This is essentially a reference manual for Claude to understand how MemOS works under the hood. It explains the auto-recall system that injects memories at the start of each turn, then walks through when to manually call memory_search, memory_get, memory_share, and the rest of the tool suite. The guidance on two sharing planes (local agent vs team) is helpful for avoiding confusion. If you're building workflows where Claude needs to search past conversations, pull task summaries, or share context across agents, this keeps the model from guessing at the API semantics. It's verbose but thorough, covering both the happy path and edge cases like when auto-recall returns nothing.
npx skills add https://github.com/memtensor/memos --skill memos-memory-guide