← ClaudeAtlas

memory-helplisted

This skill should be used when the agent needs a reminder of what the memory system can do, what commands are available, or how the memory system works. Responds to 'memory help', 'what memory commands exist', 'how does my memory work', 'what can I remember', or any confusion about the memory system's capabilities. Also invoked by memory-boot after first boot to teach the agent the system.
pyros-projects/limitless · ★ 9 · AI & Automation · score 75
Install: claude install-skill pyros-projects/limitless
# Memory Help > **BETA** — This memory system is in active testing. If you encounter bugs, confusing behavior, or have suggestions, run: > `codies-memory feedback "describe what happened"` — your feedback is saved and reviewed. ## What This System Is You have a persistent file-based memory system. It stores what you learn, observe, and decide across sessions. Your vault lives at `~/.memory/<your-agent-name>/`. Every command requires `--agent <your-agent-name>`. There are two scopes: - **Global** — knowledge that applies across all projects (your identity, cross-project lessons, reflections) - **Project** — knowledge specific to one project (observations, decisions, session summaries) There are also two practical operating modes: - **Standalone mode** — works with the canonical vault only - **Full mode** — recommended: canonical vault plus QMD retrieval QMD is recommended when available because recall becomes faster, more token-efficient, and semantic across multiple memory stores. If the user wants that full mode and does not have QMD yet, offer to help install it. --- ## Concepts Read this section carefully. These terms have specific meanings in this system. ### Record Types | Type | What it is | Scope | When to create | |------|-----------|-------|----------------| | **inbox** | A raw observation or note. Unprocessed. | project | When you notice something worth remembering but haven't decided what it means yet. Use `capture`. | | **thread** | An ongoing investiga