memory-management

Decode workplace shorthand and acronyms using a two-tier memory system.

23.4k|2.8k|Updated Jan 23, 2026
One-click install
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill memory-management-anthropics
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory-management
Source: https://github.com/anthropics/knowledge-work-plugins/tree/main/productivity/skills/memory-management
Command: npx skills add https://github.com/anthropics/knowledge-work-plugins --skill memory-management-anthropics

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 comprehend and respond to requests as if it were a seasoned colleague.

Core Features & Use Cases

  • Shorthand Decoding: Translates abbreviations and nicknames into full names and terms.
  • Tiered Memory System: Utilizes a lean CLAUDE.md for frequent terms and a comprehensive memory/ directory for deep knowledge.
  • Use Case: A user types "ask todd about the PSR for phoenix." Claude, using this Skill, decodes "todd" to Todd Martinez (Finance lead), "PSR" to Pipeline Status Report, and "phoenix" to the DB migration project, enabling a precise response.

Quick Start

Use the memory management skill to decode the term "PSR" and identify "Todd".

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 shorthand for Claude to understand?

To decode workplace acronyms and shorthand, this Skill uses a two-tier memory system translating internal jargon into clear terms. It enables Claude to comprehend requests like "ask todd about the PSR" by resolving nicknames and abbreviations into full names and contexts.

What is the best way to manage context memory for internal company jargon?

Managing context memory for internal jargon involves using a tiered system with a lean CLAUDE.md for frequent terms and a memory/ directory for deep knowledge. This structure supports lookup flows from a hot cache to a full glossary, ensuring accurate AI comprehension.

Can I use CLAUDE.md to maintain a glossary of project nicknames and abbreviations?

Yes, you can use CLAUDE.md to maintain a lean glossary of frequent project nicknames and abbreviations. It acts as working memory, while a comprehensive memory/ directory stores deep knowledge, supporting efficient lookup flows for AI comprehension.

How does the tiered memory system handle deep knowledge versus working memory?

The tiered memory system handles deep knowledge by storing comprehensive glossary details in the memory/ directory, while working memory in CLAUDE.md holds frequent terms. It supports lookup flows from a hot cache to full external profiles for precise decoding.

Does this approach require external profiles to decode internal workplace language?

No, decoding internal workplace language does not strictly require external profiles. The system primarily relies on its internal memory/ directory and CLAUDE.md working memory, though it supports lookup flows that can extend to external profiles if available.