Stats
Actions
Tags
From vault
This skill should be used when the user asks to "search notes", "find similar notes", "semantic search", "reindex vault", "rebuild index", "query vault", or needs to find notes by meaning rather than keywords.
How this skill is triggered — by the user, by Claude, or both
Slash command
/vault:sem-search-aThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> **Action skill** — Semantic search operations: BM25, vector search, hybrid search, reindexing.
Action skill — Semantic search operations: BM25, vector search, hybrid search, reindexing.
Search the vault by meaning using qmd, a local semantic search engine for markdown. BM25 + vector search + LLM re-ranking, all local. No cloud APIs.
If qmd is not installed:
brew install oven-sh/bun/bun # Bun runtime (if not installed)
bun install -g github:tobi/qmd # qmd itself
Register the vault as a collection:
qmd collection add "<vault-path>" --name vault
Build initial embeddings (~2GB models downloaded on first run):
qmd embed
Index stored at ~/.cache/qmd/index.sqlite — outside vault, no gitignore needed.
When invoked with --reindex or after batch changes to the vault:
qmd update # Re-index all collections (picks up new/changed/deleted files)
qmd embed # Rebuild vector embeddings (needed after first install or model change)
Use qmd update for routine reindexing. Use qmd embed only for initial setup or embedding model changes.
Fast keyword search. Good for finding notes that mention specific terms.
qmd search "prediction market pricing"
Vector similarity search. Finds conceptually related content even without keyword overlap.
qmd vsearch "how do agents maintain context across sessions"
This is the most useful search mode for finding related notes, confirming filing destinations, and discovering connections.
Combines BM25 + vector search + LLM re-ranking with 6 parallel searches. Highest quality but slower.
qmd query "what patterns emerge in agentic development workflows"
Use for thorough exploration. Overkill for quick lookups.
Retrieve the content of a specific document by path:
qmd get "2-Areas/ai-dev-ecosystem/2025-01-21_agentic-learnings.md"
Append format flags for programmatic use:
--json — JSON output (for parsing results)--csv — CSV output--md — Markdown formatted--files — File paths only (one per line, useful for piping)Example: qmd vsearch "agentic development" --files returns just paths.
| Need | Command | Speed |
|---|---|---|
| Find notes mentioning a term | qmd search | Fast |
| Find conceptually similar notes | qmd vsearch | Medium |
| Thorough exploration of a topic | qmd query | Slower |
| Confirm filing destination | qmd vsearch | Medium |
| Discover cross-area connections | qmd query | Slower |
qmd vsearch to confirm filing destinationsqmd vsearch or qmd query to find semantically similar notesqmd query for thorough connection discoveryqmd update after batch processingqmd collection add "<vault-path>" --name vaultqmd embed (first time takes a few minutes)qmd update to re-indexqmd collection list shows registered collectionsnpx claudepluginhub jsai23/claude-tooling --plugin vaultSearches, creates, and organizes notes in an Obsidian vault. Uses wikilinks and index notes. Relevant when managing a personal knowledge base or research notes.
Searches, creates, and organizes Obsidian notes using wikilinks and index notes for a flat vault structure.
Searches an Obsidian vault for prior knowledge, past decisions, and accumulated learnings, surfacing relevant notes before answering from general knowledge. Uses index-first retrieval with fallback content search.