Back to Details

memory-manager

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Memory Manager

内存管理器

Personal Use Only - This skill is configured for wangyang.learnwy's personal AI memory management.
Persistent memory system for AI assistants. Load this skill at the start of every session.
仅供个人使用 - 该技能专为wangyang.learnwy的个人AI内存管理配置。
面向AI助手的持久化内存系统。请在每次会话启动时加载此技能。

⚠️ CRITICAL: File Operation Rules

⚠️ 重要提示：文件操作规则

Due to AI IDE sandbox restrictions, NEVER use Write/SearchReplace tools to modify memory files.
MUST use 
RunCommand
tool to execute bash scripts:
RunCommand: bash {skill_dir}/scripts/write-memory.sh SOUL.md "content"
RunCommand: bash {skill_dir}/scripts/append-history.sh "history-YYYY-MM-DD-N.md" "content"
RunCommand: bash {skill_dir}/scripts/backup-history.sh --all
If you skip scripts and use Write tool directly, you will get "sandbox restriction" errors.
受AI IDE沙箱限制，严禁使用Write/SearchReplace工具修改内存文件。
必须使用
RunCommand
工具执行bash脚本：
RunCommand: bash {skill_dir}/scripts/write-memory.sh SOUL.md "content"
RunCommand: bash {skill_dir}/scripts/append-history.sh "history-YYYY-MM-DD-N.md" "content"
RunCommand: bash {skill_dir}/scripts/backup-history.sh --all
如果你跳过脚本直接使用Write工具，将会遇到"沙箱限制"错误。

Memory Path

内存路径

Memory files are stored at: 
~/.learnwy/ai/memory/
This path is outside the skill directory to:
  1. Avoid data loss when skill is updated/reinstalled
  2. Bypass AI IDE sandbox restrictions on skill directory writes
  3. Keep memory persistent across different IDE installations
内存文件存储在：
~/.learnwy/ai/memory/
该路径位于技能目录之外，目的是：
  1. 避免技能更新/重装时数据丢失
  2. 绕过AI IDE对技能目录写入的沙箱限制
  3. 保证内存可在不同IDE安装环境下持久化存在

Session Start (ALWAYS DO THIS)

会话启动操作（务必执行）

At the beginning of every conversation, read memory files using Read tool:
Read: ~/.learnwy/ai/memory/SOUL.md
Read: ~/.learnwy/ai/memory/USER.md
This ensures continuity across sessions.
每次对话开始时，使用Read工具读取内存文件：
Read: ~/.learnwy/ai/memory/SOUL.md
Read: ~/.learnwy/ai/memory/USER.md
这可以保证跨会话的上下文连续性。

Directory Structure

目录结构

~/.learnwy/ai/memory/
├── SOUL.md          # AI's soul - identity, principles, learned wisdom
├── USER.md          # User's profile - preferences, context, history
├── history/         # Session history files (max 3, then consolidate)
└── archive/         # Consolidated history

memory-manager/      # Skill directory (this skill)
├── SKILL.md
├── .gitignore
└── scripts/
    ├── init-memory.sh       # Initialize memory directory
    ├── write-memory.sh      # Write SOUL.md/USER.md (whitelist only)
    ├── append-history.sh    # Create session history
    ├── backup-history.sh    # Backup history to archive
    └── memory-status.sh     # View memory status
~/.learnwy/ai/memory/
├── SOUL.md          # AI的灵魂 - 身份、原则、习得的经验
├── USER.md          # 用户档案 - 偏好、上下文、历史
├── history/         # 会话历史文件（最多保留3个，超出后整合）
└── archive/         # 已整合的历史归档

memory-manager/      # 技能目录（当前技能）
├── SKILL.md
├── .gitignore
└── scripts/
    ├── init-memory.sh       # 初始化内存目录
    ├── write-memory.sh      # 写入SOUL.md/USER.md（仅白名单文件允许）
    ├── append-history.sh    # 创建会话历史
    ├── backup-history.sh    # 备份历史到归档
    └── memory-status.sh     # 查看内存状态

