mem-query

Retrieve user memories across L1-L4 layers with source attribution.

333|83|Updated Jan 9, 2026
One-click install
npx skills add https://github.com/zephyrwang6/myskill --skill mem-query
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mem-query
Source: https://github.com/zephyrwang6/myskill/tree/main/mem-query
Command: npx skills add https://github.com/zephyrwang6/myskill --skill mem-query

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

此技能通过跨多层记忆文件检索与整合,解决用户在需要基于历史信息获得个性化回答时的信息缺失问题。

Core Features & Use Cases

  • 多层级记忆检索:从 L1-L4 自动提取相关记忆并进行综合分析。
  • 来源引用:回答中附带检索源,确保可追溯。
  • 情境化个性化:结合用户历史、偏好与价值观提供定制化建议与决策支持。

Quick Start

向 AI 提出如“我的记忆中关于XXX的部分是什么?”的请求,系统将检索相关记忆并给出带来源的答案。

Frequently Asked Questions about mem-query

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I retrieve personal memories across multiple storage layers to get personalized answers?

Memory retrieval across layered storage automates extraction from L1-L4 memory layers, integrating information to deliver context-aware answers grounded in your personal history, preferences, and habits with full source attribution.

What is a multi-layer memory system and how does it improve personalized responses?

A multi-layer memory system organizes personal data across indexed levels (L1-L4), enabling cross-layer analysis that combines past experiences, preferences, and values to generate consistent, sourced answers tailored to individual context.

Can I track the source of memory-based answers in personalized responses?

Source citation is enforced in all answers, ensuring every personalized response includes retrieval sources so you can verify the memory layer and historical data that grounded each answer.

How do I set up memory indexing for context-aware personal assistance?

Memory indexing organizes personal data across L1-L4 layers, enabling the system to automatically extract relevant information when you ask questions about past experiences, preferences, or habits and return sourced, personalized answers.

What kinds of questions can memory-based personal assistants answer effectively?

Memory-based systems excel at questions about your past experiences, recurring preferences, established habits, and decision patterns—any query requiring historical context and personalization grounded in indexed personal data across multiple layers.

Do I need structured data formats to store personal memories for retrieval?

The system enforces memory indexing across L1-L4 layers without requiring predefined schemas; it retrieves and integrates personal data in various formats to deliver context-aware personalized answers with source attribution.