← 返回 Skills 市场
173
总下载
1
收藏
0
当前安装
6
版本数
在 OpenClaw 中安装
/install openclaw-workspace-governance
功能描述
🚨【高危预警 / IMPORTANT WARNING】这不是工具Skill，而是系统级架构升级！部署前务必备份工作区！This is NOT a standard tool skill, but a system-level architecture upgrade! Backup workspace befo...
安全使用建议
This package appears to be a coherent governance playbook with useful docs and three diagnostic scripts. Before installing or running it: 1) Backup your workspace (the package repeatedly warns to do this). 2) Review the contents of the three scripts (scripts/freshness-check.py, scripts/semantic-runtime-check.sh, scripts/doc-status-scan.py) to confirm they only read and report (not delete, modify critical files, or send data externally). 3) Run the scripts first in a sandbox or non-production copy of your workspace to observe behavior and outputs. 4) Check for any network calls, unexpected file writes, or subprocess invocations inside the scripts; if you see calls that contact external hosts, require credentials, or write to system locations, investigate further. 5) If you will let an agent run these autonomously, ensure human-in-the-loop approvals for any change actions and limit the agent’s filesystem and network permissions. If you can paste the three script sources here, I can review them for specific risky operations (network calls, credentials use, file writes, or obfuscated behavior) to raise confidence.
功能分析
Type: OpenClaw Skill
Name: openclaw-workspace-governance
Version: 1.0.9
This skill bundle is a comprehensive governance framework designed to manage and structure complex OpenClaw workspaces. It focuses on implementing security and reliability best practices, such as 'Separation of Duties' via a multi-agent architecture (Coordinator, Implementer, Reviewer, Policy Auditor) and 'Source of Truth' layering to prevent data drift. The included scripts (e.g., `freshness-check.py`, `doc-status-scan.py`, and `semantic-runtime-check.sh`) are utility tools for monitoring file metadata and search engine status, performing standard filesystem operations consistent with the stated purpose. No evidence of malicious intent, data exfiltration, or harmful prompt injection was found; the instructions actually serve to increase the agent's operational rigor and safety.
能力评估
Purpose & Capability
Name/description (workspace governance / system-level upgrade) match the contents: extensive governance playbook, references, examples, and three helper scripts for freshness, semantic-runtime, and doc-status checks. There are no unrelated env vars, binaries, or install steps declared — the requested footprint is proportionate to a governance tool.
Instruction Scope
SKILL.md is explicit about being a system-level change and repeatedly warns to backup and to avoid blind full-automation in production. It references and recommends running local diagnostic scripts (scripts/freshness-check.py, scripts/semantic-runtime-check.sh, scripts/doc-status-scan.py). That scope (reading workspace docs, indices, and running local checks) is coherent with the stated purpose, but these scripts are capable of accessing workspace files — you should inspect them to confirm they do only read/diagnose and do not modify or transmit secrets.
Install Mechanism
There is no install spec; this is instruction + bundled scripts. No network-based installers or archive downloads are declared. This lower-risk approach is consistent with a governance playbook.
Credentials
The package declares no required environment variables, credentials, or config paths. That is proportionate: a governance/reference skill typically needs read access to workspace files but doesn't require external credentials. If you run the scripts, consider what runtime permissions the agent/process has (file-system, index access).
Persistence & Privilege
Flags: always:false and model invocation is allowed (default). The skill does not request permanent presence or elevated platform privileges and does not declare modifications to other skills or global agent configuration. The design assumes supervised use (the README/SKILL.md repeatedly warns to back up and avoid full automation in prod).
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install openclaw-workspace-governance - 安装完成后，直接呼叫该 Skill 的名称或使用
/openclaw-workspace-governance触发 - 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
v1.0.9
Moved system capabilities to the very beginning of the README.
v1.0.8
Added detailed system capabilities and features matching the Feishu documentation.
v1.0.7
Added critical warning about system-level impact and backup requirement.
v1.0.6
Repackaged: Full Chinese document followed by full English document.
v1.0.5
Version 1.0.5
- Updated SKILL.md content with clarifications and possible incremental modifications.
- No code or functionality changes; documentation only.
v1.0.4
- Added detailed bilingual (Chinese/English) documentation and guidance to SKILL.md, explaining governance concepts for complex OpenClaw workspaces.
- Clarified intended use cases, workflow steps, and non-goals for workspace governance, targeting advanced users handling real-world complexity.
- Introduced recommended roles (Coordinator, Implementer, Reviewer, Policy Auditor, Consensus Peer) and deployment patterns for multi-agent governance.
- Outlined core concepts such as drift types, source-of-truth layering, query class retrieval, document freshness, and phase closure.
- Provided actionable steps for diagnosing drift, assigning governance responsibilities, and maintaining workspace clarity and control.
- Stated boundaries of the skill: not an automated orchestrator in v1, and not intended for automatic decision-making or universal document retention.
元数据
常见问题
OpenClaw Workspace Governance 是什么？
🚨【高危预警 / IMPORTANT WARNING】这不是工具Skill，而是系统级架构升级！部署前务必备份工作区！This is NOT a standard tool skill, but a system-level architecture upgrade! Backup workspace befo... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 173 次。
如何安装 OpenClaw Workspace Governance？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openclaw-workspace-governance」即可一键安装，无需额外配置。
OpenClaw Workspace Governance 是免费的吗？
是的，OpenClaw Workspace Governance 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
OpenClaw Workspace Governance 支持哪些平台？
OpenClaw Workspace Governance 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 OpenClaw Workspace Governance？
由 vbox（@heishiqing）开发并维护，当前版本 v1.0.9。
推荐 Skills