← 返回 Skills 市场
125
总下载
0
收藏
0
当前安装
5
版本数
在 OpenClaw 中安装
/install oatda-generate-image
功能描述
Generate images from text descriptions using AI models through OATDA's unified API. Triggers when the user wants to generate, create, or produce AI images, a...
安全使用建议
This skill appears coherent for calling OATDA's image API, but before installing: (1) verify you trust https://oatda.com and its published docs because your API key will be used there; (2) ensure your ~/.oatda/credentials.json is stored with appropriate filesystem permissions (it contains your API key); (3) prefer setting OATDA_API_KEY in the environment rather than leaving a long-lived key file if you have security concerns; (4) be aware that providing public URLs for file-type params exposes those files to the provider; and (5) confirm the endpoint domain matches official docs and that you’re comfortable with the service’s content and privacy policies.
功能分析
Type: OpenClaw Skill
Name: oatda-generate-image
Version: 1.0.6
The skill is a standard implementation for interacting with the OATDA API to generate images. It correctly identifies its requirements (curl, jq, and an API key) and provides clear instructions for the agent to resolve the API key from environment variables or a local configuration file (~/.oatda/credentials.json). The behavior is consistent with the stated purpose, and it includes explicit security instructions for the agent to avoid leaking the full API key in logs or chat outputs.
能力评估
Purpose & Capability
Name/description (image generation via OATDA) match the actual requirements: curl + jq for HTTP and JSON handling, an OATDA API key, and a credentials file for fallback. The listed model providers are plausible for a unified API proxy.
Instruction Scope
SKILL.md only instructs the agent to read the declared credentials file or env var, call OATDA endpoints to list models or generate images, and handle common HTTP errors. It does not direct reading unrelated paths or exfiltrating unrelated secrets.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest-risk install surface. It relies on standard system tools (curl, jq) already declared.
Credentials
Only one credential (OATDA_API_KEY) is required and declared as primary; the credentials file (~/.oatda/credentials.json) is explicitly listed and used as a fallback. No unrelated secrets or multiple service credentials are requested.
Persistence & Privilege
Skill is user-invocable, not always-enabled, and does not request persistent or elevated platform privileges.
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 oatda-generate-image - 安装完成后，直接呼叫该 Skill 的名称或使用
/oatda-generate-image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
v1.0.6
Re-publish with config path declaration for trust scan refresh
v1.0.3
Declare credentials.json file access in manifest
v1.0.2
Declare OATDA_API_KEY credential in metadata for trust scan
v1.0.1
Restore concrete model IDs with fallback note
v1.0.0
Initial release
元数据
常见问题
OATDA Generate Image 是什么？
Generate images from text descriptions using AI models through OATDA's unified API. Triggers when the user wants to generate, create, or produce AI images, a... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 125 次。
如何安装 OATDA Generate Image？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install oatda-generate-image」即可一键安装，无需额外配置。
OATDA Generate Image 是免费的吗？
是的，OATDA Generate Image 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
OATDA Generate Image 支持哪些平台？
OATDA Generate Image 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 OATDA Generate Image？
由 devcsde（@devcsde）开发并维护，当前版本 v1.0.6。
推荐 Skills