memem-doctor
Run a preflight health check on memem — Python version, mcp dep, claude CLI, vault writability, capabilities. Use when the user reports memem misbehaving, has…
Re-show the full memem welcome screen regardless of whether the user has seen it before. Use when the user wants to see the intro, tutorial, or welcome again.
$ npx -y skills add TT-Wang/memem --skill memem-welcome --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/memem-welcomeContext preview
The summary Claude sees to decide when to auto-load this skill.
Re-show the full memem welcome screen regardless of whether the user has seen it before. Use when the user wants to see the intro, tutorial, or welcome again.
name: memem-welcome description: Re-show the full memem welcome screen regardless of whether the user has seen it before. Use when the user wants to see the intro, tutorial, or welcome again. allowed-tools: [Bash, Read]
Force-display the full memem welcome (the brand-new-user view), even if the user has already dismissed it. This is the "re-open walkthrough" handle — it exists so returning users who want the intro again don't have to delete state files manually.
**Step 1 — Print the banner:**
███╗ ███╗███████╗███╗ ███╗███████╗███╗ ███╗ ████╗ ████║██╔════╝████╗ ████║██╔════╝████╗ ████║ ██╔████╔██║█████╗ ██╔████╔██║█████╗ ██╔████╔██║ ██║╚██╔╝██║██╔══╝ ██║╚██╔╝██║██╔══╝ ██║╚██╔╝██║ ██║ ╚═╝ ██║███████╗██║ ╚═╝ ██║███████╗██║ ╚═╝ ██║ ╚═╝ ╚═╝╚══════╝╚═╝ ╚═╝╚══════╝╚═╝ ╚═╝ persistent memory for Claude Code
**Step 2 — One-sentence pitch:**
> memem gives Claude Code persistent memory across sessions. It extracts durable lessons (decisions, conventions, bug fixes, preferences) from your completed sessions into markdown files, then surfaces the relevant ones at the start of each new session.
**Step 3 — How it works:**
1. You work normally in Claude Code — nothing to do. 2. Once you opt in via `/memem-mine` or `/memem-mine-history`, the Stop hook fires on every conversation turn and spawns a detached `mine_delta` subprocess. 3. `mine_delta` extracts durable memories from the new turns via Claude Haiku and writes them to `~/obsidian-brain/memem/memories/` — memories appear seconds after each turn ends. No background daemon, no 5-minute wait. 4. Your next session starts with relevant context pre-loaded from memory — no re-explaining the project.
**Step 4 — Mining options:**
Or just tell Claude:
If the user is unsure, recommend **`/memem-mine`** as the default.
**Step 5 — Commands and tools:**
**Slash commands:**
**MCP tools** (Claude calls these automatically when useful):
**Step 6 — Optional Obsidian note:**
Memories are plain markdown files at `~/obsidian-brain/memem/memories/`. Open that folder as an Obsidian vault for graph view and backlinks. memem works identically without Obsidian.
**Step 7 — First action suggestion:**
If the user asks "what should I do now?" or seems undecided, answer with one short recommendation:
> Start with `/memem-mine`. It enables memory for new sessions going forward without spending Haiku credits on old history.
**Step 8 — Opt-out:**
To opt out of event-triggered mining: `rm ~/.memem/.miner-opted-in`. No daemon to stop — the Stop hook just no-ops when the marker is missing.
Persistent, self-evolving memory for Claude Code. Stop re-explaining your project every session. <!-- The Glama badge URL below intentionally uses the legacy cortex-plugin slug.
Run a preflight health check on memem — Python version, mcp dep, claude CLI, vault writability, capabilities. Use when the user reports memem misbehaving, has…
Mine ALL existing Claude Code sessions, including history from before memem was installed.
Opt in to memem's event-triggered mining. New sessions are mined automatically via the Stop hook.
Show detailed memem memory system status — memory count, projects, search DB, miner health.