Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From mnemonic
Re-indexes mnemonic memories for qmd semantic search by rebuilding BM25 full-text index and regenerating vector embeddings. Use after capturing memories, bulk imports, file edits, or periodically.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mnemonic:qmd-reindexThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Re-index mnemonic memories for qmd search.
Re-index mnemonic memories for qmd search.
qmd update && qmd embed
qmd update — rebuilds the BM25 full-text indexqmd embed — regenerates vector embeddings for semantic search# Index only (skip embeddings — faster)
qmd update
# Specific collection only
qmd update -c mnemonic-zircote && qmd embed -c mnemonic-zircote
# Check status after
qmd status
/mnemonic:capture sessionsIndexing is not automatic. Searches will miss memories added since the last index.
npx claudepluginhub modeled-information-format/mnemonicSets up @tobilu/qmd for semantic search over mnemonic memories: registers collections from MNEMONIC_ROOT, builds indexes with qmd update, generates embeddings. One-time per-machine bootstrap.
Upgrades grep-based memory_search with QMD's hybrid BM25 + vector semantic search + LLM re-ranking. Fully local, no API keys needed.
Indexes local files and searches them using BM25, vector embeddings, and hybrid reranking. Includes MCP mode for tool integration.