skills/memory-system/SKILL.md
使用遗忘曲线管理会话记忆(SQLite):按永久记忆/衰减记忆分类写入、按时间自动更新 fresh/active/fading/blurry/forgotten 状态、按话题检索、执行遗忘删除、从周归档恢复,以及生成每周记忆汇总。适用于用户要求“记住/别记/恢复记忆/周总结/记忆系统落库”等场景。
npx skillsauth add Andy-HNU/AndyClaw memory-systemInstall 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.
按以下流程执行,不要跳步。
last_reviewed 距今天数分档)。fresh 与 active 进入当前上下文(默认最多 20 条)。直接使用参考 SQL:references/memory-system-prompt-v2.md 第“四、核心 SQL 操作”。
source 必填:user 或 self。emotion=positive)。last_reviewed = date('now')status = 'fresh'blurry/forgotten,不要假装记得;应明确表示记忆模糊并请求用户补充。当用户提供周归档 .md:
permanent / fresh / active。permanent:去重后插入 permanent_memoriesfresh/active:插入 memories,last_reviewed 设为归档生成日期fading/blurry:不写入memory/archives/YYYY-WW.md。记忆已恢复,我想起来了~memory/archives/YYYY-WW.md。在当天第一条对话可主动给出:
references/memory-system-prompt-v2.mdtools
Compact long Telegram chat sessions and prevent silent non-replies caused by high context usage. Use when a Telegram conversation becomes slow, misses replies, or session tokens are high (for example above ~80-85%), and when the user asks to clean, rotate, or shrink Telegram context.
tools
Send local files to Telegram chats through OpenClaw CLI delivery. Use when a user asks to send or forward a file (md/txt/pdf/image/video) to Telegram, especially from workspace paths. Supports direct chat targets and group/topic targets.
tools
轻量自我改进记录技能。用于把错误、用户纠正、知识缺口、功能诉求写入 `.learnings/`,并在每天回顾时将高价值经验提升到 AGENTS.md / SOUL.md / TOOLS.md / MEMORY.md。适用于“避免重复犯错、沉淀经验、降低长期 token 浪费”的场景;默认不启用高频 hooks。
data-ai
轻量主动代理增强。用于在不显著增加 token 的前提下引入 4 个高价值机制:VBR(先验证再汇报)、Autonomous vs Prompted Cron 区分、工具迁移检查清单、会话压缩恢复流程。适用于避免“改了文本没改机制”、减少自动任务失效、提高会话连续性。