agentleFS
guzhou079-archguzhou079-arch/deepseek-harness-android/skills/dsh-memory-sync/SKILL.md

dsh-memory-sync

Skill79 starsChanged 13 days agoMITView on GitHub

跨会话长期记忆中枢与知识提炼技能。自动从对话中提取关键事实、用户偏好、踩坑教训沉淀至本地 SQLite 记忆库 (mem.db),并在新会话中按关键词/语义精准召回,极致节省 Token。

The file

Files
SKILL.md

跨会话记忆与经验中枢技能 (memos)

一句话:告别开局失忆,用极低 Token 成本实现跨会话永续记忆与经验沉淀。

🎯 核心机制

  1. 结构化存储(mem.db):
    • lesson(教训/避坑):踩过的坑、修复方案、技术红线,永不清理。
    • fact(客观事实):环境配置、账号属性、网络状态、项目结构。
    • preference(用户偏好):沟通习惯、UI风格偏好、操作禁忌。
  2. 召回与使用原则:
    • 非必要不全量读:每次只检索与当前任务强相关的 2~3 条记忆;
    • 写前自查、写后回读:写入记忆必须按字节校验,防止脏数据污染。

🛠️ 常用记忆操作命令

MEM="node /sdcard/DeepSeekHarness/tools/mem.js"

# 1. 查找记忆(按关键词)
$MEM find 关键词1 关键词2

# 2. 添加一条避坑教训(自动置顶)
$MEM add --id lesson-custom-name --kind lesson --title "教训标题" --hot --tags 标签1,标签2 <<'EOF'
经过与结论(正文走 stdin,防止 shell 展开)
EOF

# 3. 记录流水日志
$MEM log "完成了某某任务,验证方式为..."

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.