← 返回 Skills 市场
536
总下载
0
收藏
3
当前安装
2
版本数
在 OpenClaw 中安装
/install health-check
功能描述
每日安全检查。检查 OpenClaw Gateway、磁盘空间、内存使用等系统健康状态。触发时机：cron 定时任务或手动调用。
使用说明 (SKILL.md)
Health Check
每日系统安全检查，确保 OpenClaw 和环境正常运行。
核心流程
- 读取 references/spec.md 获取详细规范
- 检查 Gateway 运行状态
- 检查磁盘空间
- 检查内存使用
- 检查最近日志有无错误
- 生成报告并发送
触发时机
- cron 定时任务（建议每日）
- 用户明确要求时
投递规则（必须）
完成报告后，通过消息工具发送。
- 渠道：feishu
- 目标：\x3C飞书群ID或用户ID> 如果报告超过 3800 字符，分成多条消息发送。 每条消息必须语义完整（不断开 URL 或格式）。 如果发送失败，重试一次。如果仍然失败，输出错误——永远不要静默退出。
输出
- 报告位置：
data/exec-logs/health-check/YYYY-MM-DD.md - 消息推送到飞书群
安全使用建议
Before installing or enabling this skill, confirm the following: 1) Ensure the host has the 'openclaw' CLI available (or update the manifest to declare it). 2) Decide exactly which log files will be inspected and restrict the checks to those paths to avoid leaking sensitive data; update SKILL.md with explicit log paths and filters. 3) Provide documented Feishu delivery credentials (webhook or API token) in the skill manifest or agent config; do not rely on unspecified/global secrets. 4) Review the report contents and test in an isolated environment so no production secrets are accidentally sent to chat. 5) Ensure the agent process has the minimum filesystem/network permissions required and that data/exec-logs is a suitable location. If you cannot confirm these points, treat the skill as potentially exfiltrating sensitive logs and avoid enabling it until the manifest and instructions are corrected.
功能分析
Type: OpenClaw Skill
Name: health-check
Version: 1.0.1
The health-check skill bundle is a standard system monitoring tool designed to verify the status of the OpenClaw Gateway, disk space, and memory usage. The instructions in SKILL.md and references/spec.md describe legitimate administrative tasks, using standard system commands (df, free) and reporting results via Feishu. No evidence of data exfiltration, malicious execution, or prompt injection was found.
能力评估
Purpose & Capability
The described checks (gateway status, disk, memory, recent logs, generate report) are coherent with a 'Health Check' skill. However the SKILL.md expects the 'openclaw' CLI and access to system logs and to a Feishu messaging channel, while the manifest declares no required binaries, env vars, or config paths — this is an inconsistency (the skill will require system tooling and messaging credentials to function).
Instruction Scope
The runtime instructions instruct the agent to run shell commands (openclaw gateway status, df -h, free -h) and to 'check logs' but do not specify which log files or safe filters. They also mandate writing reports to data/exec-logs/... and sending the full report to Feishu. The combination lets the agent read arbitrary local logs and send their contents externally; the lack of explicit log paths and data filtering is a scope creep / data-exfiltration risk if sensitive logs are present.
Install Mechanism
This is instruction-only with no install steps or downloaded code, so nothing is written to disk by an installer. That minimizes install-time risks. The risk surface is runtime (shell commands and messaging).
Credentials
The instructions require sending messages to Feishu (a network endpoint) and likely need credentials or a webhook, but the skill declares no required environment variables or primary credential. That omission is problematic: either the agent must already have Feishu credentials elsewhere (not documented), or the skill will fail or implicitly rely on unspecified secrets. Also the skill reads system logs (sensitive data) yet provides no guidance on which credentials/permissions are needed to access them safely.
Persistence & Privilege
always is false and the skill does not request persistent presence or modify other skills' configuration. Writing reports to data/exec-logs is an expected behavior for a health-check tool, but users should confirm the directory is appropriate and writable.
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 health-check - 安装完成后，直接呼叫该 Skill 的名称或使用
/health-check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
v1.0.1
- 更新投递规则，将目标 Feishu 群ID 标记为占位符 <飞书群ID或用户ID>，提高通用性和适配性
- 其余文档内容保持不变
v1.0.0
Initial release of the health-check skill:
- Provides daily system health checks for OpenClaw Gateway, disk space, memory usage, and recent logs.
- Can be triggered via cron schedule or manual request.
- Generates reports stored in data/exec-logs/health-check/YYYY-MM-DD.md.
- Sends health reports to a specified Feishu group, with automatic message splitting for long reports.
- Includes error handling and retry logic for message delivery.
元数据
常见问题
Health Check 是什么？
每日安全检查。检查 OpenClaw Gateway、磁盘空间、内存使用等系统健康状态。触发时机：cron 定时任务或手动调用。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 536 次。
如何安装 Health Check？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install health-check」即可一键安装，无需额外配置。
Health Check 是免费的吗？
是的，Health Check 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Health Check 支持哪些平台？
Health Check 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 Health Check？
由 AxelHu（@axelhu）开发并维护，当前版本 v1.0.1。
推荐 Skills