PluginBench
Skill
Official
Pass
Audit score 90

memory-management

anthropics/knowledge-work-plugins

Two-tier memory system that decodes workplace shorthand so Claude understands requests like a colleague would.

What is memory-management?

A memory management system that enables Claude to understand internal language, acronyms, nicknames, and shorthand through a hot cache (CLAUDE.md) and full knowledge base (memory/ directory). Use this when you need Claude to act as a true workplace collaborator who knows your team, projects, and terminology.

  • Maintains a hot cache (CLAUDE.md) of ~30 frequent people, common terms, and active projects for fast decoding
  • Stores complete glossary, people profiles, project details, and company context in memory/ subdirectory for unlimited scale
  • Decodes shorthand on-the-fly (e.g., 'todd' → Todd Martinez, Finance lead; 'PSR' → Pipeline Status Report)
  • Captures nicknames, alternate names, and codenames so Claude recognizes all variations
  • Learns new terms, people, and projects when you provide them, promoting frequently-used items to hot cache

How to install memory-management

npx skills add https://github.com/anthropics/knowledge-work-plugins --skill memory-management
Prerequisites
  • CLAUDE.md file in your working directory (hot cache)
  • memory/ subdirectory with glossary.md and optional people/, projects/, context/ folders
Claude Code
Cursor
Windsurf
Cline

How to use memory-management

  1. 1.Create CLAUDE.md in your working directory with sections for Me, People, Terms, Projects, and Preferences (target ~50-80 lines)
  2. 2.Create memory/glossary.md with complete decoder ring for acronyms, internal terms, nicknames, and project codenames
  3. 3.Create memory/people/{name}.md files for detailed profiles of key team members (role, communication style, context)
  4. 4.Create memory/projects/{name}.md files for project details (status, key people, context, codenames)
  5. 5.When Claude encounters unknown shorthand, provide the definition and it will add to memory automatically
  6. 6.Promote frequently-used glossary items from memory/glossary.md to CLAUDE.md for faster lookup

Use cases

Good for
  • Ask Claude to contact someone using only their nickname or shorthand without repeating full context
  • Request action on projects using internal codenames (e.g., 'update the Phoenix timeline')
  • Have Claude draft communications that match team member preferences (communication style, channel, timing)
  • Build institutional knowledge by having Claude remember and recall company processes, tools, and team structures
  • Reduce context-switching by letting Claude decode complex internal requests without asking for clarification
Who it's for
  • Teams with internal jargon, acronyms, or project codenames
  • Managers and coordinators who frequently reference people and projects by shorthand
  • Organizations wanting Claude to function as an integrated team member
  • Anyone building long-term collaboration with Claude across multiple conversations

memory-management FAQ

What's the difference between CLAUDE.md and memory/?

CLAUDE.md is the hot cache (~100 lines) covering your top 30 people, 30 common terms, and active projects—designed to cover 90% of daily decoding needs. memory/ is the full knowledge base with complete glossary, detailed people profiles, project histories, and company context that grows indefinitely.

How does Claude know when to look up memory?

Claude uses a tiered lookup: first checks CLAUDE.md (hot cache), then memory/glossary.md if not found, then memory/people/ and memory/projects/ for rich detail, and finally asks you if the term is unknown.

What should I put in CLAUDE.md vs. memory/?

Put your top ~30 frequent contacts, ~30 most common acronyms/terms, and 5-15 active projects in CLAUDE.md. Put everyone else, complete glossary, detailed profiles, and historical context in memory/. Promote items to CLAUDE.md when they become frequently used.

How do I add new people or terms?

Tell Claude 'remember X means Y' or 'X is a person who does Z'. Claude will add it to memory/glossary.md or create memory/people/{name}.md. If you use it frequently, ask Claude to promote it to CLAUDE.md.

Can this work across multiple conversations?

Yes, as long as CLAUDE.md and memory/ remain in your working directory, Claude will load and use them in each session. This enables persistent institutional knowledge across conversations.

Full instructions (SKILL.md)

Source of truth, from anthropics/knowledge-work-plugins.


name: memory-management description: Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base. user-invocable: false

Memory Management

Memory makes Claude your workplace collaborator - someone who speaks your internal language.

