Menu
大龙系统巡检 SOP - 低打扰式定期检查 OpenClaw 运行时状态、Gateway、Channel、Tasks 与错误日志。只整理值得行动的问题，格式输出「结论 / 原因 / 建议」。由「大龙-系统巡检」cron 任务触发。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Build high-performing OpenClaw agents end-to-end. Use when you want to design a new agent (persona + operating rules) and generate the required OpenClaw workspace files (SOUL.md, IDENTITY.md, AGENTS.md, USER.md, HEARTBEAT.md, optional MEMORY.md + memory/YYYY-MM-DD.md). Also use to iterate on an existing agent's behavior, guardrails, autonomy model, heartbeat plan, and skill roster.
brain v1.1.7 用户版（免费）：让AI Agent拥有类大脑决策架构。置信度触发、双保险记忆、经验胶囊复用。开箱即用，3片段内存池，2并发上限。
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4) Establishing review and quality gates, (5) Managing async communication and artifact sharing between agents.
Recommend curated prompts from a 10,000+ real-world image generation prompt library. Works with ANY AI image model — Nano Banana Pro, Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E 3, Flux, Stable Diffusion, and more. Use this skill when users want to: - Find proven image generation prompts (any model) - Get prompt inspiration for portraits, products, social media, posters, etc. - Create illustrations for articles, videos, podcasts, or marketing content - Browse categorized prompt templates with sample images - Translate and understand prompt techniques
A股量化数据分析工具，基于AkShare库获取A股行情、财务数据、板块信息等。用于回答关于A股股票查询、行情数据、财务分析、选股等问题。
Personalized news briefings from your chosen sources, delivered morning or evening, with voice option and smart filtering.
| name | system-inspection |
| description | 大龙系统巡检 SOP - 低打扰式定期检查 OpenClaw 运行时状态、Gateway、Channel、Tasks 与错误日志。只整理值得行动的问题，格式输出「结论 / 原因 / 建议」。由「大龙-系统巡检」cron 任务触发。 |
| compatibility | openclaw |
| license | MIT |
| source | https://github.com/1yihui/YiHui |
| tags | ["system-inspection","monitoring","diagnostics"] |
tags:
大龙-系统巡检 cron 任务（建议每 6–12 小时执行一次）openclaw status
重点看：
127.0.0.1 本地 / 0.0.0.0 暴露）对每个已配置的 Channel 做探测：
openclaw gateway logs --lines 50 2>&1 | grep -iE "error|warn|fail|400|500|9999"
重点关注：
openclaw cron list
检查：
openclaw status --deep
核对：
| 异常类型 | 判断条件 | 严重程度 |
|---|---|---|
| Gateway 不在 Running | openclaw status 非 running | 🔴 高 |
| Feishu API 权限错误 | 日志出现 99991672 或 contact.* 400 | 🔴 高 |
| Cron 任务失败 | cron runs 显示 error exit | 🟡 中 |
| 配置漂移 | 实际配置与预期不符 | 🟡 中 |
| 磁盘 / 内存紧张 | 经验判断（日志写入慢、内存占用异常） | 🟡 中 |
| 轻微 warn | 不影响功能 | 🟢 低（可忽略） |
contact:contact.* scopeopenclaw gateway restartopenclaw gateway logsopenclaw cron runs <job-id> 看最近一次执行详情每个巡检项输出结论，格式：
[项] 结论 / 原因（如果有）/ 建议（如果有）
如果所有项均正常或无值得打扰的事项，输出 NO_REPLY（不发消息，低打扰）。
每次巡检任务完成后，必须写两处：
~/agents/dalong/workspace/memory.md：
## YYYY-MM-DD 巡检结论
- 关键状态：...
- 发现的问题：...
- 下次需关注：...
memory/YYYY-MM-DD.md：
## 大龙巡检 YYYY-MM-DD
- 关键状态：...
- 发现的问题：...
- 下次需关注：...
两处都必须写。自己的 memory.md 积累大龙自己的经验；主控的 memory/ 方便小语召回全局信息。