qmd

Search local Markdown collections using BM25 and semantic similarity.

Updated Feb 28, 2026

Search Tags:#markdown #search #retrieval #notes #local #qmd

Ready to run

npx skills add https://github.com/ramirlm/skillshare-ramir --skill qmd-ramirlm

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/ramirlm/skillshare-ramir/tree/main/qmd-skill
Command: npx skills add https://github.com/ramirlm/skillshare-ramir --skill qmd-ramirlm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill addresses the challenge of quickly finding information within large collections of local Markdown files, offering both keyword and semantic search capabilities.

Core Features & Use Cases

Local Hybrid Search: Provides fast, keyword-based search (BM25) and slower, semantic search for related content.
Document Retrieval: Enables retrieval of specific Markdown documents by path or ID.
Use Case: When you need to find specific notes on a project, recall information from past documentation, or locate related articles within your personal knowledge base.

Quick Start

Use the qmd skill to search your notes for "project planning".

Frequently Asked Questions about qmd

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

FAQPage Schema

How do I search markdown notes locally using both keywords and semantic similarity?▼

To search markdown notes locally, you can use a hybrid approach combining BM25 keyword search for exact matches and local LLMs for semantic similarity retrieval. This enables fast information extraction from indexed collections of documents.

Do I need Bun to set up local markdown search and document retrieval?▼

Yes, you need Bun installed along with specific system prerequisites to set up local markdown search. These dependencies are required for collection indexing and generating local embeddings for optimal retrieval performance.

What is the difference between BM25 keyword search and semantic search for markdown documents?▼

BM25 keyword search provides fast exact-match retrieval for markdown documents, while semantic search uses local LLMs for slower, nuanced similarity queries. Hybrid search combines both mechanisms to find related content efficiently.

Can I retrieve a specific markdown document by its file path or ID?▼

Yes, you can retrieve specific markdown documents by path or ID. The skill indexes your local markdown collection, allowing direct document retrieval alongside its hybrid keyword and semantic search capabilities.

What are the limitations of using local LLMs for semantic search across markdown files?▼

Semantic search across markdown files using local LLMs is slower than keyword-based BM25 retrieval. It requires generating local embeddings and indexing collections beforehand, which demands specific system prerequisites and setup time.