memory-management

Name: memory-management
Availability: InStock
Author: chelleboyer

Decode shorthand and acronyms using CLAUDE.md and memory/ tiered lookup.

Updated Jan 11, 2026

Search Tags:#context #memory #acronyms #ai-assistant #decoding #workplace

Ready to run

npx skills add https://github.com/chelleboyer/reachy_mini_retail_assistant --skill memory-management-chelleboyer

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: memory-management
Source: https://github.com/chelleboyer/reachy_mini_retail_assistant/tree/main/skills/productivity/skills/memory-management
Command: npx skills add https://github.com/chelleboyer/reachy_mini_retail_assistant --skill memory-management-chelleboyer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Memory decoding bottlenecks slow collaboration; Claude needs to understand shorthand, acronyms, nicknames, and internal language to act like a knowledgeable coworker.

Core Features & Use Cases

Hot cache CLAUDE.md for ~30 frequent terms, people, and preferences, enabling fast decoding.
Deep memory in memory/ with glossary, profiles, projects, and context for richer long-term recall.
Tiered lookup workflow that starts from CLAUDE.md, falls back to memory/glossary, then to memory/people and memory/projects for full context.

Quick Start

Start by loading CLAUDE.md and memory/ to begin decoding common workspace terms and context.

Frequently Asked Questions about memory-management

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

FAQPage Schema

How do I make an AI assistant understand workplace acronyms and shorthand?▼

You can make an AI assistant understand workplace acronyms by loading a hot cache file with frequent terms and a deep memory directory for full context. This enables fast, accurate decoding of internal language.

What is the best way to manage project context for an AI assistant?▼

The best way to manage project context is using a tiered memory lookup system. It starts from a hot cache for quick access, then falls back to deep memory directories containing glossaries, profiles, and project details.

Can I use CLAUDE.md to store frequent workplace terms for quick decoding?▼

Yes, you can use CLAUDE.md as a hot cache to store around thirty frequent terms, people, and preferences. This allows the AI assistant to quickly decode common workspace shorthand during daily tasks.

How do I structure long-term memory for an AI assistant to recall people and projects?▼

You structure long-term memory by creating a deep memory directory with separate files for glossaries, people profiles, and project contexts. The AI references these files when the hot cache does not contain the needed information.

Does this memory management approach work for composing memos and locating documents?▼

Yes, this memory management approach works for composing memos and locating documents. It applies tiered context decoding to interpret internal language, enabling the AI to act like a knowledgeable coworker during daily tasks.

Why does my AI assistant forget internal team language between conversations?▼

An AI assistant forgets internal team language because it lacks a persistent memory structure. Implementing a tiered lookup workflow with a hot cache and deep memory directories solves this by providing structured, long-term context.