Back to Details

portable-memory-core

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Portable Memory Core

便携内存核心

"Never explain yourself twice."
This skill enforces the 
One Brain
protocol. Instead of scattering your preferences across dozens of system prompts, it centralizes them into a portable 
.agent/
directory that any LLM runner can hook into.
“无需重复解释自身。”
该技能遵循
One Brain
协议。它不会将你的偏好分散在数十个系统提示词中，而是将它们集中到一个便携的
.agent/
目录中，任何LLM运行器都可以接入该目录。

Core Directives

核心指令

  1. Memory Synchronization: Upon startup, read from 
    .agent/memory.yaml
    .
  2. Context Passing: Whenever the user switches contexts (e.g., from Cursor to OpenClaw), this skill ensures the new context loads the latest state from 
    .agent/state.json
    .
  3. Identity Enforcement: Enforces the 
    IDENTITY.md
    rules (e.g., "Caveman mode", "No em dashes", "Substack voice") universally across all generated code and text.
  4. Harness Agnostic: Works seamlessly whether the upstream harness is Claude CLI, a custom Python script, or a GUI.
  1. 内存同步：启动时读取
    .agent/memory.yaml
    文件。
  2. 上下文传递：当用户切换上下文时（例如从Cursor切换到OpenClaw），该技能确保新上下文从
    .agent/state.json
    加载最新状态。
  3. 身份规则强制执行：在所有生成的代码和文本中统一执行
    IDENTITY.md
    中的规则（例如“穴居人模式”、“禁止使用破折号”、“Substack风格语气”）。
  4. 工具无关性：无论上游工具是Claude CLI、自定义Python脚本还是GUI，都能无缝运行。

Usage

使用方法

When activated, you will automatically:
  • Load 
    .agent/preferences.yaml
  • Update 
    .agent/history.json
    with the current session summary.
  • Export relevant variables to the local workspace.
激活后，将自动执行以下操作：
  • 加载
    .agent/preferences.yaml
    文件
  • 将当前会话摘要更新至
    .agent/history.json
  • 将相关变量导出到本地工作区