Install
openclaw skills install smart-memory-queryEnforce proactive, query-optimized memory_search usage. Must run memory_search when (1) prior context is referenced, (2) a new task starts, or (3) a proper n...
openclaw skills install smart-memory-querymemory_search when any of these applyIf unsure, search. Missed context costs more than one extra search. If multiple triggers fire, run separate searches per trigger.
memory_search per angle, with 2–4 tokens per query.T1 “We changed to keep iCloud downloads before, right?”
memory_search("user preference root-cause config first suggestion keep iCloud downloads")memory_search("iCloud download setting") + memory_search("problem-solving preference")T1 “Didn’t we plan to migrate to a better structure first?”
memory_search("better structure migration FTS path title RRF exact tie-break")memory_search("FTS structure migration") + memory_search("RRF tie-break design")T2 “Let’s start Paddle payment integration.”
memory_searchmemory_search("Paddle payment") + memory_search("payment integration decision")T3 “OpenClaw search quality is still poor.”
memory_search("OpenClaw search quality is still poor")memory_search("OpenClaw search") + memory_search("search quality tuning")T1+T3 “What happened after switching to bge-m3?”
memory_search("what happened after switching to bge-m3")memory_search("bge-m3 migration result") + memory_search("embedding model change")T2 “Set up the new project documentation structure.”
memory_searchmemory_search("documentation structure preference") + memory_search("project template")