Stats
Actions
Tags
From smart-mcps
Search agentmemory for past observations, sessions, and learnings about a topic. Use when the user says "recall", "remember", "what did we do", or needs context from past sessions.
How this skill is triggered — by the user, by Claude, or both
Slash command
/smart-mcps:agentmemory-recall [search query][search query]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
The user wants to recall past context about: $ARGUMENTS
The user wants to recall past context about: $ARGUMENTS
smart-mcps-agentmemory find "$ARGUMENTS" --limit 10
If the command returns zero observations, retry with --depth deep (makes two extra API calls — slower but pulls from all historical data):
smart-mcps-agentmemory find "$ARGUMENTS" --limit 10 --depth deep
The output is JSON with three arrays: observations, memories, lessons.
Present results in readable prose, not raw JSON. Highlight what is most relevant to $ARGUMENTS.
~/.agentmemory/start.sh (or docker compose up -d if using Docker).--depth deep: no prior context exists for this project/topic yet. Say so clearly — do not hallucinate observations.Never invent or infer observations. Only present what the command actually returned.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub giovani-merlin/smart_mcps --plugin smart-mcps