skills.rest
MagicWifiMoney
MagicWifiMoneyCOMMUNITY
Explore all skills by this author →
𝕏@giebzGitHub

qmd

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

Updated Aug 27, 2026
Search Tags:#embeddings#search#mcp#vector-search#local-indexing#bm25
One-click install
npx skills add https://github.com/MagicWifiMoney/openclaw-starter-kit --skill qmd-magicwifimoney
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/MagicWifiMoney/openclaw-starter-kit/tree/main/skills-custom/extras/qmd
Command: npx skills add https://github.com/MagicWifiMoney/openclaw-starter-kit --skill qmd-magicwifimoney

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

qmd provides a fast, local way to index and search files so you can find relevant documents without relying on cloud search services or manual grepping.

Core Features & Use Cases

  • Local indexing: Create collections from directories and maintain an on-disk index for offline search.
  • Multiple retrieval modes: Support for BM25, vector search, and hybrid rerank workflows to improve relevance.
  • MCP and CLI-first: Operates as a command-line tool with an MCP mode for integration into mission control or automated pipelines.
  • Use Case: Ideal for personal knowledge bases, team docs, research archives, or project repositories where private, high-relevance search is required.

Quick Start

Add a folder as a collection with qmd collection add /path --name docs --mask **/*.md then run qmd update and use qmd search "your query" to find matching documents.

Frequently Asked Questions about qmd

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

FAQPage Schema
How do I index and search local files without relying on cloud services?▼

You can perform local indexing and search offline by using a CLI tool to create document collections from directories, storing the index data on disk for fast retrieval without cloud dependencies.

What is the best way to combine BM25 ranking with vector search for a document collection?▼

Hybrid search workflows combine BM25 keyword ranking with vector similarity and reranking to improve document relevance, easily executed via command line queries against a local index.

Do I need Ollama to run local vector search and reranking on my knowledge base?▼

Yes, local vector search and reranking require Ollama to generate embeddings, while the index data itself is stored locally under the cache directory for offline access.

Can I integrate local file search into automated pipelines or mission control?▼

Yes, the search CLI includes an MCP mode that allows integration into mission control or automated pipelines, supporting BM25, vector, and hybrid queries for connected workflows.

How do I add a project directory as a searchable collection from the command line?▼

Add a folder as a collection by running the CLI command with the directory path and a specified name, apply a file mask for desired extensions, update the index, and execute a search query.

Does local semantic search work offline for private team knowledge bases?▼

Yes, local semantic search operates offline for private knowledge bases by indexing files on disk and using local models for embeddings, ensuring private, high-relevance search without internet access.

Related Skills

Explore More Software Engineering Skills→
caiazzopcaiazzop

qmd

Index and search local files using BM25, vector embeddings, and reranking.

Community
Intermediate
rukikotoorukikotoo
6

rag

Query the econometrics RAG knowledge base to retrieve relevant document chunks.

Community
Intermediate
steipetesteipete
385.7k

qmd

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

Community
Advanced
christian-bromannchristian-bromann
3

langchain-embeddings-vectorstores

Convert text into embeddings and index them into vector stores for semantic search.

Community
Advanced