Use Case
Three Layer Memory + LanceDB Pro is a powerful AI agent skill that extends your assistant with new capabilities. Three-tier memory system + LanceDB Pro integrated version. Automatic management of hot/warm/cold memory, combined with real-time vector database extraction and structured scheduling maintenance. Micro Sync (scan sessions 5 times a day to record decisions + review autoCapture), Daily Wrap Up (structured summary every early morning), Weekly Compound (weekly memory fat reduction + distillation + vector cleaning). Contains... This guide walks you through installing Three Layer Memory + LanceDB Pro, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install Three Layer Memory + LanceDB Pro: npx clawhub@latest --dir ~/.claude/skills install three-layer-memory
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to documents & notes to trigger Three Layer Memory + LanceDB Pro
Review the output and refine your prompt for better results
Combine Three Layer Memory + LanceDB Pro with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing Three Layer Memory + LanceDB Pro
Help me get started with Three Layer Memory + LanceDB Pro
What can Three Layer Memory + LanceDB Pro do for my documents & notes workflow?
Show me an example of using Three Layer Memory + LanceDB Pro
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install three-layer-memoryOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install three-layer-memoryβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/three-layer-memory/π‘Extract and place the folder at the path above, then restart your agent.