Claude Skills by Lians-ai

Use Lians when a user wants Cursor to remember durable preferences, decisions, or prior work across chats, or wants to inspect, correct, or forget saved memory.

Use Lians memory from Claude Code for durable recall, resuming unfinished work across agents or sessions, repository verification, point-in-time reconstruction, lineage inspection, lookahead checks, and explicitly confirmed erasure.

Use Lians Memory when the user asks to remember a durable project fact or decision, recall prior project context, remove a specific stored memory from active service storage after confirmation, or continue work that depends on explicitly saved context. Do not use it for transient scratch text or whole-conversation capture.

Set up, diagnose, or use Lians Memory when the user asks Codex to remember durable project information, resume unfinished work, verify repository changes, continue across agents or sessions, check the memory plugin, or optimize repeated memory-heavy work.

Wire Lians memory into an existing agent codebase, test-first and minimal-diff. Use when the user asks to add persistent/compliance memory to their agent, integrate Lians, or replace a vector store with bitemporal memory.

Use Lians financial-grade agent memory - store and recall facts with a bitemporal model so stale revisions never contaminate context. Use whenever an agent needs persistent memory in finance, healthcare, or legal work, or when a task asks "what did we know on/before <date>", needs an audit trail, or must erase a data subject.