$ loading_
Build a two-tier memory system so AI understands team context and shorthand.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "memory-management" skill from askskill: 1. Download https://raw.githubusercontent.com/anthropics/knowledge-work-plugins/main/productivity/skills/memory-management/SKILL.md 2. Save it as ~/.claude/skills/memory-management/SKILL.md 3. Reload skills and tell me it's ready
Design a two-tier memory structure for our AI collaboration setup: use CLAUDE.md for current project working memory and the memory/ directory for the long-term knowledge base. Cover team acronyms, internal project codenames, member nicknames, and common phrases, and provide a folder structure plus maintenance rules.
A practical memory architecture with file organization, terminology capture methods, and update guidelines.
Our team often uses shorthand like 'Mars,' 'Little Blue,' 'QBR,' and 'Wang’s version.' Create a memory template so the AI can correctly identify the related projects, people, meetings, and document versions, and show how to write them into CLAUDE.md and memory/.
A memory template for internal shorthand with example entries for working and long-term memory.
Design a memory management workflow so the AI can retain our working context, preferences, and agreed language across sessions. Separate short-term task context from long-term team knowledge, and provide recommendations for adding, archiving, deduplicating, and reusing memory.
A memory management workflow that improves collaboration continuity and long-term team reuse.
Memory makes Claude your workplace collaborator - someone who speaks your internal language.
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:
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):
memory/glossary.md (Full Glossary):
memory/people/, projects/, context/:
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/.
CLAUDE.md in current working directorymemory/ subdirectoryUse 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
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
…
Embed Zoom meeting features into web apps with full or component-based integration.
Build weighted sales forecasts with scenario planning, commit splits, and gap analysis.
Prepare compliant month-end journal entries with debits, credits, and support.
Analyze compensation bands, offer competitiveness, equity grants, and retention risks.
Track hiring stages, update candidate status, and monitor pipeline counts.
Research competitors and compare positioning, messaging, gaps, opportunities, and threats.
Give Claude Code persistent cross-device memory with semantic recall and self-maintenance.
Add per-repo persistent memory with versioned retrieval for Claude Code.
Build a lightweight memory system for Claude Code using hooks and Markdown.
Persist team context across Claude Code sessions with synced memory files.
Enable persistent memory across Claude Code sessions for preferences, notes, and skills.
Provides local persistent memory for coding agents with low-cost context retrieval.