memory-manager

Manage and restore work context across session boundaries with a 3-tier memory model.

Updated Dec 15, 2019
One-click install
npx skills add https://github.com/matsuyoshi30/dotfiles --skill memory-manager-matsuyoshi30
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory-manager
Source: https://github.com/matsuyoshi30/dotfiles/tree/main/.agents/skills/memory-manager
Command: npx skills add https://github.com/matsuyoshi30/dotfiles --skill memory-manager-matsuyoshi30

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automatically preserve and restore work context across session boundaries using a 3-tier memory model, helping you resume work after pauses, switches, or compaction.

Core Features & Use Cases

  • 3-tier memory structure: short-term, mid-term, and long-term memories that survive session switches and compaction.
  • Auto-triggered context loading: restores short-term on session start, selectively loads mid/long-term based on user prompts, and persists state before compaction.
  • Resumption-friendly outputs: stores structured memory artifacts and an index of long-term knowledge to guide future work.
  • Use Case: when switching tasks, the system rehydrates context so you can continue without re-building context.

Quick Start

Prompt the system to restore your last session context and begin tracking current work.

Frequently Asked Questions about memory-manager

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

FAQPage Schema
How do I preserve work context across session boundaries without manual input?

To preserve work context across session boundaries, this Skill applies a 3-tier memory model that automatically saves and restores short-term, mid-term, and long-term memories during task boundaries and compaction. It triggers automatically to persist state without manual intervention.

What is the 3-tier memory model for managing session context?

The 3-tier memory model for session context management structures saved information into short-term, mid-term, and long-term memories. This hierarchy selectively loads relevant context based on user prompts and survives session switches and compaction.

How can I restore my previous work context after a session compaction?

You can restore work context after compaction because the system auto-triggers to persist state before compaction occurs. Upon the next session start, it automatically rehydrates short-term memory and selectively loads mid-term and long-term memories.

Does memory management for workflow context require manual invocation?

Memory management for workflow context requires minimal user invocation. The system uses auto-trigger hooks during session start, user prompts, and task boundaries to automatically load and persist memory, so you do not need to manually save state.

When should I use structured memory lifecycles for task tracking?

You should use structured memory lifecycles for task tracking when switching tasks frequently or resuming work after pauses. The system rehydrates context automatically so you can continue without rebuilding context, storing structured artifacts for future use.