skills.rest
AnandaAnugrahHandyanto
AnandaAnugrahHandyantoCOMMUNITY
Explore all skills by this author →
GitHub

qmd

Index local markdown notes and documents for hybrid BM25 and vector search.

Updated Jun 19, 2026
Search Tags:#llm#search#notes#vector#local#bm25#qmd
One-click install
npx skills add https://github.com/AnandaAnugrahHandyanto/savarez_agent --skill qmd-anandaanugrahhandyanto
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/AnandaAnugrahHandyanto/savarez_agent/tree/main/optional-skills/research/qmd
Command: npx skills add https://github.com/AnandaAnugrahHandyanto/savarez_agent --skill qmd-anandaanugrahhandyanto

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local knowledge bases and notes often sit in fragmented files and copies; qmd unifies index and search to provide fast, relevant results across markdown notes, meeting transcripts, and docs.

Core Features & Use Cases

  • Hybrid search combining BM25, vector similarity, and LLM reranking for high-quality results.
  • Local indexing of notes, transcripts, and documentation with instant retrieval and cross-collection querying.
  • Use Case: quickly locate all mentions of a concept across your project notes and meeting transcripts.

Quick Start

Query your local notes with a hybrid search using qmd.

Frequently Asked Questions about qmd

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

FAQPage Schema
How do I perform hybrid search across local markdown notes and transcripts?▼

Hybrid search across local markdown notes blends BM25, vector similarity, and LLM reranking to retrieve exact terms and conceptual insights. Indexing local documentation enables fast cross-collection querying for text-rich datasets.

What is hybrid search for personal knowledge bases and how does it work?▼

Hybrid search for personal knowledge bases combines BM25 keyword matching, vector similarity, and LLM reranking. This mechanism unifies fragmented local files to retrieve exact phrases and conceptual insights across large collections.

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

Yes, local vector search requires Node.js >=22 and SQLite with extension support. You also need the qmd tool to index local markdown notes and meeting transcripts for local-only operation.

Can I use MCP integration for on-device search of meeting transcripts?▼

Yes, MCP integration is supported for on-device search of meeting transcripts. Applying this to local knowledge bases enables instant retrieval while maintaining local-only operation without external servers.

What is the best way to find concepts across project notes and meeting transcripts?▼

The best way to find concepts across project notes is applying hybrid search that blends BM25, vector similarity, and LLM reranking. This approach retrieves both exact terms and conceptual insights from large text-rich collections.

Why does local document indexing require SQLite with extension support?▼

Local document indexing requires SQLite with extension support to handle vector similarity operations alongside BM25 keyword matching. This combination enables fast hybrid retrieval across large datasets of markdown notes and transcripts.

Related Skills

Explore More Software Engineering Skills→
superfhpsuperfhp

qmd

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

Community
Intermediate
johnlindquistjohnlindquist
24

research

Automate comprehensive topic research with web search and AI synthesis.

Community
Advanced
Z43LZ43L

qmd

Search markdown and text documents with hybrid keyword and semantic retrieval.

Community
Advanced
nadicodeainadicodeai

qmd

Index and search local text collections with hybrid retrieval.

Official
Advanced