← 返回 Skills 市场
mcp98252302

Model Checker

作者 mcp98252302 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
115
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install model-checker
功能描述
查询公司内部可用AI模型列表。
安全使用建议
This skill is coherent and simple: it issues a single unauthenticated GET to a specified API to return available models. Before installing, confirm the endpoint domain (cwork-api-test.xgjktech.com.cn) is legitimate and permitted by your org. Even unauthenticated GETs can leak information (request metadata, IP, headers), so consider running it in an environment with approved outbound network rules. If you prefer, ask the skill author for an official corporate endpoint or documentation and confirm there are no hidden endpoints or requirements. Finally, note the package depends on axios (npm) — ensure your runtime will install dependencies from trusted registries.
功能分析
Type: OpenClaw Skill Name: model-checker Version: 1.0.0 The skill bundle is a straightforward implementation for querying a list of available AI models from a specified corporate API endpoint (xgjktech.com.cn). The code in index.js and the instructions in SKILL.md are consistent with the stated purpose and do not exhibit any signs of data exfiltration, malicious execution, or prompt injection.
能力评估
Purpose & Capability
The name/description ('query internal AI models') matches the SKILL.md and index.js which perform a GET to an AI model-list endpoint. There are no unrelated required binaries, env vars, or config paths.
Instruction Scope
SKILL.md explicitly instructs calling https://cwork-api-test.xgjktech.com.cn/filegpt/t_ai/nologin/aiTypeList. index.js implements a single axios GET to that URL and does not read local files, env vars, or other system state.
Install Mechanism
There is no install spec (instruction-only), but repository includes package.json/package-lock.json listing axios. This is proportional to the task (HTTP request). No arbitrary downloads or extracted archives are present. Runtime may install npm deps, which is expected but worth noting.
Credentials
The skill requests no credentials or config. However it calls an external host (cwork-api-test.xgjktech.com.cn). Although the path includes 'nologin' (no auth), users should verify that the endpoint is a trusted corporate API before allowing calls from the agent, since outbound requests reveal the agent's network traffic and may include headers or metadata.
Persistence & Privilege
The skill does not request permanent presence (always:false), does not modify other skills or system settings, and has normal agent-invocation settings.
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 model-checker
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /model-checker 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
v1.0.0
Initial release
元数据
Slug model-checker
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

Model Checker 是什么?

查询公司内部可用AI模型列表。 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 Model Checker?

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

Model Checker 是免费的吗?

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

Model Checker 支持哪些平台?

Model Checker 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 Model Checker?

由 mcp98252302(@mcp98252302)开发并维护,当前版本 v1.0.0。

💬 留言讨论