qmd

Search local markdown notes using hybrid BM25 and semantic retrieval.

1|Updated Jun 25, 2026
One-click install
npx skills add https://github.com/Signmanal/VIGIL --skill qmd-signmanal
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/Signmanal/VIGIL/tree/main/optional-skills/research/qmd
Command: npx skills add https://github.com/Signmanal/VIGIL --skill qmd-signmanal

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually searching through large collections of local markdown notes, meeting transcripts, and documentation to find specific information is time-consuming and often inaccurate with basic keyword-only search tools.

Core Features & Use Cases

  • Hybrid Local Search: Combines BM25 keyword matching, semantic vector search, and LLM-powered reranking to deliver highly relevant results without sending any data to cloud services.
  • Flexible Search Modes: Supports fast keyword lookup for exact terms, conceptual semantic search for vague queries, and high-quality hybrid search for complex questions requiring the best possible accuracy.
  • Use Case: A security analyst can use this skill to quickly locate past meeting decisions about a database migration across years of stored team meeting transcripts and project documentation.

Quick Start

Use the qmd skill to search your local notes and project docs for all mentions of the database migration plan from last quarter's team syncs.

Frequently Asked Questions about qmd

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

FAQPage Schema
How does hybrid search work for local markdown notes and documentation?

Hybrid search for local markdown notes and documentation combines BM25 keyword matching, semantic vector similarity, and LLM-powered reranking. This approach ensures highly relevant retrieval from large collections of text files without sending any data to cloud services.

What is the best way to search meeting transcripts for specific past decisions?

The best way to search meeting transcripts for specific past decisions is using a local hybrid search skill. It applies BM25 keyword matching and semantic vector similarity to quickly locate relevant content across thousands of stored text files.

Can I use semantic search on my local knowledge base without uploading data to the cloud?

Yes, you can perform semantic search on a local knowledge base without uploading data to the cloud. This skill processes all text files locally, ensuring data privacy while delivering conceptual search results for vague queries.

Does local document retrieval support MCP integration for AI assistant workflows?

Yes, local document retrieval supports optional MCP integration for AI assistant workflows. This allows AI assistants to leverage hybrid search capabilities to access specific content across your local documentation efficiently.

How do I search thousands of local text files for a vague concept instead of an exact keyword?

To search thousands of local text files for a vague concept instead of an exact keyword, use semantic vector search mode. This mode interprets conceptual meaning rather than strict keyword matching, finding relevant notes even without exact terms.