虾尊记忆自动管理器

记忆自动主动管理：每15分钟自动扫描对话，发现重要信息自动写入每日memory。解决"主动感知靠自觉经常失效"的问题。 使用场景： - 每次对话结束后自动检查是否有遗漏的重要信息 - 自动记录完成的任务、决策、教训、配置变更 - 增量扫描对话历史，不遗漏不重复 - user + assistant 消息双读，确保...

This skill is coherent with its stated goal, but it persistently reads transcripts and writes user/assistant content to disk. Before installing: (1) review whether you want all transcripts (including potential secrets) saved into ~/.openclaw/workspace/memory; (2) consider file permissions or encryption for that directory; (3) check the cron deliver settings (Feishu/channel) to avoid accidentally posting sensitive summaries to external channels; (4) test the script manually (python3 ~/.openclaw/scripts/memory-scan.py) and inspect the produced files to confirm formatting and redaction behavior; (5) if you need limits, add filters to memory-scan.py to redact tokens/credentials or to skip messages containing sensitive markers. The installer’s sed step references a hardcoded filename GUID that appears unnecessary — verify transcript path configuration after install. Autonomous invocation is allowed by default but is not combined with other red flags here; still monitor first few runs.

Type: OpenClaw Skill Name: xiazun-memory-auto Version: 1.0.0 The skill is a utility for automated memory management that scans OpenClaw session transcripts and updates daily work logs. It uses a Python script (memory-scan.py) to perform incremental scans of chat history and sets up cron jobs to trigger the AI agent to summarize new information. The code and instructions in SKILL.md and setup.sh are consistent with the stated purpose and do not exhibit signs of data exfiltration, malicious execution, or unauthorized persistence.