qmd

Index and search local knowledge bases with hybrid retrieval.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/travelinman1013/leroys-agent --skill qmd-travelinman1013
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/travelinman1013/leroys-agent/tree/main/optional-skills/research/qmd
Command: npx skills add https://github.com/travelinman1013/leroys-agent --skill qmd-travelinman1013

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Index and search personal knowledge bases locally using hybrid retrieval (BM25, vector search, and LLM reranking) to avoid cloud dependencies.

Core Features & Use Cases

  • Local indexing of markdown notes, documents, transcripts, and knowledge bases
  • Hybrid search that combines BM25, vector search, and LLM reranking for high-quality results
  • Optional MCP integration to expose tools to Hermes Agent and other clients

Quick Start

Install qmd globally, add your collections, and run your first query.

Frequently Asked Questions about qmd

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

FAQPage Schema
How do I search personal notes and documents locally without cloud dependencies?

You can index and search personal knowledge bases locally using hybrid retrieval combining BM25, vector search, and LLM reranking, avoiding cloud dependencies entirely.

What is hybrid retrieval and how does it work for local knowledge bases?

Hybrid retrieval combines BM25 keyword matching, vector search for semantic similarity, and LLM reranking to deliver high-quality search results from local knowledge bases.

Can I use local vector search and BM25 for offline document indexing?

Yes, this Skill supports offline execution by indexing documents, notes, and transcripts locally, utilizing configurable embedding pipelines for vector search and BM25.

How do I integrate local knowledge search with an MCP client?

Optional MCP integration exposes your local collections and search tools to MCP clients like Hermes Agent, enabling external tool access to your indexed knowledge base.

Does this local search tool support managing multiple document collections?

Yes, it supports indexing and searching across multiple collections, allowing you to manage distinct knowledge bases for notes, transcripts, and project documents.