/images.js async --body '{...}'
node scripts/images.js async-fetch --task-id \x3Cid>
node scripts/images.js generate-content --model gemini-3-pro-image-preview --body '{...}'
URL 键
v1_images_generationsv1_images_generations_asyncv1_images_generations_async_fetch（{task_id}）v1_models_generate_content（{model}）
配置同其它 aiznt-*：TsClaw「同步天树凭证」批量写入。
安全使用建议
This skill appears to be a straightforward client that forwards image-generation requests to endpoints defined in AIZNT_PROXY_URLS, authenticated with TS_TOKEN. Before installing: verify the origin of the TS_TOKEN and the contents of AIZNT_PROXY_URLS (ensure endpoints are official/trusted domains), avoid passing sensitive local files via --body-file unless you intend to upload them, and be aware that if the agent invokes this skill autonomously it can send prompts/files to the configured endpoints. If you cannot verify the proxy URLs or token source, do not install or restrict the skill from autonomous invocation and revoke the token if suspicious activity is observed.
功能分析
Type: OpenClaw Skill
Name: aiznt-images
Version: 1.0.0
The skill provides a standard interface for image generation using OpenAI-style and Gemini APIs. The logic in `scripts/images.js` and `scripts/client.js` is transparent, focusing on making authenticated HTTP requests to endpoints defined in environment variables (TS_TOKEN and AIZNT_PROXY_URLS). No malicious behaviors such as data exfiltration to hardcoded domains, obfuscation, or unauthorized execution were found.
能力评估
Purpose & Capability
Name/description (image generation, Gemini generateContent) match the required secret (TS_TOKEN) and AIZNT_PROXY_URLS which provide the service endpoints. The code only implements HTTP calls to those endpoints and does not request unrelated credentials or binaries.
Instruction Scope
SKILL.md and scripts instruct the agent to POST JSON bodies (or read a local file via --body-file) to the URLs contained in AIZNT_PROXY_URLS. This is expected for a proxy-based image client, but it means whatever URLs are in AIZNT_PROXY_URLS will receive prompts and files — verify those endpoints are trusted. The script reads arbitrary local file paths only when the user passes --body-file (user-controlled).
Install Mechanism
No install spec or external downloads; the skill is instruction+bundled JS files only. Nothing is fetched or executed from third-party URLs at install time.
Credentials
Only two environment inputs are required: primaryEnv TS_TOKEN (auth token) and AIZNT_PROXY_URLS (JSON mapping of API endpoints). Both are directly used by the client and are proportionate to an API proxy client.
Persistence & Privilege
always:false (normal). The skill can be invoked autonomously (default), and because it uses a network token and sends data to configurable endpoints, autonomous invocation increases potential impact; consider limiting autonomous use if you cannot fully trust the token or endpoint config.
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 aiznt-images - 安装完成后，直接呼叫该 Skill 的名称或使用
/aiznt-images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
Publish from ts-claw bundled-skills
元数据
常见问题
TS Images 是什么？
通用图生图（OpenAI 风格）与 Gemini generateContent 文生图。Use when: 文生图、异步出图、Gemini 图像模型。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 168 次。
如何安装 TS Images？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install aiznt-images」即可一键安装，无需额外配置。
TS Images 是免费的吗？
是的，TS Images 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
TS Images 支持哪些平台？
TS Images 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 TS Images？
由 tianshu（@wangshengli0421）开发并维护，当前版本 v1.0.0。
推荐 Skills