Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Automatically identify, merge, and clean duplicate or outdated entries in MEMORY.md to maintain concise, organized, and up-to-date information.
Automatically identify, merge, and clean duplicate or outdated entries in MEMORY.md to maintain concise, organized, and up-to-date information.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
保持 MEMORY.md 清洁,避免信息冗余
随着时间推移,MEMORY.md 会出现: 重复信息 — 同一事件多次记录 过时信息 — 已完成的任务仍标记为进行中 冗余描述 — 同一项目多处描述 碎片化 — 相关信息散落各处
function similarity(text1, text2) { // Jaccard 相似度 const words1 = new Set(text1.toLowerCase().split(/\s+/)); const words2 = new Set(text2.toLowerCase().split(/\s+/)); const intersection = new Set([...words1].filter(x => words2.has(x))); const union = new Set([...words1, ...words2]); return intersection.size / union.size; }
相似度 >0.8 — 完全重复,删除 相似度 0.5-0.8 — 部分重复,合并 相似度 <0.5 — 不同内容,保留
保留最新时间戳 合并所有唯一信息 保留最高优先级标记
# 运行去重 node skills/memory-dedup/dedup.mjs # 预览(不修改文件) node skills/memory-dedup/dedup.mjs --dry-run # 备份后去重 node skills/memory-dedup/dedup.mjs --backup
# 每周日凌晨 2 点自动去重 openclaw cron add --name "memory-dedup-weekly" \ --cron "0 2 * * 0" --tz "Asia/Shanghai" \ --session isolated --agent main \ --message "运行记忆去重,清理 MEMORY.md 冗余信息"
自动备份 — 去重前备份原文件 人工审核 — 生成 diff 供审核 可回滚 — 保留最近 10 次备份 白名单 — 某些关键信息不去重
文件大小减少 30-50% 检索速度提升 2-3 倍 信息密度提升 40% 维护成本降低 60%
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Largest current source with strong distribution and engagement signals.