how-it-works

仓库创建 2025年9月1日最近提交 3 天前SkillHot 收录 20 天前

▸ 精选理由

帮助用户理解后台记忆行为与隐私边界。

▸ 风险提示

会暴露系统如何处理数据，涉及隐私与存储位置说明

这个 Skill 做什么

解释 claude-mem 的观测、记忆注入和数据存储机制。

把 Claude 的 Read/Edit/Bash 等操作都变成压缩过的“观测”，会话结束时汇总成记忆条目，相关内容会在下一次会话自动注入到 prompt 里，省掉重复解释代码和决策的麻烦。注入从第二次会话开始生效，能让新会话带上上次的上下文。底层把这些观察结果保存在后端的持久化记忆存储（按会话压缩和索引，类似向量库/数据库），方便检索和回放。

▸ 展开 SKILL.md 英文原文

Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".

Skill 开发管理记忆说明隐私注入时机通用

8.9w

Stars

7.7k

Forks

仓库内 Skill

+2.5k

7 日增星

安装 / 使用

给你的 Agent 一句话（通用）

帮我安装这个 skill：https://raw.githubusercontent.com/thedotmack/claude-mem/main/plugin/skills/how-it-works/SKILL.md

或 curl 直取 SKILL.md

curl -fsSL "https://raw.githubusercontent.com/thedotmack/claude-mem/main/plugin/skills/how-it-works/SKILL.md"

SKILL.MD 节选查看完整文件 ↗

# How claude-mem works

## What it does

Every Read, Edit, and Bash that Claude makes turns into a compressed observation. Observations get summarized at session end. Relevant ones get auto-injected into future prompts so the next session starts with context from the last one — no re-explaining the codebase, no re-discovering decisions.

## When it kicks in

Memory injection starts on your second session in a project.

The first session in a fresh project seeds memory; subsequent sessions receive auto-injected context for relevant past work. Run `/learn-codebase` if you want to front-load the entire repo into memory in a single pass (~5 minutes, optional).

## Where data lives

Everything st

via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有