skills.rest
projectedanx
projectedanxCOMMUNITY
Explore all skills by this author →
𝕏@ALifeInArtifyAIGitHub

qmd

Indexes and queries local markdown files and transcripts via hybrid BM25, vector embeddings, and LLM reranking search engine.

1|Updated May 12, 2026
Search Tags:#markdown#rag#search#mcp#knowledge-base#local-ai
One-click install
npx skills add https://github.com/projectedanx/hermes-agent --skill qmd-projectedanx
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/projectedanx/hermes-agent/tree/main/optional-skills/research/qmd
Command: npx skills add https://github.com/projectedanx/hermes-agent --skill qmd-projectedanx

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the challenge of fragmented personal knowledge by providing a unified, local search engine that indexes your notes, transcripts, and documentation without relying on cloud services.

Core Features & Use Cases

  • Hybrid Search: Combines BM25 keyword matching with semantic vector search and LLM-powered reranking for maximum accuracy.
  • Local Privacy: All indexing and model inference run entirely on your machine, ensuring your sensitive data never leaves your device.
  • Use Case: Quickly find specific decisions made in past meeting transcripts or retrieve technical documentation across multiple project folders using natural language queries.

Quick Start

Ask the agent to search your notes for a specific topic by providing a natural language query like search my notes for the database migration plan.

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 and transcripts without sending data to the cloud?▼

To search local markdown files and transcripts without cloud reliance, you can use a local hybrid retrieval engine that indexes documents directly on your machine, ensuring sensitive data never leaves your device.

What is hybrid search for a personal knowledge base?▼

Hybrid search for a knowledge base combines BM25 keyword matching with semantic vector search and LLM-powered reranking to maximize query accuracy across diverse document collections.

Do I need Node.js 22 to run local vector search and LLM reranking?▼

Yes, running this local vector search and LLM reranking engine requires Node.js 22 along with local GGUF model support to handle semantic understanding and query expansion.

Can I use natural language queries to find decisions in meeting transcripts?▼

Yes, you can use natural language queries to find specific decisions in meeting transcripts by asking the agent to search your indexed notes across multiple project folders.

Does local knowledge base search integrate with MCP for agentic access?▼

Yes, local knowledge base search integrates with MCP for agentic access, allowing automated agents to query your indexed markdown files and transcripts directly.

Related Skills

Explore More Education & Research Skills→
cxnaivecxnaive

qmd

Index local markdown notes and perform hybrid semantic search with BM25 and vector embeddings.

Community
Advanced
robwestzrobwestz

kb-query

Search an indexed knowledge base with natural language and return semantically ranked results.

Community
Intermediate
steipetesteipete
385.7k

qmd

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

Community
Advanced
JuanMS20JuanMS20

qmd

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

Community
Advanced