skill

conversation-memory · davila7 — Claude Code skill: what it does, how to install

Q: How to install conversation-memory in Claude Code?

Run `npx claude-code-templates@latest --skill ai-research/conversation-memory` in your project terminal. Alternatively, install it with `npx skills add davila7/claude-code-templates --skill conversation-memory -a claude-code`.

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

Install into Claude Code · claude-code-templates All methods and platforms ↓

npx claude-code-templates@latest --skill ai-research/conversation-memory

Open on GitHub

What conversation-memory 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.

What it helps with

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 for the agent

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

How to install conversation-memory

1claude-code-templates

npx claude-code-templates@latest --skill ai-research/conversation-memory

2Skills CLI (Vercel)

npx skills add davila7/claude-code-templates --skill conversation-memory -a claude-code

3Manually: put the files in place

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

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

Manually: put the files in place

.agents/skills/conversation-memory/SKILL.md

For all projects use ~/.agents/skills/

Manually: put the files in place

.cursor/skills/conversation-memory/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install davila7/claude-code-templates conversation-memory

2Manually: put the files in place

.github/skills/conversation-memory/SKILL.md

Platform CLI

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

Manually: put the files in place

.devin/skills/conversation-memory/SKILL.md

The legacy .windsurf/skills/ path still works

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about conversation-memory

How to install conversation-memory in Claude Code?

Run npx claude-code-templates@latest --skill ai-research/conversation-memory in your project terminal. Alternatively, install it with npx skills add davila7/claude-code-templates --skill conversation-memory -a claude-code.

What memory tiers does this skill cover?

It provides patterns for tiered memory architectures, dividing context into short-term sessions, persistent long-term storage, and dedicated entity records.

What is the main security risk outlined in the guide?

Lack of strict per-user boundaries can leak sensitive memories from one conversation into another user session.

conversation-memory by other authors comes first.

conversation-memory sickn33 Architectural patterns for LLM conversation memory: session buffers, persistent storage, and entity tracking. CX Codex +1 1,500installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. 1,052,851installs ask-matt Matt Pocock Routes you to the right Matt Pocock skill or flow for the task at hand. Use it when you need a starting point for a feature, prototype, incoming issue, or hard bug. 766,587installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. 711,230installs writing-plans Jesse Vincent This skill turns requirements for a multi-step task into an implementation plan before code changes begin. It helps when another engineer needs exact files, interfaces, and checks. CX Codex 282,859installs caveman-review JuliusBrussee Turns code review comments into one line per finding: location, problem, fix. Useful when a diff or PR needs a fast pass without the filler. CX Codex +1 411,800installs caveman-compress JuliusBrussee Compresses CLAUDE.md, todo lists, and other prose files into a shorter format while retaining a readable backup. CX Codex +1 411,500installs

From the same set804

The whole set →

plotly Teaches Claude Code to generate interactive Python charts, multi-panel dashboards, and statistical plots with Plotly. 383installs add-authentication-system Build an authentication layer for an existing application with a selected sign-in method. The command covers user accounts, session handling, access rules, and common security controls. 382installs nextjs-middleware-creator Generates modular Next.js middleware and helper scripts for routing. It sets up JWT authentication, rate limiting, and security headers. 381installs invoice-organizer Sorts invoices, receipts and bank statements into folders, renames every file to one pattern and writes a CSV your accountant can use. 380installs agent-evaluation Evaluate an agent’s behavior, capabilities, and consistency across runs. Use the skill when you need to test an agent beyond a single benchmark result. 378installs interactive-documentation A slash command that builds documentation with runnable code examples, playgrounds and API testing. Useful once a plain README stops being enough. 372installs agents-crewai A Claude skill for assembling teams of autonomous agents with roles, memory, and sequential or hierarchical task execution. 371installs setup-formatting A Claude Code command that configures code formatters and enforces project style rules. Useful when setting up Prettier, Black, or rustfmt with git hooks. 370installs