skills.rest
NITISH-gitbit
NITISH-gitbitCOMMUNITY
Explore all skills by this author →
GitHub

qmd

Combine BM25 keyword matching, vector semantic search, and LLM reranking for local Markdown file retrieval.

Updated Jun 26, 2026
Search Tags:#markdown#semantic search#search#knowledge base#local AI
One-click install
npx skills add https://github.com/NITISH-gitbit/hermes-custom --skill qmd-nitish-gitbit
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/NITISH-gitbit/hermes-custom/tree/main/optional-skills/research/qmd
Command: npx skills add https://github.com/NITISH-gitbit/hermes-custom --skill qmd-nitish-gitbit

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill allows users to search personal knowledge bases, notes, documents, and meeting transcripts locally, providing fast and efficient access to information stored in Markdown files.

Core Features & Use Cases

  • Local Search: Perform keyword and semantic searches on personal knowledge bases and notes.
  • Hybrid Search: Combines keyword matching, semantic understanding, and LLM reranking for high-quality search results.
  • CLI and MCP Integration: Supports CLI commands and can be integrated with Hermes Agent for easy access through the MCP client.
  • Use Case: Users can quickly find relevant information within a large collection of Markdown files without the need for cloud services.

Quick Start

Set up qmd with qmd setup and index your notes directory with qmd collection add ~/notes --name notes. Once indexed, use qmd search "keyword" to search your notes.

Frequently Asked Questions about qmd

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

FAQPage Schema
How do I search local markdown files for specific keywords?▼

To search local markdown files, you can index your notes directory and use a hybrid search combining BM25 keyword matching and vector semantic search. This provides fast, on-device access to your personal knowledge base.

What is the best way to find information in a local knowledge base without cloud services?▼

Hybrid search allows you to find information in a local knowledge base without cloud services by running entirely on-device. It combines keyword matching, semantic understanding, and LLM reranking to retrieve relevant markdown documents.

How does semantic search work for personal markdown notes?▼

Semantic search for personal markdown notes works by combining BM25 keyword matching with vector search and LLM reranking. This hybrid approach improves retrieval quality by understanding both exact terms and contextual meaning on your local device.

Can I integrate local markdown search with an MCP client?▼

Yes, you can integrate local markdown search with an MCP client using the Hermes Agent. The tool supports both CLI commands and MCP integration, allowing you to access your indexed personal knowledge base through your preferred client.

How do I set up and index a collection of markdown notes for searching?▼

To set up markdown searching, run the setup command, then add your notes directory to create a named collection. Once your markdown files are indexed locally, you can execute keyword and semantic searches against them.

Related Skills

Explore More Product & Management Skills→
saskinosiesaskinosie
39

weaviate-query-agent

Query local Weaviate collections with semantic, hybrid, and RAG searches.

Community
Intermediate
joshuarolljoshuaroll

media-transcript-search

Retrieve and search YouTube transcripts with keyword filtering and export.

Community
Intermediate
zengbaochengzengbaocheng

mcp-service-integration

Wrap flight search, web search, and knowledge-base APIs into MCP servers.

Community
Advanced
JuanMS20JuanMS20

qmd

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

Community
Advanced