System safety and control-plane skill that prevents agent deadlocks and freezes. Provides non-LLM control commands to inspect task state, flush message queues, cancel long-running work, and recover safely without restarting the container. Use when implementing or operating long-running tasks, sub-agents, benchmarks, background monitors (e.g., Moltbook, PNR checks), or when the system becomes unresponsive and needs immediate recovery controls.
数据来源：ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一：命令行安装（推荐）
推荐（无需提前安装 clawhub）
npx clawhub@latest --dir ~/.claude/skills install error-guard或使用 clawhub CLI（需提前安装）
clawhub --dir ~/.claude/skills install error-guard⚠️ 需要 Node.js 18+，没有 Node？请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二：手动下载安装（无需 Node）
下载 ZIP，解压后将文件夹放到以下路径，重启 Agent 即可：
安装路径
~/.claude/skills/error-guard/💡解压后将文件夹放到上方路径，重启 Agent 即可生效
--- name: error-guard description: > System safety and control-plane skill that prevents agent deadlocks and freezes. Provides non-LLM control commands to inspect task state, flush message queues, cancel long-running work, and recover safely without restarting the container. Use when implementing or operating long-running tasks, sub-agents, benchmarks, background monitors (e.g., Moltbook, PNR checks), or when the system becomes unresponsive and needs immediate recovery controls. ---
⚠️ System‑level skill (Advanced users)
This skill defines the control‑plane safety primitives for OpenClaw. It is intentionally minimal, non‑blocking, and designed to prevent agent freezes, deadlocks, and unrecoverable states when running long‑lived or high‑risk workloads.
> Warning: This skill operates at the agent control‑plane level. > It should be installed only by users who understand OpenClaw’s execution model and are running workloads that can block, hang, or run for extended periods.
Report current system health and task registry state.
Returns:
Constraints:
Emergency stop.
Immediately:
Constraints:
Safe recovery sequence.
Steps:
/flushThis skill is the last line of defense. Keep it small, fast, and reliable.
安装 Error Guard — Control‑Plane Safety 后，可以对 AI 说这些话来触发它
Help me get started with Error Guard — Control‑Plane Safety
Explains what Error Guard — Control‑Plane Safety does, walks through the setup, and runs a quick demo based on your current project
Use Error Guard — Control‑Plane Safety to system safety and control-plane skill that prevents agent deadlocks...
Invokes Error Guard — Control‑Plane Safety with the right parameters and returns the result directly in the conversation
What can I do with Error Guard — Control‑Plane Safety in my developer & devops workflow?
Lists the top use cases for Error Guard — Control‑Plane Safety, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/error-guard/ 目录（个人级，所有项目可用），或 .claude/skills/error-guard/（项目级）。重启 AI 客户端后，用 /error-guard 主动调用，或让 AI 根据上下文自动发现并使用。
Error Guard — Control‑Plane Safety 支持 Claude、Cursor、OpenClaw，可与这些 AI 平台无缝集成，扩展其能力。
Error Guard — Control‑Plane Safety 可免费安装使用。请查阅仓库了解许可证信息。
System safety and control-plane skill that prevents agent deadlocks and freezes. Provides non-LLM control commands to inspect task state, flush message queues, cancel long-running work, and recover safely without restarting the container. Use when implementing or operating long-running tasks, sub-agents, benchmarks, background monitors (e.g., Moltbook, PNR checks), or when the system becomes unresponsive and needs immediate recovery controls.
Automate my developer & devops tasks using Error Guard — Control‑Plane Safety
Identifies repetitive steps in your workflow and sets up Error Guard — Control‑Plane Safety to handle them automatically
Error Guard — Control‑Plane Safety 属于「Developer & DevOps」分类，该分类的技能帮助 AI 智能体在此领域执行专业任务。