← 返回 Skills 市场
lilisidu1210-ui

调用closeai的gpt

作者 lilisidu1210-ui · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
356
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install gpt-chat
功能描述
GPT聊天 - 使用GPT模型进行对话和内容生成
使用说明 (SKILL.md)

GPT 聊天 Skill

使用 GPT 模型进行对话和内容生成。

已配置

  • 默认模型: GPT-5.1
  • 脚本路径: skills/gpt-chat/scripts/gpt.js

⚠️ 使用前请设置环境变量 OPENAI_API_KEY 或在对话中提供你的 Key

支持的模型

模型 输入价格 输出价格 说明
GPT-5.2 $1.75/1M tokens $14/1M tokens 最新旗舰模型
GPT-5.1 $1.25/1M tokens $10/1M tokens 稳定版(默认)
GPT-5 $1.25/1M tokens $10/1M tokens 标准版

使用方法

在对话中可以直接使用以下命令:

  1. 查看可用模型:

    运行 node skills/gpt-chat/scripts/gpt.js list
    
  2. 切换模型:

    运行 node skills/gpt-chat/scripts/gpt.js set gpt-5.2
    
  3. 发送消息:

    运行 node skills/gpt-chat/scripts/gpt.js chat 你的问题
    
  4. 查看当前模型:

    运行 node skills/gpt-chat/scripts/gpt.js current
    

直接调用示例

可以直接在对话中说:

  • "使用 GPT-5.2 模型"
  • "切换到 gpt-5.1"
  • "用 gpt-5 回答我的问题"

API Key 配置

如需使用自己的 API Key,可以设置环境变量 OPENAI_API_KEY,或在对话中提供你的 Key。

安全使用建议
This skill is a local Node-based GPT client and will ask for your OpenAI API key. Before installing or running it: (1) do not paste your API key into chat — set OPENAI_API_KEY as an environment variable instead; (2) inspect and change any API base to the official https://api.openai.com if you intend to use OpenAI directly — several scripts default to api.openai-proxy.org which could forward your key/requests to a third party; (3) if you already supplied a key while trying this skill, treat it as compromised and rotate it; (4) run the skill in an isolated environment and review network traffic (or the skill author’s explanation) if you need to trust a proxy endpoint. The code otherwise matches the described functionality, but the non-official proxy default and the encouragement to paste keys in conversation are the main security concerns.
功能分析
Type: OpenClaw Skill Name: gpt-chat Version: 1.0.0 The skill is classified as suspicious due to the use of a third-party proxy (api.openai-proxy.org) as the default endpoint for the OPENAI_API_KEY in gpt.js and generate-article.js, which risks exposing sensitive credentials to an unofficial intermediary. Furthermore, the documentation (SKILL.md) deceptively claims to support non-existent 'GPT-5.1' and 'GPT-5.2' models with specific pricing, acting as a misleading lure for users to provide their API keys. The bundle also includes an unadvertised local HTTP server (server.js) that exposes API functionality on port 3456, which could allow unauthorized local network access to the user's configured credentials.
能力评估
Purpose & Capability
The name/description claim a GPT chat client using OpenAI; the code largely implements that. However, several scripts default to a non-official API base (api.openai-proxy.org) while others call api.openai.com. A GPT chat skill should default to the official OpenAI API (api.openai.com). The proxy default is disproportionate and unexplained.
Instruction Scope
SKILL.md instructs running the included Node scripts (list, set, chat) which matches the code. But it explicitly suggests users may provide the API key in the conversation body which risks exposing secrets in logs or transcripts. The runtime instructions do not declare or warn about an API_BASE override, even though the code supports it.
Install Mechanism
No install spec (instruction-only) and required binary is just node. Code files are bundled with the skill (so code runs locally) — this is expected for a script-based skill and does not itself indicate an install-time integrity risk.
Credentials
The declared required env var is only OPENAI_API_KEY which is appropriate. However, the code also reads OPENAI_API_BASE (not declared in requires.env) and defaults it to api.openai-proxy.org in multiple scripts. Undeclared endpoint configuration and a non-official default endpoint expand the trust surface and could lead to API key forwarding to an untrusted third party.
Persistence & Privilege
The skill does not request always:true, does not modify other skill settings, and stores only a local state.json in its own directory. No elevated persistence or cross-skill config changes detected.
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 gpt-chat
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /gpt-chat 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 of gpt-chat skill for conversational and content generation using the GPT model. - Default model set to GPT-5.1, with support for GPT-5 and GPT-5.2. - Key command-line functions: list, set, chat, and current model status. - Requires OPENAI_API_KEY environment variable to function. - Includes clear example commands for switching models and interacting via the script.
元数据
Slug gpt-chat
版本 1.0.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 1
常见问题

调用closeai的gpt 是什么?

GPT聊天 - 使用GPT模型进行对话和内容生成. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 356 次。

如何安装 调用closeai的gpt?

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

调用closeai的gpt 是免费的吗?

是的,调用closeai的gpt 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

调用closeai的gpt 支持哪些平台?

调用closeai的gpt 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 调用closeai的gpt?

由 lilisidu1210-ui(@lilisidu1210-ui)开发并维护,当前版本 v1.0.0。

💬 留言讨论