Token导航 LogoToken导航TokenDH.com
运维敏感数据clawhub未标认证来源可访问clear审计提醒

multi-user-workspace多用户工作区

Agent Skill

multi-user-workspace 用于补充运维相关能力,适合在 OpenClaw 中需要让 Agent 承接运维相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

26,258

周安装

1,052

GitHub Stars

2

下载量

8,292
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:multi-user-workspace(多用户工作区)
来源仓库:https://github.com/shun-dong/multi-user-workspace
安装命令:
openclaw skills install multi-user-workspace
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install multi-user-workspace

简介

multi-user-workspace 管理具有沙箱权限与关系网络的多用户协作环境。

  • 适用于企业内部知识共享、项目团队或在线教育系统。
  • 通过 OpenClaw 安装后,Agent 可分配资源并监控用户活动。
  • 使用前需定义角色权限矩阵,确保最小化访问原则。
  • 注意网络拓扑设计,防止单点故障影响整体可用性。

SKILL.md

name
multi-user-workspace
description
Multi-user workspace management with sandbox permissions, user profiles, and relationship networks.

Friends

Configure per-user sessions with sandbox isolation, friend profiles, and relationship awareness.

Core Concepts

  • UserId: Lowercase unique identifier (e.g., alice, bob). Used in session keys, filenames, and cross-references.
  • Session: One session per user, named agent:<agentId>:<mainKey> where mainKey typically contains the userId.
  • Sandbox: Optional Docker isolation per session, configured in openclaw.json.
  • FRIENDS/: User profile directory (one file per user, named {userId}.md).
  • RELATIONS/: Relationship directory (files named {userId1}-{userId2}.md, alphabetically sorted, can be mutiple users).

Example Workspace Structure

workspace/
├── USER.md              # User registry with permissions
├── AGENTS.md            # Multi-user guidance for assistant
├── FRIENDS/
│   ├── alice.md        # alice's profile
│   └── bob.md          # bob's profile
├── RELATIONS/
│   └── alice-bob.md    # Relationship between alice and bob
├── private/            # Admin-only files (optional)
...

USER.md

Registry of all users. The assistant reads this to identify users and extract userId and Name.

Format:

# User Registry

## Users

### alice
- UserId: alice
- Name: Alice
- Role: administrator

### bob
- UserId: bob
- Name: Bob
- Role: guest

Note: userId is unique and in lower case. Use Role to determine sandbox configuration in openclaw.json.

FRIENDS/

User profiles. One Markdown file per user, named {userId}.md.

Content is flexible. Common sections include:

# Alice

## Info
- UserId: alice
- Name: Alice
- Role: administrator
- Emails: alice@example.com
...
## Assistant Relationship
- How the user prefers to interact with the assistant
- Preferred communication style
- Ongoing projects or interests

## Notes
Free-form information about the user.

RELATIONS/

Interpersonal relationships. Files named {userId1}-{userId2}.md (alphabetical order, can be mutiple users).

Content is flexible. Example:

# Alice & Bob

## Users
- **alice**: Alice
- **bob**: Bob

## Relationship
Friends who collaborate on projects.

## Information Sharing
- Can mention each other's public projects
- Do not share private details without asking

AGENTS.md

Instructions for the assistant. Add this section:

## User Identification

When a session starts (after `/new`):

1. Get current session via `session_status`
2. Extract userId from the session key (e.g., `agent:main:alice` → `alice`)
3. Read `FRIENDS/{userId}.md` for user profile
4. Read `RELATIONS/*{userId}*.md` for all relationships involving this user
5. Greet the user by name

## Cross-User Boundaries

- Default: Information does not flow between users
- Exception: Only when explicitly defined in RELATIONS/

Session Configuration

Each user gets an isolated session with configurable sandbox and tool permissions. Configure via openclaw.json.

Administrator Configuration

Full access, no sandbox restrictions:

{
  agents: {
    defaults: {
      workspace: "~/.openclaw/workspace",
    },
    list: [
      {
        id: "main",
        // Administrator: no sandbox, all tools allowed
        sandbox: { mode: "off" },
      },
    ],
  },
  bindings: [
    // Route admin sessions to main agent without sandbox
    { agentId: "main", match: { session: { regex: "alice$" } } },
  ],
}

Guest Configuration

Sandboxed session with isolated workspace. Guest can read/write/execute in their own directory only:

{
  agents: {
    defaults: {
      workspace: "~/.openclaw/workspace",
    },
    list: [
      {
        id: "main",
        // Guest: sandbox enabled, isolated directory
        sandbox: {
          mode: "all",
          scope: "session",
          workspaceAccess: "none",  // Don't mount main workspace
          docker: {
            binds: [
              // Mount guest's own directory as /workspace
              "~/.openclaw/workspace/guests/bob:/workspace:rw"
            ]
          }
        },
        tools: {
          allow: ["read", "write", "edit", "exec", "process"],
          deny: ["browser", "canvas", "nodes", "cron", "gateway"],
        },
      },
    ],
  },
  bindings: [
    // Route guest sessions to sandboxed agent
    { agentId: "main", match: { session: { regex: "bob$" } } },
  ],
}

Directory Setup:

mkdir -p ~/.openclaw/workspace/guests/bob

Notes:

  • Guest sees /workspace as their root (isolated from main workspace)
  • Can read/write/execute freely within their directory
  • Cannot access USER.md, FRIENDS/, RELATIONS/, or other guests' data

Configuration Options

Sandbox:

  • mode: "off" | "all" — Disable or enable sandbox
  • scope: "session" — One container per user session
  • workspaceAccess: "none" | "ro" | "rw" — Workspace file access

Tools:

  • allow: Array of permitted tool names
  • deny: Array of prohibited tool names (overrides allow)

Routing:

  • bindings[].match.session.regex: Match session key pattern (e.g., alice$ matches sessions ending with "alice")

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

70.99%
按下载量换算5,886

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

未展示

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills