Memory Management

by anthropicsae1513ea94dcNo license27K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated today

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.

FeaturedInstructions onlyProductivity & WorkflowAI & Agents
AI-generated overview

Two-tier memory system that decodes workplace shorthand, acronyms and nicknames so an agent understands internal requests.

What it does
This skill defines a two-tier memory structure for an AI agent: a CLAUDE.md hot cache of roughly 30 frequent people, terms and active projects, plus a memory/ directory holding a full glossary, people profiles, project files and company context. It specifies lookup flow, file formats, and rules for adding, recalling, promoting and demoting entries. The deliverable is the memory file layout and the decoding procedure, not executable code.
When to use it
Use it when an agent must interpret internal shorthand, acronyms, nicknames or project codenames in a workplace setting. It also fits when setting up or maintaining persistent context files about people, projects and company terminology.
Requirements
No scripts; instructions only. It expects a working directory where CLAUDE.md and a memory/ subdirectory can be created and read, and it references a /productivity:start command for bootstrapping from chat, calendar, email and documents.

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.

markdown
# 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:

markdown
# 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:

markdown
# 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:

markdown
# Project Phoenix
**Codename:** Phoenix**Also called:** "the migration"**Status:** Active, launching Q2
## What It IsDatabase 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:

markdown
# 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 cases2. memory/glossary.md        → Full glossary if not in hot cache3. memory/people/, projects/ → Rich detail when needed4. 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.

Source and attribution

Source:anthropics/knowledge-work-pluginsinproductivity/skills/memory-managementat commitae1513e

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

More from anthropics/knowledge-work-plugins

Ticket Deflector

anthropics

Featured

Reads a forwarded customer email or ticket, pulls order and refund status from a payments connector (PayPal, Square, or Stripe) or Shopify, account history from the CRM, and open tickets from a support desk (Zoho Desk), drafts a tone-matched reply in the owner's writing voice, and can issue a refund through the payments connector with explicit owner approval. With Shopify connected it also runs a proactive order-triage mode that surfaces orders needing attention — unfulfilled past the promised window, payment problems, pending refunds, stuck shipments — and drafts the next action for each before the customer has to ask. Use when the user says "draft a response," "answer this customer," "where's my order," "I want a refund," "check my orders," or "anything about to blow up."

Awaiting classification27Kupdated today

Tax Season Organizer

anthropics

Featured

Prepares tax-season materials for the owner's accountant, not tax advice. US federal tax; a non-US business gets its closed-books packet instead. Two modes: (1) quarterly estimated tax from YTD net income in the ledger (MYOB, NetSuite, QuickBooks, Xero, or Zoho Books); (2) year-end 1099 prep, scanning the ledger, PayPal, and Stripe for contractors paid over USD 600 into a 1099-NEC list with missing W-9 flags. Any tax request routes first to /tax-prep, which confirms the books are closed and reconciled before running this skill. Use this skill directly only when the owner says the period's books are already closed: "books are closed, now do the 1099s," "run the quarterly estimate off the closed numbers," or "just the contractor W-9 list."

Awaiting classification27Kupdated today

Tax Prep

anthropics

Featured

Prepares tax materials from closed books: a quarterly estimated payment breakdown or a year-end 1099-NEC list and accountant packet.

Business & Finance27Kupdated today

Smb Onboard

anthropics

Featured

Guides a small-business owner through first-time setup: connecting tools, running a value-proof recipe, capturing business context, and setting a weekly…

Productivity & Workflow27Kupdated today

Smb Router

anthropics

Featured

Routes a small-business owner's request to the right plugin skill or command and explains what is available.

Productivity & Workflow27Kupdated today

Month End Prep

anthropics

Featured

Reconciles the accounting ledger (MYOB, NetSuite, QuickBooks, Xero, or Zoho Books) against PayPal, Shopify, Square, and Stripe settlements, flags transactions that need attention, suspicious duplicates, and missing receipts, then writes a plain-English P&L narrative and exports a close packet (xlsx + one-page PDF). This is the first link of the /close-month command; a request to close the month or the books routes there, and the command runs this skill before refreshing the forecast and distributing the packet. Use this skill directly only when the owner wants the reconciliation alone, with no forecast refresh and no distribution: "just reconcile, no packet," "what's missing from the books," "flag the duplicates and missing receipts," or "write the P&L narrative for this month."

Awaiting classification27Kupdated today

More in Productivity & Workflow

Notion Spec To Implementation

openai

Featured

Turns Notion specs into implementation plans, linked tasks, and progress updates inside Notion.

Productivity & Workflow27Kupdated 4 weeks ago

Notion Research Documentation

openai

Featured

Researches Notion pages and synthesizes findings into cited briefs, comparisons, or reports published back to Notion.

Productivity & Workflow27Kupdated 4 weeks ago

Notion Meeting Intelligence

openai

Featured

Prepares meeting agendas and pre-reads using Notion context and research, tailored to attendees and meeting type.

Productivity & Workflow27Kupdated 4 weeks ago

Linear

openai

Featured

Guides an agent through managing Linear issues, projects, cycles and team workflows via the Linear MCP server.

Productivity & Workflow27Kupdated 4 weeks ago

Define Goal

openai

Featured

Turns a vague intention into a concrete, measurable goal with verification evidence and scope bounds.

Productivity & Workflow27Kupdated 4 weeks ago

Plan Payroll

anthropics

Featured

Chains cash forecasting, overdue-invoice reminders, and payroll run staging so an owner can confirm payroll is covered before submitting it.

Productivity & Workflow27Kupdated today