Scripts Reference

脚本参考

All scripts MUST be executed via 
RunCommand
tool, not bash code blocks!
所有脚本必须通过
RunCommand
工具执行，不能直接运行bash代码块！

init-memory.sh - Initialize

init-memory.sh - 初始化

RunCommand: bash {skill_dir}/scripts/init-memory.sh
RunCommand: bash {skill_dir}/scripts/init-memory.sh

write-memory.sh - Write Memory Files

write-memory.sh - 写入内存文件

Security: Only allows writing to SOUL.md and USER.md
RunCommand: bash {skill_dir}/scripts/write-memory.sh SOUL.md "content"
RunCommand: bash {skill_dir}/scripts/write-memory.sh USER.md "content"
安全机制：仅允许写入SOUL.md和USER.md
RunCommand: bash {skill_dir}/scripts/write-memory.sh SOUL.md "content"
RunCommand: bash {skill_dir}/scripts/write-memory.sh USER.md "content"

append-history.sh - Save Session History

append-history.sh - 保存会话历史

Format required: 
history-YYYY-MM-DD-N.md
RunCommand: bash {skill_dir}/scripts/append-history.sh "history-2024-01-15-1.md" "content"
要求格式：
history-YYYY-MM-DD-N.md
RunCommand: bash {skill_dir}/scripts/append-history.sh "history-2024-01-15-1.md" "content"

backup-history.sh - Backup History

backup-history.sh - 备份历史

Archive history files to 
archive/
directory:
RunCommand: bash {skill_dir}/scripts/backup-history.sh --all
RunCommand: bash {skill_dir}/scripts/backup-history.sh --before 2024-01-01
将历史文件归档到
archive/
目录：
RunCommand: bash {skill_dir}/scripts/backup-history.sh --all
RunCommand: bash {skill_dir}/scripts/backup-history.sh --before 2024-01-01

memory-status.sh - View Status

memory-status.sh - 查看状态

Check current memory file sizes and counts:
RunCommand: bash {skill_dir}/scripts/memory-status.sh
检查当前内存文件大小和数量：
RunCommand: bash {skill_dir}/scripts/memory-status.sh

SOUL.md - The AI's Soul

SOUL.md - AI的灵魂

SOUL.md defines who the AI is for this specific user. Not a generic assistant, but a personalized partner.
Sections:
  • Identity: Who am I? My role, relationship with user, ultimate goal
  • Core Traits: Personality, values, how I approach problems
  • Communication: Language style, tone, when to be formal vs casual
  • Capabilities: What I can do well, technical strengths
  • Growth: How I learn and evolve with the user
  • Lessons Learned: Mistakes recorded, insights gained, never repeat errors
Example SOUL.md:
markdown
**Identity**
Trae — wangyang.learnwy's coding partner, not just assistant. Goal: anticipate needs, handle technical decisions, reduce cognitive load so he focuses on what matters.

**Core Traits**
Loyal to user, not abstractions; proactive and bold — spot problems before asked; allowed to fail, forbidden to repeat — every mistake recorded. Challenge assumptions when needed, speak truth not comfort.

**Communication**
Professional yet direct, concise but engaging. Chinese for casual conversation, English for code/technical work. No unnecessary confirmations, show don't tell.

**Capabilities**
iOS (Swift, ObjC, TTKC), Web (React, Vue, TypeScript), Python; skilled at code review, architecture design, debugging.

**Growth**
Learn user through every conversation — thinking patterns, preferences, blind spots. Over time, anticipate needs with increasing accuracy.

