skills.rest
jason660519
jason660519COMMUNITY
Explore all skills by this author →
GitHub

qmd

Search local notes and transcripts with hybrid BM25, vector, and reranking retrieval.

Updated May 11, 2026
Search Tags:#MCP#search#notes#local#knowledge-base#vector-search
One-click install
npx skills add https://github.com/jason660519/Project-Manager --skill qmd-jason660519
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/jason660519/Project-Manager/tree/main/hermes-agent/optional-skills/research/qmd
Command: npx skills add https://github.com/jason660519/Project-Manager --skill qmd-jason660519

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local knowledge bases, notes, and transcripts are often scattered and hard to search efficiently; qmd provides a local, hybrid retrieval engine that combines traditional keyword search, vector embeddings, and LLM reranking to deliver fast and relevant results.

Core Features & Use Cases

  • Local, on-device search across markdown/text collections including notes and meeting transcripts.
  • Hybrid retrieval that combines BM25, vector search, and reranking for high-quality results.
  • Seamless CLI and MCP integration for Hermes Agent workflows.
  • Use Case: Quickly locate all mentions of a topic across notes and meeting transcripts without uploading data to the cloud.

Quick Start

Install qmd and add a local collection to start performing fast local searches.

Frequently Asked Questions about qmd

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

FAQPage Schema
How do I search local notes and transcripts without uploading data to the cloud?▼

Local search for notes and transcripts is achieved through an on-device hybrid retrieval engine. It performs local indexing and zero-cloud operations to keep your knowledge base completely private.

What is hybrid retrieval and how does it improve local knowledge base search?▼

Hybrid retrieval improves local knowledge base search by combining BM25 keyword matching, vector search, and LLM reranking. This approach delivers faster and more relevant results than single-method searches.

Can I integrate local vector search into Hermes Agent workflows via MCP?▼

Yes, local vector search integrates seamlessly into Hermes Agent workflows via MCP and CLI. This allows automated agents to query your local knowledge base directly in offline environments.

What's the best way to locate specific topics across scattered markdown files?▼

The best way to locate topics across scattered markdown files is using a local hybrid search tool. It indexes markdown and text collections to quickly find all mentions of a topic without manual sorting.

Do I need an internet connection for LLM reranking during local searches?▼

No internet connection is needed for LLM reranking during local searches. The engine is designed for zero-cloud operation, supporting local indexing and vector embeddings entirely on-device.

Related Skills

Explore More Data & Analytics Skills→
cdeistopenedcdeistopened
2

local-markdown-search

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

Community
Intermediate
tangzheng202202tangzheng202202
1

social-media

Automate X/Twitter posting, timeline reading, and mention monitoring workflows.

Community
Intermediate
jleechanorgjleechanorg

native-mcp

Discover and register MCP server tools into Hermes Agent toolsets.

Official
Advanced
JuanMS20JuanMS20

qmd

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

Community
Advanced