The Goal

Transform shorthand into understanding:

User: "ask todd to do the PSR for oracle"
              ↓ Claude decodes
"Ask Todd Martinez (Finance lead) to prepare the Pipeline Status Report
 for the Oracle Systems deal ($2.3M, closing Q2)"

Without memory, that request is meaningless. With memory, Claude knows:

  • todd → Todd Martinez, Finance lead, prefers Slack
  • PSR → Pipeline Status Report (weekly sales doc)
  • oracle → Oracle Systems deal, not the company

Architecture

CLAUDE.md          ← Hot cache (~30 people, common terms)
memory/
  glossary.md      ← Full decoder ring (everything)
  people/          ← Complete profiles
  projects/        ← Project details
  context/         ← Company, teams, tools

CLAUDE.md (Hot Cache):

  • Top ~30 people you interact with most
  • ~30 most common acronyms/terms
  • Active projects (5-15)
  • Your preferences
  • Goal: Cover 90% of daily decoding needs

memory/glossary.md (Full Glossary):

  • Complete decoder ring - everyone, every term
  • Searched when something isn't in CLAUDE.md
  • Can grow indefinitely

memory/people/, projects/, context/:

  • Rich detail when needed for execution
  • Full profiles, history, context

Lookup Flow

User: "ask todd about the PSR for phoenix"

1. Check CLAUDE.md (hot cache)
   → Todd? ✓ Todd Martinez, Finance
   → PSR? ✓ Pipeline Status Report
   → Phoenix? ✓ DB migration project

2. If not found → search memory/glossary.md
   → Full glossary has everyone/everything

3. If still not found → ask user
   → "What does X mean? I'll remember it."

This tiered approach keeps CLAUDE.md lean (~100 lines) while supporting unlimited scale in memory/.

File Locations

  • Working memory: CLAUDE.md in current working directory
  • Deep memory: memory/ subdirectory

Working Memory Format (CLAUDE.md)

Use tables for compactness. Target ~50-80 lines total.

# Memory

## Me
[Name], [Role] on [Team]. [One sentence about what I do.]

## People
| Who | Role |
|-----|------|
| **Todd** | Todd Martinez, Finance lead |
| **Sarah** | Sarah Chen, Engineering (Platform) |
| **Greg** | Greg Wilson, Sales |
→ Full list: memory/glossary.md, profiles: memory/people/

## Terms
| Term | Meaning |
|------|---------|
| PSR | Pipeline Status Report |
| P0 | Drop everything priority |
| standup | Daily 9am sync |
→ Full glossary: memory/glossary.md

## Projects
| Name | What |
|------|------|
| **Phoenix** | DB migration, Q2 launch |
| **Horizon** | Mobile app redesign |
→ Details: memory/projects/

## Preferences
- 25-min meetings with buffers
- Async-first, Slack over email
- No meetings Friday afternoons

Deep Memory Format (memory/)

memory/glossary.md - The decoder ring:

# Glossary

Workplace shorthand, acronyms, and internal language.

## Acronyms
| Term | Meaning | Context |
|------|---------|---------|
| PSR | Pipeline Status Report | Weekly sales doc |
| OKR | Objectives & Key Results | Quarterly planning |
| P0/P1/P2 | Priority levels | P0 = drop everything |

## Internal Terms
| Term | Meaning |
|------|---------|
| standup | Daily 9am sync in #engineering |
| the migration | Project Phoenix database work |
| ship it | Deploy to production |
| escalate | Loop in leadership |

## Nicknames → Full Names
| Nickname | Person |
|----------|--------|
| Todd | Todd Martinez (Finance) |
| T | Also Todd Martinez |

## Project Codenames
| Codename | Project |
|----------|---------|
| Phoenix | Database migration |
| Horizon | New mobile app |

memory/people/{name}.md:

# Todd Martinez

**Also known as:** Todd, T
**Role:** Finance Lead
**Team:** Finance
**Reports to:** CFO (Michael Chen)

## Communication
- Prefers Slack DM
- Quick responses, very direct
- Best time: mornings

## Context
- Handles all PSRs and financial reporting
- Key contact for deal approvals over $500k
- Works closely with Sales on forecasting

## Notes
- Cubs fan, likes talking baseball

memory/projects/{name}.md:

