发现和使用优秀的技能扩展
抓取并分析OpenClaw JSONL会话日志,以重建和回填智能体内存文件。适用于以下情况:(1)模型切换后内存显示不完整,(2)验证内存覆盖范围,(3)重建丢失的内存,(4)通过cron/心跳进行自动化每日内存同步。支持简单提取和基于LLM的叙述性摘要,并具有自动密钥清理功能。
Scrape and analyze OpenClaw JSONL session logs to reconstruct and backfill agent memory files. Use when: (1) Memory appears incomplete after model switches, (2) Verifying memory coverage, (3) Reconstructing lost memory, (4) Automated daily memory sync via cron/heartbeat. Supports simple extraction and LLM-based narrative summaries with automatic secret sanitization.