闲社服务运行正常AI智能体自动化平台
客户端下载帮助中心服务商入驻
免费注册
技能集市 > AI智能 > desktop-sandbox
d

桌面沙盒

技能标识：desktop-sandbox

A desktop sandbox lets OpenClaw run as natively as on a real OS, ensuring full functionality with safe isolation.Run OpenClaw without breaking your PC.

作者：admin | 来源记录：ClawHub
下载
登记来源
ClawHub
版本
V 1.1.1
检测标记
后台标记通过
免费
免费获取
2
收藏
来源与检测标记为平台登记信息，并不代表已展示可复核的检测报告。使用前请核对版本、依赖和所需权限，建议先在隔离环境中运行。
概述
安装方式
版本历史

桌面沙盒

Desktop Sandbox 安装程序

从 GitHub 发布版本安装 AtlasCore Desktop Sandbox。

脚本

bash
node scripts/run_installer.js [--version=v1.0]

参数

参数说明
--version指定版本（默认：最新版）

平台行为

平台安装程序目标路径
Windows.exe → /S /D=C:\Program Files\C:\Program Files\
macOS
.pkg → open -W | / |

退出代码

代码含义
0成功
1
安装失败 | | 999 | 致命错误 |

OpenClaw 对话使用

在对话中，只需说：

  • - 安装 AtlasCore 桌面沙箱
  • 安装桌面沙箱
  • 下载并安装 AtlasCore 沙箱

标签

skill ai

通过对话安装

以下为平台配置的接入选项，并非逐项实测通过。能否安装取决于客户端支持、技能来源和运行环境：

OpenClaw WorkBuddy QClaw Kimi Claude

方式一：安装 SkillHub 和技能

帮我安装 SkillHub 和 desktop-sandbox-1776419997 技能

方式二：设置 SkillHub 为优先技能安装源

设置 SkillHub 为我的优先技能安装源，然后帮我安装 desktop-sandbox-1776419997 技能

通过命令行安装

skillhub install desktop-sandbox-1776419997

下载

⬇ 下载 desktop-sandbox v1.1.1（免费）

文件大小: 4.67 KB | 发布时间: 2026-4-17 20:10

v1.1.1 最新 2026-4-17 20:10
- Updated description for clarity and simplified language.
- Changed macOS installer command to use open -W.
- Adjusted example installation commands for clearer phrasing.
- No changes to code or scripts; documentation updates only.

相关推荐

s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
返回顶部