skills.rest
thClaws
thClawsOFFICIAL
Explore all skills by this author →
WebsiteGitHub

memory-management

Decode shorthand, acronyms, and nicknames into actionable context for Claude.

15|6|Updated Apr 29, 2026
Search Tags:#context#memory#acronyms#workflows#knowledge-base#decoding#nicknames
One-click install
npx skills add https://github.com/thClaws/marketplace --skill memory-management-thclaws
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: memory-management
Source: https://github.com/thClaws/marketplace/tree/main/plugins/productivity/skills/memory-management
Command: npx skills add https://github.com/thClaws/marketplace --skill memory-management-thclaws

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Decodes shorthand, acronyms, and internal terms to make Claude understand requests like a colleague would. The two-tier memory system (AGENTS.md + memory/) provides a compact hot cache and a full knowledge base for deeper context.

Core Features & Use Cases

  • Hot cache (AGENTS.md) keeps top contacts, terms, and preferences lightweight for fast decoding.
  • Full memory (memory/) stores detailed profiles, projects, and company context for richer future interactions.
  • Use Case: Quickly map a request like "ask todd about the PSR" to Todd Martinez, Pipeline Status Report, and the associated project context for accurate execution.

Quick Start

Load AGENTS.md and memory/glossary.md to bootstrap the lookup and decoding chain.

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?▼

To decode workplace acronyms and shorthand, you use a two-tier memory system that maps terms like PSR to Pipeline Status Report. It uses a hot cache for quick lookups and a full knowledge base to provide actionable context for accurate execution.

What is the best way to maintain context for Claude across different projects?▼

Maintaining context for Claude requires a structured memory hierarchy using AGENTS.md and a memory directory. This stores detailed profiles, company context, and project data to support richer future interactions across different workflows.

How do I set up a knowledge base for Claude to recognize nicknames and contacts?▼

Setting up a knowledge base for nicknames and contacts requires loading AGENTS.md and memory/glossary.md. You must structure directories for people and projects to bootstrap the lookup and decoding chain for quick mapping.

Do I need to create specific files to manage memory for workflows?▼

Yes, managing memory for workflows requires specific files including AGENTS.md, memory/glossary.md, memory/people/, memory/projects/, and memory/context. This lightweight governance maintains accuracy across hot cache and full memory stores.

Can I use a hot cache for quick term lookups instead of a full memory store?▼

Yes, you can use a hot cache via AGENTS.md for quick lookups of top contacts and terms. The two-tier system applies the hot cache for fast decoding while using the full memory store for deeper knowledge when needed.

Related Skills

Explore More Content & Communication Skills→
TbK0ngTbK0ng

trellis-bootstrap

Initialize Trellis AI workflow scaffolding with .trellis structure, memory, and CLI hooks.

Community
Intermediate
berlinguyincaberlinguyinca
3

autospec-listen

Route mid-conversation intents to autospec workflows for issue filing or spec writing.

Community
Intermediate
GenerativeAgentsGenerativeAgents

glossary-creation

Extract and consolidate project terms into a standardized glossary at docs/glossary.md.

Official
Advanced
kevinlinkevinlin
14

memory-management

Decode shorthand and acronyms into a two-tier memory system with CLAUDE.md and memory/ directories.

Community
Intermediate