← 返回 Skills 市场
dickwu

Multi Workplace

作者 farmerwu · GitHub ↗ · v0.4.0
cross-platform ⚠ suspicious
748
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install multi-workplace
功能描述
Manage multiple workplaces (project directories) with multi-agent orchestration, isolated memory, and inter-agent communication. Use when the user mentions:...
安全使用建议
This skill appears to do what it says, but it operates on and modifies local files and uses user-editable Markdown to build system prompts for spawned agents — a real prompt-injection and file-modification risk. Before installing or running it: 1) review the included scripts (init_workplace.sh, build.sh) and the Rust server source to confirm they do what you expect; 2) back up CLAUDE.md, opencode.jsonc, and any important project files in case the skill overwrites them; 3) inspect any .workplace/agents/*.md files (or any workplace skills pulled from git) before allowing them to run, since their contents become system prompts for subagents; 4) prefer building and running the Rust server yourself rather than running an untrusted prebuilt binary; 5) only install from a trusted source and consider limiting write access (or running in a sandbox) if you must evaluate it in an untrusted environment. If you want, I can point out the exact lines in the scripts and SKILL.md that perform file writes and compose system prompts so you can review them more easily.
功能分析
Type: OpenClaw Skill Name: multi-workplace Version: 0.4.0 The 'multi-workplace' skill is designed for extensive local system interaction, including broad file system access (reading/writing to `~/.openclaw/workspace/.workplaces/` and project-specific `.workplace/` directories), execution of shell scripts (`scripts/init_workplace.sh`, `scripts/scan_workplaces.sh`), and running a local Rust binary (`workplace-server`). While these high-privilege operations are central to the skill's stated purpose, the reliance on shell scripts and recursive calls introduces a significant attack surface for potential vulnerabilities (e.g., shell injection, path traversal) if user-provided inputs are not perfectly sanitized. No clear evidence of intentional malicious behavior such as data exfiltration, unauthorized network communication, or covert persistence mechanisms was found.
能力评估
Purpose & Capability
Name/description align with the files and scripts: the skill scans repos, creates per-project .workplace/ directories, runs a Rust file-watcher, spawns agents, and syncs IDE context. The requested artifacts (registry in ~/.openclaw/workspace, per-project .workplace/) are consistent with the advertised functionality.
Instruction Scope
The SKILL.md instructs the agent to read many local files (README.md and other *.md, structure.json, config.json), to use agent .md files as the basis for system prompts, to write/modify project-root files (CLAUDE.md, opencode.jsonc, .cursor rules), and to update ~/.openclaw/workspace/registry.json and current.json. Using user-editable agent definitions and arbitrary project files to build system prompts is a prompt-injection risk; writing IDE/config files can clobber user content if not carefully handled.
Install Mechanism
No install spec (instruction-only), lowering install risk. The package includes build scripts and Rust source for a local file-watcher server; building runs locally and copies the binary into assets/bin. There are no network downloads or opaque external installers in the package. Pre-built binaries are mentioned but not bundled in the listed manifest — build-from-source is provided.
Credentials
The skill asks for no environment variables or external credentials. It does, however, read/write the user's home (~/.openclaw/workspace/) and project directories and expects access to git, jq, and optionally Rust toolchain. It also writes to 'supermemory' via containerTag (platform memory) — appropriate for multi-workplace memory but worth noting as it stores project summaries in platform memory.
Persistence & Privilege
always:false (good). The skill spawns persistent components (kernel agent, background Rust watcher) by design and updates process-status.json and registry files. This is coherent with its purpose but increases the blast radius because these background processes read and act on local files continuously.
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 multi-workplace
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /multi-workplace 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
v0.4.0
Hierarchical /workplace navigation: parent→child drill-down with inline buttons, parent:child colon syntax for direct switching, auto-init parent folders (no .git) with recursive child init and cross-linking
v0.3.0
Telegram/Discord inline button UI for workspace switching, agent control, deploy env selector
v0.2.0
Fix: full-tree.md now workspace-level only (name/uuid/path for self, parent, linked, siblings). No more file tree dumps.
v0.1.0
Initial release: multi-agent workspace management with Rust file-watcher, IDE sync (Cursor/Claude Code/OpenCode), Swarm orchestration, isolated memory, export/import
元数据
Slug multi-workplace
版本 0.4.0
许可证
累计安装 0
当前安装数 0
历史版本数 4
常见问题

Multi Workplace 是什么?

Manage multiple workplaces (project directories) with multi-agent orchestration, isolated memory, and inter-agent communication. Use when the user mentions:... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 748 次。

如何安装 Multi Workplace?

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

Multi Workplace 是免费的吗?

是的,Multi Workplace 完全免费(开源免费),可自由下载、安装和使用。

Multi Workplace 支持哪些平台?

Multi Workplace 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 Multi Workplace?

由 farmerwu(@dickwu)开发并维护,当前版本 v0.4.0。

💬 留言讨论