memory-management

Decode shorthand, acronyms, and nicknames using CLAUDE.md and memory/ directories.

704|58|Updated Mar 20, 2026
One-click install
npx skills add https://github.com/openyak/desktop --skill memory-management-openyak
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory-management
Source: https://github.com/openyak/desktop/tree/main/backend/app/data/plugins/productivity/skills/memory-management
Command: npx skills add https://github.com/openyak/desktop --skill memory-management-openyak

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Decodes shorthand, acronyms, nicknames, and internal language to help Claude understand requests like a colleague would.

Core Features & Use Cases

  • Hot cache: A lean CLAUDE.md that covers ~30 key terms and people for fast decoding.
  • Deep memory: memory/glossary.md plus memory/people/, memory/projects/, and memory/context/ for full knowledge storage.
  • Contextual lookup: Tiered lookup flow using CLAUDE.md first, then memory/glossary.md, then memory/ for richer detail.

Quick Start

Ask Claude to decode 'todd PSR' to demonstrate how shorthand becomes actionable memory.

Frequently Asked Questions about memory-management

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

FAQPage Schema
How do I help Claude understand workplace acronyms and internal shorthand?

This Skill decodes internal workplace shorthand by applying a tiered lookup flow that checks a CLAUDE.md hot cache first, then falls back to a memory directory to interpret acronyms and nicknames like a colleague.

What is the best way to store project context and glossary terms for AI memory?

Storing project context for AI memory requires a structured directory containing separate files for glossary terms, people, projects, and context, alongside a lean CLAUDE.md hot cache for rapid access to frequently used terms.

Can I use CLAUDE.md as a hot cache for frequent AI memory lookups?

Yes, CLAUDE.md functions as a hot cache covering roughly thirty key terms and people, enabling fast decoding of frequent internal workplace language before the AI performs deeper memory lookups.

How does contextual memory lookup work for internal project language?

Contextual memory lookup works by sequentially checking the CLAUDE.md hot cache, then a glossary file, and finally the full memory directory to provide richer project detail and decode internal workplace language.

When do I need a scalable memory directory structure for AI context?

A scalable memory directory is needed when workplace tasks require both quick shorthand interpretation and deeper lookup, allowing you to organize growing knowledge across separate glossary, people, projects, and context files.