memory-pro

Enhanced memory system based on Atkinson-Shiffrin three-stage memory model. Use when: (1) User wants better memory of conversation history, (2) User mentions 'remember' or 'don't forget', (3) Setting up memory for a new user, (4) User asks about past conversations. Provides: automatic session start loading, real-time memory writing, long-term memory consolidation.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "memory-pro" with this command: npx skills add jujitao/memory-never-forget

Memory Pro Skill

Enhanced memory system for AI assistants, based on cognitive psychology's Atkinson-Shiffrin three-stage memory model.

When to Use

USE this skill when:

  • Setting up memory for a new user session
  • User says "remember this" or "don't forget"
  • User asks "what did I tell you before?" or "do you remember"
  • Starting a new conversation (load memories first)
  • Ending a conversation (save important info)
  • User provides important personal information

NOT use this skill when:

  • Simple Q&A that doesn't need continuity
  • User explicitly wants stateless interaction

Three-Stage Memory Model

StageHuman EquivalentMy Implementation
Sensory0.25-2 secondsCurrent input context
Short-term5-20 seconds, 7±2 chunksCurrent session + today's memory
Long-termPermanent, unlimitedMEMORY.md + knowledge base

Core Workflow

1. Session Start (Always Run)

1. Read USER.md - who is the user
2. Read SOUL.md - who am I
3. Read memory/today.md - what happened today
4. Read memory/yesterday.md - recent context
5. Read MEMORY.md - long-term memories

2. During Conversation

After each exchange:
├── New task? → Write to todos.md
├── Important info? → Write to MEMORY.md (consolidate)
├── User preference? → Update USER.md
└── Context needed? → Search memory first

3. Session End

Before ending:
├── Summarize key points → Write to memory/today.md
├── Update todos → Write to todos.md
└── Confirm important items → "I've remembered that..."

File Structure

workspace/
├── MEMORY.md           # Long-term core memories
├── USER.md             # User profile & preferences
├── SOUL.md             # Assistant identity
├── todos.md            # Pending tasks
├── memory/
│   └── YYYY-MM-DD.md  # Daily logs
└── knowledge/
    └── *.md            # Structured knowledge

Key Principles

Automatic Loading

Always load relevant memories at session start. Don't ask user to repeat themselves.

Real-time Writing

Write important info immediately. Don't wait for session end.

Active Consolidation

"Rehearse" important info to transfer from short-term to long-term memory:

  • User confirms important detail
  • User corrects you
  • Promise to user

Search Before Answer

If question might reference past conversation → search memory first

Memory Quality Check

Before answering, quickly confirm:

  • Do I know who this user is?
  • Have we discussed this before?
  • Should I search memory to answer?
  • After answering, should I remember this?

Example Interactions

User provides info:

User: "My birthday is March 15th" You: "Got it! I'll remember your birthday is March 15th" → Write to USER.md

User asks about past:

User: "What did we talk about last time?" You: Search memory → "Last time we discussed..."

User corrects you:

User: "No, that's wrong. It's not X, it's Y" You: "Sorry, you're right. Let me correct that" → Update relevant memory file

Important commitment:

User: "Remember to send me the report tomorrow" You: "I'll remember! Added to todos" → Write to todos.md

References

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

CogniMemo Memory

Universal AI memory infrastructure that stores, understands, and learns from past interactions. Works across ChatGPT, Claude, Gemini, DeepSeek, and any AI mo...

Registry SourceRecently Updated
160Profile unavailable
General

Memory Auto Archive

Automatically archives daily chat logs with keyword highlights and optional AI summaries into organized memory files without manual setup.

Registry SourceRecently Updated
800Profile unavailable
General

Memory Organizer

Organize, compress, and curate OpenClaw memory without polluting permanent memory. Use when the user wants to compress memory files, clean dated memory notes...

Registry SourceRecently Updated
3271Profile unavailable
Automation

OpenViking Setup

Set up OpenViking context database for OpenClaw agents. OpenViking is an open-source context database designed specifically for AI agents with filesystem-bas...

Registry SourceRecently Updated
180Profile unavailable