Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot official · Anthropic

memory-management — Claude Code skill: project memory

This skill organizes workplace shorthand, names, and project details into files an agent can consult. It fits projects where requests rely on an internal vocabulary and shared context.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add anthropics/knowledge-work-plugins --skill memory-management -a claude-code
Open on GitHub

What memory-management does

The memory has two tiers. CLAUDE.md holds frequently used names, terms, active projects, and preferences. The fuller glossary lives in memory/glossary.md; detailed records go in memory/people/, memory/projects/, and memory/context/. The agent checks the short reference first, then looks up more detail as needed.

For a request such as asking Todd about the PSR for Phoenix, the skill directs the agent to check CLAUDE.md, then the glossary and relevant detail files. If a term is still unclear, it asks the user. New information is filed by type, with frequently used terms and key contacts also added to working memory.

The setup relies on CLAUDE.md and the memory/ directory in the project. That matters when choosing where to use it: the examples and lookup flow expect those paths and Markdown files.

What it helps with

  • decode internal shorthand in requests
  • match a nickname to a colleague’s profile
  • look up project details by codename
  • save new terms and preferences for later

Example prompts for the agent

  • Ask Todd to prepare the PSR for Phoenix using the project memory files.
  • Remember that “T” means Todd Martinez and update the person’s profile.
  • What does “the migration” mean? Check the glossary and project files.

How to install memory-management

1Skills CLI (Vercel)

npx skills add anthropics/knowledge-work-plugins --skill memory-management -a claude-code

2Manually: put the files in place

~/.claude/skills/memory-management/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/memory-management/

From the same set133

The whole set →
data-visualization official anthropics Selects chart types based on data structure and produces Python visualization code in matplotlib, seaborn, and plotly. Useful for reports and research figures. Claude Code CX Codex Cursor +1 13,700installs documentation official anthropics A skill for technical writing that drafts READMEs, API references, runbooks, architecture docs and onboarding guides. Useful when the code exists but the description does not. Claude Code CX Codex Cursor +1 10,300installs build-dashboard official anthropics Builds a self-contained HTML dashboard with Chart.js charts, KPI cards, and filterable tables. Useful for turning raw data or queries into a standalone browser report. Claude Code CX Codex Cursor +1 9,100installs task-management official anthropics Tracks commitments, active work, and follow-ups in a local TASKS.md file. Useful when managing project to-dos directly from the AI coding chat. Claude Code CX Codex Cursor +1 7,200installs architecture official anthropics Writes an Architecture Decision Record or reviews a system design: options, trade-offs, consequences. Useful when you have to pick between technologies. Claude Code CX Codex Cursor +1 6,700installs knowledge-synthesis official anthropics Merges search results across chats, emails, and documents into deduplicated answers with source attribution. Flags conflicting facts and scores source reliability. Claude Code CX Codex Cursor +1 6,400installs testing-strategy official anthropics This skill designs testing strategies and test plans for a project. Use it when you need test types, coverage goals, or gaps in existing checks. Claude Code CX Codex Cursor +1 6,400installs view-pdf official anthropics Opens PDFs in an interactive viewer for shared markup, form filling, highlights, stamps, and visual signatures. Use it when text reading alone is not enough. Claude Code CX Codex Cursor +1 6,300installs

Similar

research-ops affaan-m A skill that routes research requests to the right tool and labels every claim as sourced fact, your context, inference or recommendation. Useful when the answer depends on what is true now. Claude Code CX Codex Cursor +1 4,400installs skill-scout affaan-m Searches local skills, marketplaces, GitHub, and the web before you create or fork one. Use it to check whether a suitable workflow already exists. Claude Code CX Codex Cursor +1 4,400installs project-graveyard Shubham Saboo Scans your machine for abandoned side projects, diagnoses causes of death from git history, and picks the most viable repo to finish. Claude Code CX Codex Cursor +1 2,000installs refactor-plan official github This skill investigates a codebase and writes a step-by-step multi-file refactor plan before edits begin. Use it when the proposed change needs review first. GitHub Copilot 12,965installs memory-merger official github Moves mature notes from a domain memory file into its instruction file. Useful when project guidance grows through reviewed lessons. GitHub Copilot 12,846installs find-skills vercel-labs Discovers and installs agent skills from skills.sh directly inside your coding assistant. Handy when you need domain-specific workflows for a project. Claude Code CX Codex Cursor +1 4,000,000installs grill-me Matt Pocock grill-me interviews you about a plan or design to expose gaps and sharpen decisions. Use it before implementation starts. Claude Code 1,424,476installs grill-with-docs Matt Pocock This skill interviews you about a plan or design and creates ADRs and a glossary along the way. Use it when decisions need sharper definition. Claude Code 1,219,756installs

Questions about memory-management

How do I install memory-management in Claude Code?

Run npx skills add anthropics/knowledge-work-plugins --skill memory-management -a claude-code. The skill file is placed at ~/.claude/skills/memory-management/SKILL.md.

What does memory-management do?

It sets up a two-tier memory system: quick references go in CLAUDE.md, while the full glossary and detailed records about people and projects live in memory/. The agent checks these sources in order and asks when it cannot resolve a term.

Where should I keep full profiles and project details?

Store people’s profiles in memory/people/, project details in memory/projects/, and company, team, or tool context in memory/context/.

Source text

SKILL.md · Apache-2.0
---
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.

```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 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:**
```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 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

| Type | CLAUDE.md (Hot Cache) | memory/ (Full Storage) |
|------|----------------------|------------------------|
| Person | Top ~30 frequent contacts | glossary.md + people/{name}.md |
| Acronym/term | ~30 most common | glossary.md (complete list) |
| Project | Active projects only | glossary.md + projects/{name}.md |
| Nickname | In Key People if top 30 | glossary.md (all nicknames) |
| Company context | Quick reference only | context/company.md |
| Preferences | All 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.

© anthropics · Apache-2.0 · anthropics/knowledge-work-plugins

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor