← 返回 Skills 市场

MiniMax文生图

Name: MiniMax文生图
Author: xiaoliang1319-cloud

作者 xiaoliang1319-cloud · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

106

总下载

当前安装

版本数

在 OpenClaw 中安装

/install dmxapi-image

功能描述

使用 MiniMax (image-01) 和其他模型生成图片。支持文生图、图片编辑。当用户需要生成图片、AI绘图时使用此技能。使用方法：用户需要配置 DMXAPI_API_KEY 环境变量。

使用说明 (SKILL.md)

MiniMax Image Generation Skill

功能

文生图 - 根据文本描述生成图片
支持多种尺寸和比例

使用前提

用户需要：

MiniMax API Key（sk-cp-xxx 格式）
确保套餐包含图片生成功能

API 用法

const https = require('https');

const apiKey = 'YOUR_MINIMAX_API_KEY';

const body = JSON.stringify({
  model: 'image-01',
  prompt: '描述内容',
  aspect_ratio: '1:1',
  response_format: 'base64'
});

const options = {
  hostname: 'api.minimaxi.com',
  path: '/v1/image_generation',
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': `Bearer ${apiKey}`
  }
};

示例

生成小龙虾头像：

model: image-01
prompt: cute cartoon lobster mascot, kawaii style, orange color, big eyes
aspect_ratio: 1:1

安全使用建议

Do not install until the manifest and documentation are reconciled. Specifically: (1) Confirm the exact environment variable name the agent will read (e.g., DMXAPI_API_KEY) and ensure it is declared as the primary credential in the skill manifest; (2) Verify the service domain (api.minimaxi.com) and the provider's reputation and privacy policy, since prompts and generated images will be sent to that external API; (3) Limit the API key's scope and rotate/revoke it if shared; (4) Prefer the SKILL.md include a clear example using process.env.DMXAPI_API_KEY (or equivalent) so the agent will not rely on ambiguous or hard-coded keys; (5) If you handle sensitive images or prompts, avoid using this skill until you confirm data handling practices. These steps will reduce the risk of accidental data exposure caused by the manifest/instruction mismatch.

功能分析

Type: OpenClaw Skill Name: dmxapi-image Version: 1.0.0 The skill bundle contains only metadata and documentation (SKILL.md) for integrating with the MiniMax image generation API. It provides standard usage instructions and a JavaScript code snippet for making HTTPS requests to api.minimaxi.com, with no executable scripts or malicious instructions present.

能力评估

⚠ Purpose & Capability

The declared purpose (text→image generation) matches the SKILL.md's API usage (image-01 on api.minimaxi.com). However the registry metadata lists no required environment variable or primary credential while the SKILL.md explicitly says a MiniMax API key (sk-cp-xxx format / DMXAPI_API_KEY) is required. That inconsistency suggests the manifest is incomplete or incorrect.

ℹ Instruction Scope

The runtime instructions are narrowly scoped to calling the MiniMax image-generation API and include an example POST. They do not instruct reading arbitrary files or other system state. However the SKILL.md does not show how the key is obtained (no explicit env var name in the code example) and the top description mentions DMXAPI_API_KEY—this ambiguity is worth clarifying.

✓ Install Mechanism

No install spec or code files are present (instruction-only), so nothing is written to disk and there is no package download risk.

⚠ Credentials

The skill needs an API key to operate, yet the skill manifest metadata does not declare any required environment variables or primary credential. The SKILL.md references a key (format sk-cp-xxx) and mentions DMXAPI_API_KEY — the mismatch is disproportionate and ambiguous. Also be aware that sending prompts/images to an external API can expose sensitive content to the provider.

✓ Persistence & Privilege

The skill does not request permanent presence (always:false) and contains no instructions to modify other skills or system-wide configurations.

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 dmxapi-image
安装完成后，直接呼叫该 Skill 的名称或使用 /dmxapi-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

v1.0.0

首个版本，支持MiniMax image-01模型文生图

元数据

Slug dmxapi-image

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题