← 返回 Skills 市场
252
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install mz-minimax-img-gen
功能描述
MiniMax image-01 文生图工具。支持中文指令（画一张、生成图片、帮我画）和英文指令（generate an image、draw）。双端支持（中国区/国际区）。Token Plan 每日免费额度：Plus 50张/天、Max 120张/天、Ultra 800张/天。模型：image-01，输出 PNG。
安全使用建议
This skill appears to do exactly what it claims: send your prompt to MiniMax's image-01 endpoints and save returned images locally. Before installing: ensure you trust the MiniMax endpoints you use (api.minimax.chat for China, api.minimax.io for global), keep your MINIMAX_API_KEY secret, and only provide a key from your MiniMax account. The script uses the requests library and saves base64-decoded PNG files to the output directory; you may review scripts/image_gen.py yourself if you want to confirm behavior. Network access is required for the API calls; there are no other external endpoints or unexpected credential requests.
功能分析
Type: OpenClaw Skill
Name: mz-minimax-img-gen
Version: 1.3.8
The skill is a legitimate implementation of a text-to-image generator using the MiniMax API. The Python script (scripts/image_gen.py) correctly handles API authentication via environment variables, supports regional endpoints (api.minimax.chat and api.minimax.io), and saves generated images locally without any signs of data exfiltration, malicious execution, or prompt injection.
能力评估
Purpose & Capability
Name/description claim text-to-image using MiniMax image-01. The script and docs only require a MINIMAX_API_KEY and call MiniMax endpoints (api.minimax.chat / api.minimax.io). Requested capabilities match the stated purpose.
Instruction Scope
SKILL.md instructs installing requests, setting MINIMAX_API_KEY, choosing region, and running the included Python script. The runtime instructions only reference the MiniMax API, local output directory, and the declared env var. The agent is not instructed to read unrelated files or system configuration.
Install Mechanism
No install spec in registry; SKILL.md suggests 'pip install requests' which is proportionate and low risk. There are no downloads from arbitrary URLs or archive extraction steps.
Credentials
Only MINIMAX_API_KEY is required (declared in SKILL.md and allowList). That single credential is appropriate for calling the external MiniMax API. No unrelated secrets, config paths, or excessive env vars are requested.
Persistence & Privilege
The skill does not request permanent/always-on installation. It does not modify other skills or system-wide settings. Autonomous invocation is allowed by default but is normal for skills and not combined with other red flags.
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 mz-minimax-img-gen - 安装完成后，直接呼叫该 Skill 的名称或使用
/mz-minimax-img-gen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
v1.3.8
Fix: English title first, Chinese second
v1.3.7
Fix: add Chinese displayName for ClawHub
v1.3.6
Fix: declare MINIMAX_API_KEY in allowList; English-first displayName for ClawHub
v1.3.5
Title: Chinese-first for openclawmp, English-first for ClawHub
元数据
常见问题
MiniMax image-01 · AI Text-to-Image Tool 是什么？
MiniMax image-01 文生图工具。支持中文指令（画一张、生成图片、帮我画）和英文指令（generate an image、draw）。双端支持（中国区/国际区）。Token Plan 每日免费额度：Plus 50张/天、Max 120张/天、Ultra 800张/天。模型：image-01，输出 PNG。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 252 次。
如何安装 MiniMax image-01 · AI Text-to-Image Tool？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install mz-minimax-img-gen」即可一键安装，无需额外配置。
MiniMax image-01 · AI Text-to-Image Tool 是免费的吗？
是的，MiniMax image-01 · AI Text-to-Image Tool 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
MiniMax image-01 · AI Text-to-Image Tool 支持哪些平台？
MiniMax image-01 · AI Text-to-Image Tool 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-01 · AI Text-to-Image Tool？
由 sweesama（@sweesama）开发并维护，当前版本 v1.3.8。
推荐 Skills