skills.rest
William2333ZZ
William2333ZZCOMMUNITY
Explore all skills by this author →
GitHub

memory

Store and retrieve persistent workspace memory in MEMORY.md and daily logs.

5|2|Updated Feb 24, 2026
Search Tags:#knowledge management#retrieval#memory#workspace#persistence#storage
One-click install
npx skills add https://github.com/William2333ZZ/ParameciumU --skill memory-william2333zz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: memory
Source: https://github.com/William2333ZZ/ParameciumU/tree/main/agents/agent-mmiyhmh9/skills/memory
Command: npx skills add https://github.com/William2333ZZ/ParameciumU --skill memory-william2333zz

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill manages the long-term memory of the agent, ensuring that important information, user preferences, and past decisions are stored, retrieved, and forgotten as needed, making interactions more coherent and personalized over time.

Core Features & Use Cases

  • Long-term Memory Storage: Persistently store key information in MEMORY.md or daily logs in memory/YYYY-MM-DD.md.
  • Information Retrieval: Search and recall past information using keywords or semantic similarity.
  • Memory Management: Mark information for forgetting and optionally rebuild search indexes for faster retrieval.
  • Use Case: If a user previously stated a preference for concise answers, this skill can recall that preference to tailor future responses.

Quick Start

Use the memory skill to search for information about user preferences.

Frequently Asked Questions about memory

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

FAQPage Schema
How does persistent workspace memory management work for agents?▼

Long-term memory storage saves key information in MEMORY.md or daily logs in memory/YYYY-MM-DD.md. This ensures agent continuity by persistently retaining user preferences and past decisions for coherent, personalized interactions over time.

How do I retrieve past user preferences and historical data in a workspace?▼

You retrieve historical data by searching file-based memory storage using keywords or semantic similarity. Optional FTS5 indexing and vector embeddings enable efficient recall of user preferences and past decisions from MEMORY.md and daily logs.

Can I use FTS5 indexing and vector embeddings for agent memory retrieval?▼

Yes, FTS5 indexing and vector embeddings are optional features supported for efficient memory searching and recall. They optimize the retrieval of historical data and user preferences from file-based storage in MEMORY.md and daily logs.

What is the best way to manage long-term memory storage for agent continuity?▼

The best way is using a file-based system that stores key information in MEMORY.md and daily logs in memory/YYYY-MM-DD.md. This approach handles user preferences and past decisions, ensuring agent continuity and personalized interactions over time.

How do I mark information for forgetting and rebuild search indexes?▼

You mark information for forgetting and optionally rebuild search indexes through the memory management skill. This manages the lifecycle of stored data in MEMORY.md and daily logs, ensuring efficient retrieval of relevant historical data.

Related Skills

Explore More Software Engineering Skills→
espennilsenespennilsen
114

pi-memory

Manage persistent memory across AI sessions with file-based storage.

Community
Intermediate
zerAdazerAda

gsd-profile-user

Generate developer behavioral profiles and personalized USER-PROFILE.md, GSD-dev-preferences, and GEMINI.md sections.

Community
Intermediate
winsorllcwinsorllc

vector-memory

Store and retrieve semantic memories using OpenAI embeddings in a local JSON file.

Community
Intermediate
GSU-FrankJGSU-FrankJ

memory-systems

Implements agent memory systems for cross-session persistence and structured knowledge representation via temporal graphs, vector stores, and entity tracking.

Community
Advanced