Token导航 LogoToken导航TokenDH.com
开发敏感数据github未标认证来源可访问许可证需确认审计异常

openclaw-self-healingOpenClaw self healing 文档

Agent Skill

openclaw-self-healing 用于记录任务执行中的错误、用户纠正、经验和能力缺口,适合在 Codex、Claude、Cursor、Gemini CLI 中希望让 Agent 持续沉淀问题、修正和最佳实践时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

20,016

周安装

834

GitHub Stars

37

下载量

6,672
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:openclaw-self-healing(OpenClaw self healing 文档)
来源仓库:https://github.com/ramsbaby/openclaw-self-healing
仓库路径:skills/openclaw-self-healing
安装命令:
npx skills add https://github.com/ramsbaby/openclaw-self-healing --skill openclaw-self-healing
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/ramsbaby/openclaw-self-healing --skill openclaw-self-healing

简介

OpenClaw Gateway 的 4 层自主自愈系统,以 Claude Code 作为 AI 急救医生。

  • 通过看门狗监控、带重试的 HTTP 运行状况检查、通过 Claude Code 进行人工智能驱动的诊断以及用于人为干预的 Discord/Telegram 警报来升级
  • 捕获持续学习文档(症状到解决方案映射)和推理日志,以进行可解释的 AI 决策
  • 包括用于跟踪事件恢复成功率、时间和趋势的指标仪表板
  • 需要 tmux、Claude Code CLI 和 jq;与 macOS LaunchAgent 集成以实现连续后台操作

SKILL.md

OpenClaw Self-Healing System

"The system that heals itself — or calls for help when it can't."

A 4-tier autonomous self-healing system for OpenClaw Gateway.

Architecture

Level 1: Watchdog (180s)     → Process monitoring (OpenClaw built-in)
Level 2: Health Check (300s) → HTTP 200 + 3 retries
Level 3: Claude Recovery     → 30min AI-powered diagnosis 🧠
Level 4: Discord Alert       → Human escalation

What's Special (v2.0)

  • World's first Claude Code as Level 3 emergency doctor
  • Persistent Learning - Automatic recovery documentation (symptom → cause → solution → prevention)
  • Reasoning Logs - Explainable AI decision-making process
  • Multi-Channel Alerts - Discord + Telegram support
  • Metrics Dashboard - Success rate, recovery time, trending analysis
  • Production-tested (verified recovery Feb 5-6, 2026)
  • macOS LaunchAgent integration

Quick Setup

1. Install Dependencies

brew install tmux
npm install -g @anthropic-ai/claude-code

2. Configure Environment

# Copy template to OpenClaw config directory
cp .env.example ~/.openclaw/.env

# Edit and add your Discord webhook (optional)
nano ~/.openclaw/.env

3. Install Scripts

# Copy scripts
cp scripts/*.sh ~/openclaw/scripts/
chmod +x ~/openclaw/scripts/*.sh

# Install LaunchAgent
cp launchagent/com.openclaw.healthcheck.plist ~/Library/LaunchAgents/
launchctl load ~/Library/LaunchAgents/com.openclaw.healthcheck.plist

4. Verify

# Check Health Check is running
launchctl list | grep openclaw.healthcheck

# View logs
tail -f ~/openclaw/memory/healthcheck-$(date +%Y-%m-%d).log

Scripts

ScriptLevelDescription
gateway-healthcheck.sh2HTTP 200 check + 3 retries + escalation
emergency-recovery.sh3Claude Code PTY session for AI diagnosis (v1)
emergency-recovery-v2.sh3Enhanced with learning + reasoning logs (v2) ⭐
emergency-recovery-monitor.sh4Discord/Telegram notification on failure
metrics-dashboard.sh-Visualize recovery statistics (NEW)

Configuration

All settings via environment variables in ~/.openclaw/.env:

VariableDefaultDescription
DISCORD_WEBHOOK_URL(none)Discord webhook for alerts
OPENCLAW_GATEWAY_URLhttp://localhost:18789/Gateway health check URL
HEALTH_CHECK_MAX_RETRIES3Restart attempts before escalation
EMERGENCY_RECOVERY_TIMEOUT1800Claude recovery timeout (30 min)

Testing

Test Level 2 (Health Check)

# Run manually
bash ~/openclaw/scripts/gateway-healthcheck.sh

# Expected output:
# ✅ Gateway healthy

Test Level 3 (Claude Recovery)

# Inject a config error (backup first!)
cp ~/.openclaw/openclaw.json ~/.openclaw/openclaw.json.bak

# Wait for Health Check to detect and escalate (~8 min)
tail -f ~/openclaw/memory/emergency-recovery-*.log

Links

License

MIT License - do whatever you want with it.

Built by @ramsbaby + Jarvis 🦞

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.68%
按下载量换算2,447

Claude

30.34%
按下载量换算2,024

Cursor

18.72%
按下载量换算1,249

Gemini CLI

9.96%
按下载量换算665

安全审计

Gen Agent Trust Hub

未通过

Socket

未通过

Snyk

可疑

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills