skills.rest
JSai23
JSai23COMMUNITY
Explore all skills by this author →
GitHub

vault-sem-search-a

Enable semantic search of local vault notes using qmd with BM25, vector search, and LLM re-ranking.

1|Updated Jan 25, 2026
Search Tags:#embeddings#search#vault#notes#semantic#qmd
One-click install
npx skills add https://github.com/JSai23/claude-tooling --skill vault-sem-search-a
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vault-sem-search-a
Source: https://github.com/JSai23/claude-tooling/tree/main/compiled/vault/agentskills/vault-sem-search-a
Command: npx skills add https://github.com/JSai23/claude-tooling --skill vault-sem-search-a

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables semantic search of vault notes by meaning using a local search engine, avoiding brittle keyword-only queries and enabling richer retrieval.

Core Features & Use Cases

  • Semantic search: local BM25 + vector search + LLM re-ranking to surface conceptually related vault notes.
  • Hybrid workflows: supports keyword and semantic queries, rapid reindexing, and document retrieval.
  • Use Case: quickly locate context for a note about a topic even if the exact terms differ.

Quick Start

Use this skill to search vault notes semantically with qmd and retrieve the most relevant documents.

Frequently Asked Questions about vault-sem-search-a

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I search my local vault notes by meaning instead of exact keywords?▼

Semantic search finds conceptually related vault notes by combining local BM25 keyword search, vector embeddings, and LLM re-ranking, surfacing context even when exact terms differ.

Can I run semantic search locally without sending my vault notes to an external server?▼

Yes, the semantic search runs locally using the qmd engine and stores all vector embeddings directly on your device, ensuring your vault notes remain private and secure.

What is the best way to find context in my notes if the exact wording does not match my query?▼

Using hybrid search is the best way to locate context in your notes, as it combines BM25 keyword matching with vector-based semantic retrieval and LLM re-ranking to find relevant documents.

How do I reindex my vault notes for semantic search after adding new content?▼

You can perform rapid reindexing directly through the qmd engine to update local vector embeddings, ensuring newly added vault notes are immediately retrievable by semantic queries.

Does semantic search with vector embeddings work with my existing local vault setup?▼

Yes, this semantic search approach applies to local vaults and requires no external dependencies, allowing you to perform keyword, vector-based, and hybrid document retrieval directly.

Why does standard keyword search miss conceptually related notes in my vault?▼

Standard keyword search is brittle and only matches exact terms, whereas semantic search uses vector embeddings and LLM re-ranking to understand the underlying meaning and surface related vault notes.

Related Skills

Explore More Software Engineering Skills→
cdeistopenedcdeistopened
2

local-markdown-search

Index and search local Markdown collections with BM25 and vector embeddings.

Community
Intermediate
jhl-labsjhl-labs
50

RAG & Vector Search

Retrieve relevant documents and augment LLM prompts with vector search.

Official
Advanced
steipetesteipete
385.7k

qmd

Index local files and search them with BM25, vector, and hybrid queries.

Community
Advanced
JuanMS20JuanMS20

qmd

Index Markdown and text files for local hybrid search with BM25, vectors, and reranking.

Community
Advanced