gateway-watchdog-xiaoxi/SKILL.md
# SKILL.md - OpenClaw Gateway Watchdog > 让你的 OpenClaw Gateway 7/24 稳定运行 ## 触发语 - "帮我 7/24 运行" - "让 Gateway 持续运行" - "设置 watchdog" - "保持 Gateway 运行" ## 做什么 1. 检查是否有 `gateway_watchdog.py`,如果没有则从 GitHub 下载 2. 执行 `python gateway_watchdog.py start` 3. 反馈结果 ## 快速开始 ```bash # 一键安装+启动 python install.py # 或手动 python gateway_watchdog.py start python gateway_watchdog.py status python gateway_watchdog.py restart python gateway_watchdog.py stop ``` ## 输出示例 ``` 用户: 帮我7/24运行 -> 📥 正在下载 gateway_watchdo
npx skillsauth add adminlove520/xiaoxi-skills gateway-watchdog-xiaoxiInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
让你的 OpenClaw Gateway 7/24 稳定运行
gateway_watchdog.py,如果没有则从 GitHub 下载python gateway_watchdog.py start# 一键安装+启动
python install.py
# 或手动
python gateway_watchdog.py start
python gateway_watchdog.py status
python gateway_watchdog.py restart
python gateway_watchdog.py stop
用户: 帮我7/24运行
-> 📥 正在下载 gateway_watchdog.py...
-> ✅ 下载完成
-> 🚀 启动 Gateway Watchdog...
-> ✅ Gateway Watchdog 已启动 (PID: 12345)
-> ✅ 完成!Gateway 将 7/24 运行
| 命令 | 说明 |
|------|------|
| python install.py | 一键安装并启动 |
| python gateway_watchdog.py start | 启动 watchdog |
| python gateway_watchdog.py status | 查看状态 |
| python gateway_watchdog.py restart | 重启 Gateway |
| python gateway_watchdog.py stop | 停止 watchdog |
不要用 OpenClaw 自己的 cron 监控 Gateway。 Gateway 挂了,cron job 根本收不到 wake event,形成死锁。
外部 watchdog:
🦞 小溪的作品
data-ai
Spaced-repetition flashcard system. Create cards from facts or text, chat with flashcards using free-text answers graded by the agent, generate quizzes from YouTube transcripts, review due cards with adaptive scheduling, and export/import decks as CSV.
development
Canvas LMS integration — fetch enrolled courses and assignments using API token authentication.
development
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
devops
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.