← 返回 Skills 市场
MiniMax Image Generator
作者
Tony Simons
· GitHub ↗
· v1.0.1
· MIT-0
183
总下载
1
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install minimax-imagegen
功能描述
Expert image generation skill using MiniMax image-01. Use this skill ANY TIME the user asks to create, generate, make, or produce an image, visual, graphic,...
安全使用建议
This skill appears to be a straightforward image generator, but exercise caution before installing: 1) The SKILL.md and script require MINIMAX_API_KEY though the registry metadata does not declare it — expect to provide that API key; 2) The skill sends prompts and image data to https://api.minimax.io (no homepage/source is provided) — verify the service is trustworthy before using a real API key or sending sensitive imagery; 3) Generated images are saved to ~/.openclaw/workspace/images — ensure you are comfortable with files being written there; 4) If you plan to install, confirm the owner/source and consider creating a scoped API key with limited privileges or using a throwaway key for initial testing. If you want higher assurance, ask the publisher for a homepage, privacy/security info for minimax.io, and updated registry metadata that declares MINIMAX_API_KEY explicitly.
功能分析
Type: OpenClaw Skill
Name: minimax-imagegen
Version: 1.0.1
The minimax-imagegen skill is a legitimate tool for generating images using the MiniMax API. The core logic in `scripts/generate-image.mjs` correctly handles API authentication via environment variables and safely downloads images to a local workspace. The `SKILL.md` instructions provide helpful prompt engineering guidelines for the agent without any malicious directives or attempts to exfiltrate sensitive data.
能力评估
Purpose & Capability
The skill's stated purpose (image generation with MiniMax image-01) matches the included script and SKILL.md. However, the registry metadata lists no required environment variables even though SKILL.md and the script both gate on MINIMAX_API_KEY — this metadata omission is inconsistent and could mislead users about needed credentials.
Instruction Scope
Runtime instructions focus on prompt engineering, selecting parameters, calling the image generation API, and saving results to the workspace (~/.openclaw/workspace/images). The SKILL.md does not instruct the agent to read unrelated system files or exfiltrate unrelated data. It does permit subject_reference entries (URLs or base64) which may cause the agent to fetch user-supplied images; that behavior is consistent with the skill's purpose.
Install Mechanism
There is no install spec (instruction-only skill) and a single included Node script is provided. The script performs network calls to https://api.minimax.io and downloads generated images — expected for an image-generation skill. The external API host (minimax.io) has no homepage provided in the skill metadata, so users should verify the service's legitimacy before providing credentials.
Credentials
The script and SKILL.md require MINIMAX_API_KEY (and the SKILL.md even lists it in gates) but the registry 'Requirements' section lists no required env vars or primary credential. This mismatch is a material coherence problem: the skill legitimately needs one API key for its function, but the published metadata failing to declare it could confuse users and tooling managing secrets. No other unrelated credentials are requested.
Persistence & Privilege
The skill does not request permanent/always-available privileges (always:false), does not modify other skills' configs, and only writes generated images to a workspace directory. It does not request elevated system access. Autonomous invocation is enabled by default but that is expected behavior for skills.
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 minimax-imagegen - 安装完成后，直接呼叫该 Skill 的名称或使用
/minimax-imagegen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
v1.0.1
v1.0.1: Security fixes — removed auth-profiles.json fallback, added MINIMAX_API_KEY env gate, fixed default output path to ~/.openclaw/workspace/images/
v1.0.0
Initial release: MiniMax image-01 generation with expert prompt engineering, use-case mapping, and aspect ratio guidance.
元数据
常见问题
MiniMax Image Generator 是什么？
Expert image generation skill using MiniMax image-01. Use this skill ANY TIME the user asks to create, generate, make, or produce an image, visual, graphic,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 183 次。
如何安装 MiniMax Image Generator？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install minimax-imagegen」即可一键安装，无需额外配置。
MiniMax Image Generator 是免费的吗？
是的，MiniMax Image Generator 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
MiniMax Image Generator 支持哪些平台？
MiniMax Image Generator 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 MiniMax Image Generator？
由 Tony Simons（@asimons81）开发并维护，当前版本 v1.0.1。
推荐 Skills