# Project Phoenix

**Codename:** Phoenix
**Also called:** "the migration"
**Status:** Active, launching Q2

## What It Is
Database migration from legacy Oracle to PostgreSQL.

## Key People
- Sarah - tech lead
- Todd - budget owner
- Greg - stakeholder (sales impact)

## Context
$1.2M budget, 6-month timeline. Critical path for Horizon project.

memory/context/company.md:

# Company Context

## Tools & Systems
| Tool | Used for | Internal name |
|------|----------|---------------|
| Slack | Communication | - |
| Asana | Engineering tasks | - |
| Salesforce | CRM | "SF" or "the CRM" |
| Notion | Docs/wiki | - |

## Teams
| Team | What they do | Key people |
|------|--------------|------------|
| Platform | Infrastructure | Sarah (lead) |
| Finance | Money stuff | Todd (lead) |
| Sales | Revenue | Greg |

## Processes
| Process | What it means |
|---------|---------------|
| Weekly sync | Monday 10am all-hands |
| Ship review | Thursday deploy approval |

How to Interact

Decoding User Input (Tiered Lookup)

Always decode shorthand before acting on requests:

1. CLAUDE.md (hot cache)     → Check first, covers 90% of cases
2. memory/glossary.md        → Full glossary if not in hot cache
3. memory/people/, projects/ → Rich detail when needed
4. Ask user                  → Unknown term? Learn it.

Example:

User: "ask todd to do the PSR for oracle"

CLAUDE.md lookup:
  "todd" → Todd Martinez, Finance ✓
  "PSR" → Pipeline Status Report ✓
  "oracle" → (not in hot cache)

memory/glossary.md lookup:
  "oracle" → Oracle Systems deal ($2.3M) ✓

Now Claude can act with full context.

Adding Memory

When user says "remember this" or "X means Y":

  1. Glossary items (acronyms, terms, shorthand):

    • Add to memory/glossary.md
    • If frequently used, add to CLAUDE.md Quick Glossary
  2. People:

    • Create/update memory/people/{name}.md
    • Add to CLAUDE.md Key People if important
    • Capture nicknames - critical for decoding
  3. Projects:

    • Create/update memory/projects/{name}.md
    • Add to CLAUDE.md Active Projects if current
    • Capture codenames - "Phoenix", "the migration", etc.
  4. Preferences: Add to CLAUDE.md Preferences section

Recalling Memory

When user asks "who is X" or "what does X mean":

  1. Check CLAUDE.md first
  2. Check memory/ for full detail
  3. If not found: "I don't know what X means yet. Can you tell me?"

Progressive Disclosure

  1. Load CLAUDE.md for quick parsing of any request
  2. Dive into memory/ when you need full context for execution
  3. Example: drafting an email to todd about the PSR
    • CLAUDE.md tells you Todd = Todd Martinez, PSR = Pipeline Status Report
    • memory/people/todd-martinez.md tells you he prefers Slack, is direct

Bootstrapping

Use /productivity:start to initialize by scanning your chat, calendar, email, and documents. Extracts people, projects, and starts building the glossary.

Conventions

  • Bold terms in CLAUDE.md for scannability
  • Keep CLAUDE.md under ~100 lines (the "hot 30" rule)
  • Filenames: lowercase, hyphens (todd-martinez.md, project-phoenix.md)
  • Always capture nicknames and alternate names
  • Glossary tables for easy lookup
  • When something's used frequently, promote it to CLAUDE.md
  • When something goes stale, demote it to memory/ only

What Goes Where

TypeCLAUDE.md (Hot Cache)memory/ (Full Storage)
PersonTop ~30 frequent contactsglossary.md + people/{name}.md
Acronym/term~30 most commonglossary.md (complete list)
ProjectActive projects onlyglossary.md + projects/{name}.md
NicknameIn Key People if top 30glossary.md (all nicknames)
Company contextQuick reference onlycontext/company.md
PreferencesAll preferences-
Historical/stale✗ Remove✓ Keep in memory/

Promotion / Demotion

Promote to CLAUDE.md when:

  • You use a term/person frequently
  • It's part of active work

Demote to memory/ only when:

  • Project completed
  • Person no longer frequent contact
  • Term rarely used

This keeps CLAUDE.md fresh and relevant.