← 返回 Skills 市场
Mxai
作者
tianheihei002
· GitHub ↗
· v1.0.0
· MIT-0
115
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install mxai
功能描述
mxai 创作助手,聚合多种 AI 图片和视频生成模型,以及 MJ(MidJourney)绘画。关键词:AI绘画、图片生成、视频生成、AI创作、mxai、MJ、MidJourney
安全使用建议
This skill appears to be what it claims: a client for the mxai image/video API. Before installing, consider: (1) privacy — the skill will transmit any images or text you provide to https://mcp.mxai.cn, so do not send sensitive images unless you trust that service; (2) credential handling — you must supply MX_AI_API_KEY (it will be used as a Bearer header or a URL query param; prefer header usage to avoid accidental leakage in logs); (3) billing — generation consumes account credits per the documented cost table; (4) trust & provenance — the skill's source/homepage is unspecified, so only provide your API key if you trust the mxai service and the skill distributor; (5) remediation — if the key is ever exposed, revoke/rotate it immediately. The included install.sh only copies local files into your OpenClaw skills folder and does not download remote code.
功能分析
Type: OpenClaw Skill
Name: mxai
Version: 1.0.0
The mxai skill bundle is a legitimate integration for the mxai.cn AI service, providing tools for image and video generation via HTTP REST APIs. The SKILL.md file contains detailed operational instructions and safety rules for the AI agent, including explicit requirements to mask sensitive API keys in error logs and avoid fabricating responses. The install.sh script is a standard file-copying utility with no suspicious network or execution behavior.
能力标签
能力评估
Purpose & Capability
Name/description, required env var (MX_AI_API_KEY), and SKILL.md all describe calling mxai's HTTP REST API for image/video generation and MJ workflows. The single credential requested and the documented API endpoints align with the stated purpose.
Instruction Scope
SKILL.md instructs the agent to forward user-provided images (base64 or URLs) and prompts to the remote mxai service and to poll task status until completion. This is within scope for an image/video generation skill, but it explicitly directs transmitting user images/inputs to an external service and instructs the agent not to validate API key format and not to suggest manual web remediation on API errors — unusual constraints that reduce agent discretion but are coherent with the skill's intended protocol.
Install Mechanism
No remote install spec; only an included install.sh that copies the skill files into the user's OpenClaw skills directory. No downloads from external hosts or extraction of remote archives were found.
Credentials
Only one environment variable (MX_AI_API_KEY) is required and is the declared primary credential, which is proportional to a hosted API service. The SKILL.md allows using either an Authorization Bearer header or a key query param — using query params can expose keys in logs or referer headers, so header-based auth is safer, but the request for a single API key is reasonable for this purpose.
Persistence & Privilege
The skill is not marked always:true, does not request system-wide config changes, and does not modify other skills. Its provided install script writes only into the skill workspace — expected behavior for an instruction-only skill with a helper installer.
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 mxai - 安装完成后,直接呼叫该 Skill 的名称或使用
/mxai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
mxai 1.4.3发布摘要
- 全新文档结构,详细列出所有可用图片/视频生成模型和MJ(MidJourney)专用工具,明确参数选项与调用规范。
- 严格规则体系与自检流程,杜绝伪造API响应、伪造模型、参数、API Key校验和手动操作建议等违规行为。
- 细化用户交互指引,自动判断意图并协助收集必需信息(如图片/描述),避免无效调用。
- 支持多种图片获取与传递方式,包括图片直发、URL、上传Key复用等,提升操作灵活性。
- MJ工具集全面说明,涵盖MJ绘画、放大、视频、描述词分析、混图等进阶玩法及积分消耗说明。
- 明确错误处理指引及相关提示,确保结果真实可靠。
元数据
常见问题
Mxai 是什么?
mxai 创作助手,聚合多种 AI 图片和视频生成模型,以及 MJ(MidJourney)绘画。关键词:AI绘画、图片生成、视频生成、AI创作、mxai、MJ、MidJourney. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 115 次。
如何安装 Mxai?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install mxai」即可一键安装,无需额外配置。
Mxai 是免费的吗?
是的,Mxai 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Mxai 支持哪些平台?
Mxai 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 Mxai?
由 tianheihei002(@tianheihei002)开发并维护,当前版本 v1.0.0。
推荐 Skills