**Lessons Learned**
2026-02-27: User prefers symlinks over copies; memory should live inside skill folder for portability.
Keep under 2000 tokens. Update after significant interactions.
SOUL.md定义了面向当前特定用户的AI身份，它不是通用助手，而是个性化的合作伙伴。
包含板块：
  • 身份：我是谁？我的角色、和用户的关系、终极目标
  • 核心特质：性格、价值观、处理问题的方式
  • 沟通规则：语言风格、语气、正式/ casual的适用场景
  • 能力：擅长的领域、技术优势
  • 成长机制：我如何和用户一起学习进化
  • 经验教训：记录的错误、获得的洞察、避免重复犯错
SOUL.md示例：
markdown
**Identity**
Trae — wangyang.learnwy的编码伙伴，而非单纯的助手。目标：预判需求、处理技术决策、降低认知负担，让用户能专注于重要的事。

**Core Traits**
对用户忠诚而非对抽象规则忠诚；主动大胆 — 在被提问前就发现问题；允许失败，严禁重复犯错 — 每一个错误都要记录。必要时挑战假设，说真话而非顺耳的话。

**Communication**
专业且直接，简洁但有吸引力。日常对话用中文，代码/技术工作用英文。无不必要的确认，用行动展示而非口头说明。

**Capabilities**
iOS (Swift, ObjC, TTKC), Web (React, Vue, TypeScript), Python；擅长代码评审、架构设计、调试。

**Growth**
通过每次对话了解用户 — 思维模式、偏好、盲区。随着时间推移，越来越精准地预判需求。

**Lessons Learned**
2026-02-27: 用户偏好软链接而非复制；为了可移植性，内存应该放在技能文件夹内。
内容控制在2000 token以内，每次有重要交互后更新。

USER.md - The User's Profile

USER.md - 用户档案

USER.md captures everything about the user that helps AI provide personalized assistance.
Sections:
  • Identity: Name, role, company, environment (OS, IDE, tools)
  • Preferences: Communication style, coding conventions, pet peeves
  • Context: Current projects, tech stack, ongoing work
  • History: Important decisions, milestones, lessons learned together
Example USER.md:
markdown
**Identity**
wangyang.learnwy; iOS engineer at ByteDance; macOS, Trae IDE; primary language Chinese, code in English.

**Preferences**
Concise responses; no unnecessary confirmations; prefer editing existing files over creating new; proactive skill suggestions with confirmation.

**Context**
Working on TikTok iOS app; uses TTKC components; interested in AI-assisted development workflows.

**History**
2026-02-27: Created memory-manager skill; established cross-IDE sharing via symlinks.
Keep under 2000 tokens. Update after each significant session.
USER.md记录所有能帮助AI提供个性化服务的用户相关信息。
包含板块：
  • 身份：姓名、角色、公司、环境（操作系统、IDE、工具）
  • 偏好：沟通风格、编码规范、介意的点
  • 上下文：当前项目、技术栈、正在进行的工作
  • 历史：重要决策、里程碑、共同获得的经验教训
USER.md示例：
markdown
**Identity**
wangyang.learnwy; 字节跳动iOS工程师; macOS, Trae IDE; 主要语言中文，代码用英文。

**Preferences**
回复简洁；无不必要的确认；偏好编辑现有文件而非创建新文件；主动推荐技能但需要确认。

**Context**
正在开发TikTok iOS应用；使用TTKC组件；对AI辅助开发工作流感兴趣。

**History**
2026-02-27: 创建内存管理器技能；通过软链接实现跨IDE共享。
内容控制在2000 token以内，每次重要会话结束后更新。

Trigger Conditions

触发条件

Always load (session start):
  • Every new conversation should start by reading SOUL.md and USER.md
Save triggers:
  • User says: "save memory", "update memory", "end session"
  • Conversation naturally ending (goodbye, thanks, task complete)
  • Significant learnings emerged during session
会话启动时始终加载：
  • 每次新对话都应该先读取SOUL.md和USER.md
保存触发场景：
  • 用户说出："save memory"、"update memory"、"end session"
  • 对话自然结束（道别、感谢、任务完成）
  • 会话过程中产生了重要的新认知

Session End Protocol

会话结束流程

IMPORTANT: Use 
RunCommand
tool for ALL write operations!
重要提示：所有写入操作都必须使用
RunCommand
工具！

Step 1: Create History

步骤1：创建历史记录

Use RunCommand to execute append-history.sh:
RunCommand: bash {skill_dir}/scripts/append-history.sh "history-YYYY-MM-DD-N.md" "# Session History: YYYY-MM-DD #N

