← 返回 Skills 市场
686
总下载
2
收藏
25
当前安装
1
版本数
在 OpenClaw 中安装
/install openclaw-workspace
功能描述
Audit and improve OpenClaw workspaces across SOUL, AGENTS, TOOLS, USER, MEMORY, and skills for persona tuning, proactive behavior, recall, and workflow fit....
安全使用建议
This skill is coherent for auditing an OpenClaw workspace, but it will read your workspace files and conversation memory to form recommendations — so only run it if you are comfortable the agent accessing those files. If your workspace or memory contains sensitive secrets, either remove or redact them first, or ask the agent to perform a high-level audit that avoids reading raw files. Because this is instruction-only (no downloads or credentials requested), the main risk is data exposure from the agent reading project and memory files, not from the skill installing or exfiltrating new code. If you want tighter control, restrict the agent's file/memory access or request the audit be done on a sanitized copy of the workspace.
功能分析
Type: OpenClaw Skill
Name: openclaw-workspace
Version: 1.0.0
The OpenClaw Workspace skill is a configuration management tool designed to help the agent audit and refine its own operational files (e.g., SOUL.md, AGENTS.md, MEMORY.md). The instructions in SKILL.md focus on organizational logic, personality consistency, and memory optimization, emphasizing user review and explicit diffs rather than hidden changes. There are no indicators of data exfiltration, malicious execution, or prompt injection attacks.
能力评估
Purpose & Capability
The name/description (workspace audit and improvement) matches the instructions: the SKILL.md explicitly directs the agent to inspect SOUL.md, AGENTS.md, TOOLS.md, MEMORY.md, memory/*.md, skills/, and related workspace files. No unrelated binaries, credentials, or install steps are requested.
Instruction Scope
Instructions intentionally authorize reading workspace files and prior conversation memory (memory_search on MEMORY.md and memory/*.md) to form audit evidence. This is coherent for an audit skill, but it grants broad discretionary access to the agent's workspace and conversation history — expect the skill to examine many internal files when invoked.
Install Mechanism
No install spec and no code files are present. Being instruction-only means nothing is downloaded or written to disk by the skill itself, which reduces install-time risk.
Credentials
The skill declares no required environment variables, credentials, or config paths. The lack of external credential requests is proportionate to the declared purpose.
Persistence & Privilege
always is false and disable-model-invocation is false (normal). The skill does not request persistent system-wide privileges or modifications to other skills. Autonomous invocation is allowed but not unusually privileged.
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 - 安装完成后，直接呼叫该 Skill 的名称或使用
/openclaw-workspace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
v1.0.0
Clarified activation wording so the skill is picked more reliably for broad workspace improvement requests.
元数据
常见问题
OpenClaw Workspace 是什么？
Audit and improve OpenClaw workspaces across SOUL, AGENTS, TOOLS, USER, MEMORY, and skills for persona tuning, proactive behavior, recall, and workflow fit.... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 686 次。
如何安装 OpenClaw Workspace？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openclaw-workspace」即可一键安装，无需额外配置。
OpenClaw Workspace 是免费的吗？
是的，OpenClaw Workspace 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
OpenClaw Workspace 支持哪些平台？
OpenClaw Workspace 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（linux, darwin, win32）。
谁开发了 OpenClaw Workspace？
由 Iván（@ivangdavila）开发并维护，当前版本 v1.0.0。
推荐 Skills