# conversation-memory

Architecture guidelines for handling session context, entity facts, and persistent recall in LLM conversations.

- skill · `type=skill` · Claude Code · 380 installs
- Author: davila7
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/skills/ai-research/conversation-memory
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/conversation-memory

## What it does

This skill outlines patterns for handling conversational state across multiple tiers instead of dumping full histories into prompts. It details methods for updating entity attributes, consolidating dialogue records, and injecting only relevant facts into model prompts.

The guide highlights common pitfalls like maintaining an unindexed single storage or collecting raw transcripts without pruning. Without explicit lifecycle policies, unbounded memory pools inevitably degrade retrieval latency.

Multi-tenant isolation represents the main architectural risk. Failing to partition memory boundaries strictly by user identity causes cross-session data leaks.

## Install

### Claude Code (native platform)

1. **claude-code-templates**
```bash
npx claude-code-templates@latest --skill ai-research/conversation-memory
```

2. **Skills CLI (Vercel)**
```bash
npx skills add davila7/claude-code-templates --skill conversation-memory -a claude-code
```

3. **Manually: put the files in place**
- File: `~/.claude/skills/conversation-memory/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/conversation-memory/

### Codex

**Manually: put the files in place**
- File: `.agents/skills/conversation-memory/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

**Manually: put the files in place**
- File: `.cursor/skills/conversation-memory/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install davila7/claude-code-templates conversation-memory
```

2. **Manually: put the files in place**
- File: `.github/skills/conversation-memory/SKILL.md`

### Gemini CLI

**Platform CLI**
```bash
gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/ai-research/conversation-memory
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/conversation-memory/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/skills/ai-research/conversation-memory

## When to use it
- structure layered memory combining short-term and persistent records
- track and update entity attributes across extended dialogues
- filter retrieved memories before feeding them into prompt context
- enforce data isolation between different users

## Example prompts
- Design a tiered memory architecture for an assistant that needs to remember user preferences
- How should I handle entity updates so past facts get refreshed cleanly?
- Set up a pruning strategy to keep our conversation memory from slowing down queries

## Similar
- [setup-matt-pocock-skills](https://affpapa.org/en/nevibecode/skills/setup-matt-pocock-skills.md) — skill · 1052851 installs
- [ask-matt](https://affpapa.org/en/nevibecode/skills/ask-matt.md) — skill · 766587 installs
- [to-tickets](https://affpapa.org/en/nevibecode/skills/to-tickets.md) — skill · 711230 installs
- [writing-plans](https://affpapa.org/en/nevibecode/skills/writing-plans.md) — skill · 282859 installs
- [caveman-review](https://affpapa.org/en/nevibecode/skills/caveman-review.md) — skill · 411800 installs
- [caveman-compress](https://affpapa.org/en/nevibecode/skills/caveman-compress.md) — skill · 411500 installs

## Other versions with the same name
- [conversation-memory · sickn33](https://affpapa.org/en/nevibecode/skills/sickn33-conversation-memory.md) — 1500 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 804 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md