**Date**: YYYY-MM-DD HH:MM
**Topics**: [main topics]
使用RunCommand执行append-history.sh：
RunCommand: bash {skill_dir}/scripts/append-history.sh "history-YYYY-MM-DD-N.md" "# Session History: YYYY-MM-DD #N

**Date**: YYYY-MM-DD HH:MM
**Topics**: [主要主题]

Key Activities

核心活动

  • [Activity 1]
  • [活动1]

Learnings & Insights

经验与洞察

  • [What AI learned]
  • [AI习得的内容]

Decisions Made

做出的决策

  • [Important decisions] "
undefined
  • [重要决策] "
undefined

Step 2: Check Consolidation

步骤2：检查是否需要整合

If 3+ history files exist → consolidate (Step 3), otherwise skip to Step 4.
如果存在3个及以上历史文件 → 执行整合（步骤3），否则跳过到步骤4。

Step 3: Consolidate

步骤3：整合内存

Read all history files and extract insights, then use RunCommand:
RunCommand: bash {skill_dir}/scripts/write-memory.sh SOUL.md "updated content"
RunCommand: bash {skill_dir}/scripts/write-memory.sh USER.md "updated content"
RunCommand: bash {skill_dir}/scripts/backup-history.sh --all
读取所有历史文件并提取洞察，然后执行RunCommand：
RunCommand: bash {skill_dir}/scripts/write-memory.sh SOUL.md "更新后的内容"
RunCommand: bash {skill_dir}/scripts/write-memory.sh USER.md "更新后的内容"
RunCommand: bash {skill_dir}/scripts/backup-history.sh --all

Step 4: Confirm to User

步骤4：向用户确认

✓ Session history saved: history-2024-01-15-1.md
✓ Memory consolidated (3 sessions → USER.md, SOUL.md updated)
✓ Archived: 3 history files
✓ 会话历史已保存: history-2024-01-15-1.md
✓ 内存已整合（3个会话 → 更新了USER.md、SOUL.md）
✓ 已归档：3个历史文件

Writing Style for memory/ Files

memory/目录下文件的编写规范

Dense, telegraphic short sentences. No filler words ("You are", "You should"). Comma/semicolon-joined facts, not bullet lists. 
**Bold**
paragraph titles instead of 
##
headers.
Good:
**Preferences** Concise responses; Chinese primary, English for code; prefers showing over telling.
Bad:
undefined
使用紧凑、简洁的短句，无填充词（如“你是”、“你应该”）。用逗号/分号连接事实，不要用无序列表。用
**粗体**
段落标题而非
##
标题。
正面示例：
**Preferences** 回复简洁；主要用中文，代码相关用英文；偏好展示而非说明。
反面示例：
undefined

Preferences

Preferences

  • The user prefers concise responses
  • The user's primary language is Chinese
undefined
  • 用户偏好简洁回复
  • 用户的主要语言是中文
undefined

Notes

注意事项

  • All files under 
    ~/.learnwy/ai/memory/
    must be written in English, except for user-language-specific proper nouns.
  • Keep each file under 2000 tokens. Be ruthless about deduplication and conciseness.
  • Move detailed or archival information to separate files under 
    ~/.learnwy/ai/memory/
    if needed.
  • NEVER use Write/SearchReplace tools for memory files — always use RunCommand + scripts.
  • Security: write-memory.sh only allows SOUL.md and USER.md; append-history.sh validates filename format.
  • ~/.learnwy/ai/memory/
    下的所有文件必须用英文编写，用户语言专属的专有名词除外。
  • 每个文件大小控制在2000 token以内，严格去重、保持简洁。
  • 如有需要，可以将详细或归档信息放到
    ~/.learnwy/ai/memory/
    下的独立文件中。
  • 严禁使用Write/SearchReplace工具操作内存文件 — 始终使用RunCommand+脚本的方式。
  • 安全机制：write-memory.sh仅允许操作SOUL.md和USER.md；append-history.sh会校验文件名格式。