skills.rest
robertbr123
robertbr123COMMUNITY
Explore all skills by this author →
WebsiteGitHub

qmd

Index and search local documents using BM25, vector search, and AI reranking.

Updated May 9, 2026
Search Tags:#local search#knowledge base#vector search#document search#AI retrieval
One-click install
npx skills add https://github.com/robertbr123/Linket-Agent --skill qmd-robertbr123
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/robertbr123/Linket-Agent/tree/main/optional-skills/research/qmd
Command: npx skills add https://github.com/robertbr123/Linket-Agent --skill qmd-robertbr123

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @tobilu/qmd, sqlite, node.js, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill solves the challenge of searching through extensive local document collections, providing a quick and efficient way to find information without the need for cloud dependencies.

Core Features & Use Cases

  • Local Search Engine: Indexes and searches markdown notes, documents, and transcripts.
  • Hybrid Retrieval: Combines keyword matching, semantic understanding, and AI-powered reranking.
  • CLI and MCP Integration: Supports direct integration with Linket Agent and other tools.

Quick Start

Start the QMD MCP server with 'qmd mcp --http --daemon' and use 'mcp_qmd_search' to search your documents.

Frequently Asked Questions about qmd

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

FAQPage Schema
How do I search my local knowledge base without cloud dependencies?▼

You can search your local knowledge base offline using QMD, which indexes local documents and provides retrieval without requiring any cloud services. It operates entirely locally using Node.js and SQLite.

How does hybrid retrieval combine keyword matching and semantic search?▼

Hybrid retrieval combines BM25 keyword matching, vector search for semantic understanding, and AI-powered reranking to find and prioritize relevant documents. This multi-stage approach improves search accuracy across personal knowledge bases.

How do I start the QMD server for local document search?▼

Start the QMD MCP server using the command 'qmd mcp --http --daemon', then utilize the 'mcp_qmd_search' function to query your indexed documents. This enables direct integration with Linket Agent and other supported tools.

Do I need Node.js and SQLite to run local vector search?▼

Yes, Node.js and SQLite are required dependencies for installing and operating this local vector search tool. The offline functionality relies on these environments to manage and query your document collections.

Can I use MCP integration for markdown notes and transcripts retrieval?▼

Yes, this tool supports CLI and MCP integration for indexing and searching markdown notes, documents, and transcripts. It operates offline to provide quick retrieval tailored for personal knowledge bases.

What is the best way to rerank AI retrieval results for a personal knowledge base?▼

The best way to rerank AI retrieval results is using a hybrid approach that applies AI-powered reranking after initial BM25 and vector search. This ensures the most contextually relevant documents surface first.

Related Skills

Explore More Data & Analytics Skills→
superfhpsuperfhp

qmd

Index and query markdown notes with BM25, vector search, and LLM reranking.

Community
Intermediate
weipingweiping
1

brain-search

Retrieve relevant references from a personal knowledge base using natural-language queries.

Community
Basic
ldzhhxxldzhhxx
1

qmd

Index and search markdown documents with BM25, vector search, and LLM reranking.

Community
Intermediate
davpatel605-beepdavpatel605-beep

chroma

Store and retrieve vector embeddings for semantic search and document retrieval.

Community
Intermediate