memory-management

Manage two-tier memory in CLAUDE.md and memory/ to decode workplace shorthand.

4|2|Updated Mar 9, 2026
One-click install
npx skills add https://github.com/kyopark2014/agent-plugins --skill memory-management-kyopark2014
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory-management
Source: https://github.com/kyopark2014/agent-plugins/tree/main/application/plugins/productivity/skills/memory-management
Command: npx skills add https://github.com/kyopark2014/agent-plugins --skill memory-management-kyopark2014

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill transforms shorthand, acronyms, and internal jargon into clear understanding, enabling Claude to communicate and act like a true colleague within your specific workplace environment.

Core Features & Use Cases

  • Shorthand Decoding: Automatically translates abbreviations, nicknames, and internal terms into their full meanings.
  • Tiered Memory System: Utilizes a quick-access cache (CLAUDE.md) and a comprehensive knowledge base (memory/ directory) for efficient information retrieval.
  • Use Case: A user asks Claude to "ask todd to do the PSR for oracle." Claude uses its memory to understand that "todd" is Todd Martinez (Finance lead), "PSR" is Pipeline Status Report, and "oracle" refers to a specific deal, allowing it to fulfill the request accurately.

Quick Start

Use the memory management skill to decode the phrase "ask todd about the PSR for phoenix".

Frequently Asked Questions about memory-management

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

FAQPage Schema
How do I decode workplace acronyms and internal shorthand for an AI assistant?

You decode workplace shorthand by implementing a two-tier memory system that progressively discloses information from a hot cache to a full knowledge base, enabling the AI to understand internal jargon. This allows accurate interpretation of user requests.

How does tiered memory work for managing company-specific glossaries and people profiles?

Tiered memory works by managing working memory in a quick-access cache file and storing deep knowledge in a dedicated directory. This structure contains glossaries, people profiles, project details, and company context for efficient information retrieval.

What's the best way to make Claude understand internal team nicknames and project references?

The best way to make Claude understand internal references is to map workplace-specific shorthand, acronyms, and internal language into a structured knowledge base. This transforms abbreviations and nicknames into their full meanings for accurate communication.

Can I use a memory directory to help AI translate abbreviations like PSR into full meanings?

Yes, you can use a memory directory to translate abbreviations. The system automatically decodes shorthand like PSR into full meanings such as Pipeline Status Report, enabling the AI to act like a true colleague within your specific workplace environment.

Do I need to manually update the CLAUDE.md cache when adding new workplace jargon?

The system utilizes a quick-access cache for working memory alongside a comprehensive knowledge base directory. This setup facilitates accurate interpretation by progressively disclosing information, allowing the AI to retrieve newly added context efficiently.

Why does an AI assistant misunderstand my internal company jargon and shorthand?

An AI misunderstands internal jargon because it lacks the workplace-specific context. By implementing a memory system with glossaries and project details, the AI can decode abbreviations and internal terms, preventing misinterpretation of user requests.