skills.rest
CraftOS-dev
CraftOS-devCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

qmd

Index and search local files with BM25, vector embeddings, and reranking.

375|38|Updated Dec 2, 2025
Search Tags:#indexing#cli#search#vector search#bm25#local files
One-click install
npx skills add https://github.com/CraftOS-dev/CraftBot --skill qmd-craftos-dev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/CraftOS-dev/CraftBot/tree/main/skills/qmd
Command: npx skills add https://github.com/CraftOS-dev/CraftBot --skill qmd-craftos-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a command-line interface for indexing and searching local files using a combination of BM25, vector embeddings, and reranking, making it easy to find information within your personal documents.

Core Features & Use Cases

  • Local Indexing: Create and manage indexes for your local files.
  • Hybrid Search: Perform searches using BM25, vector similarity, or a hybrid approach.
  • Document Retrieval: Get specific content from indexed documents.
  • Use Case: Quickly find all markdown files related to a specific project by searching through your local notes using natural language queries.

Quick Start

Use the qmd skill to search for 'project planning documents' within your local files.

Frequently Asked Questions about qmd

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

FAQPage Schema
How do I search local files using vector embeddings and BM25?▼

You can search local files using BM25 and vector embeddings by creating collections and performing hybrid searches via a command-line interface to retrieve relevant document content.

What is hybrid search and how does it work for local document retrieval?▼

Hybrid search combines BM25 keyword matching with vector similarity to find information within local files, using reranking capabilities to improve the accuracy of retrieved documents.

Do I need Ollama to perform vector search on local files?▼

Yes, the local vector search and reranking capabilities integrate with Ollama to generate vector embeddings, which are stored in the ~/.cache/qmd directory.

Can I manage multiple indexes for different local file collections?▼

Yes, you can manage multiple local file indexes by adding distinct collections and updating them through the command-line interface to organize your document retrieval.

What is the best way to find specific markdown notes using natural language queries?▼

The best way to find markdown notes is using a local search CLI that combines BM25 and vector embeddings to match natural language queries against indexed personal documents.

Are there limitations when indexing local files for hybrid search?▼

Local file indexing relies on your machine's storage capacity for cached indexes and requires Ollama integration for vector embedding generation, limiting offline search functionality.

Related Skills

Explore More Software Engineering Skills→
steipetesteipete
385.7k

qmd

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

Community
Advanced
jaechang-hitsjaechang-hits
298

samtools-bam-processing

Process SAM, BAM, and CRAM alignment files with samtools.

Community
Intermediate
vignesh2027vignesh2027
18

bear-notes

Create, search, and append text to Bear notes via command line.

Community
Basic
andrewblockernstandrewblockernst

AgentDB Vector Search

Implements vector-based semantic search for documents using AgentDB and Node.js.

Community
Advanced