← 返回 Skills 市场
yang1002378395-cmyk

Openclaw Cn Installer

作者 yang1002378395-cmyk · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ⚠ suspicious
245
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install openclaw-cn-installer
功能描述
OpenClaw 中文安装配置助手。一键检测环境、配置国产 AI 模型(DeepSeek/智谱/阿里通义)。适合中国用户快速上手 OpenClaw。
安全使用建议
This skill appears to do what it says: it checks your environment, prompts you for API keys for DeepSeek/智谱/阿里通义, saves them to ~/.openclaw/.env (plaintext), updates ~/.openclaw/config.json, and tests connections to the listed provider endpoints. Before installing: (1) confirm you trust the source (package.json repo URL) because the tool will store API keys locally; (2) ensure ~/.openclaw has appropriate filesystem permissions; (3) prefer creating limited-scope API keys and rotate them if you later distrust the tool; (4) you can inspect the three JS files yourself—there is no hidden network exfiltration in the code, only requests to the declared provider domains and an npm mirror check; (5) if you need stricter security, avoid entering high-privilege keys here or use environment-level secrets managers instead.
功能分析
Type: OpenClaw Skill Name: openclaw-cn-installer Version: 1.0.1 The skill bundle is a legitimate configuration utility designed to help Chinese users set up OpenClaw with local AI providers like DeepSeek, Zhipu, and Alibaba Qwen. The scripts (check-env.js, setup-ai.js, and test-connection.js) perform standard environment checks, local storage of API keys in the user's home directory (~/.openclaw/.env), and connectivity tests against official provider endpoints. No evidence of data exfiltration, malicious shell execution, or prompt injection was found, and the package contains no external dependencies.
能力评估
Purpose & Capability
Name/description (Chinese installer for DeepSeek/智谱/阿里通义) align with the included files: environment checker, model setup (writes local .env and config.json), and connection tester that POSTs to the declared provider endpoints.
Instruction Scope
SKILL.md tells the agent to run the three included scripts and references only ~/.openclaw files and provider endpoints. The scripts only inspect the system environment, prompt for API keys, store them locally, and call provider APIs to test connectivity—no unrelated file reads or external endpoints beyond provider/platform URLs and the npm mirror check.
Install Mechanism
No install spec; this is instruction-plus-scripts only. Files are plain JS and package.json points to a GitHub repo. No downloads from untrusted URLs or archive extraction steps are present.
Credentials
The skill requests no environment variables from the platform, but it prompts users to enter provider API keys and stores them in plaintext at ~/.openclaw/.env and writes ~/.openclaw/config.json. This is expected for a local installer but users should be aware keys are stored locally and readable by any process with access to that path.
Persistence & Privilege
always is false and there is no attempt to modify other skills or system-wide agent settings. The skill creates/updates files only under the user's home ~/.openclaw directory, which is consistent with its role.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install openclaw-cn-installer
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /openclaw-cn-installer 触发
  4. 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
openclaw-cn-installer v1.0.1 - 修正文档内容,确保与实际功能一致 - 移除未实现功能的说明,提升文档准确性
v1.0.0
首次发布: 环境检测 + AI模型配置 + 连接测试
元数据
Slug openclaw-cn-installer
版本 1.0.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

Openclaw Cn Installer 是什么?

OpenClaw 中文安装配置助手。一键检测环境、配置国产 AI 模型(DeepSeek/智谱/阿里通义)。适合中国用户快速上手 OpenClaw。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 245 次。

如何安装 Openclaw Cn Installer?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install openclaw-cn-installer」即可一键安装,无需额外配置。

Openclaw Cn Installer 是免费的吗?

是的,Openclaw Cn Installer 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Openclaw Cn Installer 支持哪些平台?

Openclaw Cn Installer 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 Openclaw Cn Installer?

由 yang1002378395-cmyk(@yang1002378395-cmyk)开发并维护,当前版本 v1.0.1。

💬 留言讨论