skills.rest
sheawinkler
sheawinklerCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

qmd

Search local markdown and text collections using hybrid BM25 and vector ranking.

78|16|Updated Apr 23, 2026
Search Tags:#mcp#privacy#on-device#knowledge-base#hybrid-search#local-search
One-click install
npx skills add https://github.com/sheawinkler/hermes-agent-ultra --skill qmd-sheawinkler
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/sheawinkler/hermes-agent-ultra/tree/main/optional-skills/research/qmd
Command: npx skills add https://github.com/sheawinkler/hermes-agent-ultra --skill qmd-sheawinkler

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Locally search across your notes, documents, and transcripts to find relevant information without relying on cloud services.

Core Features & Use Cases

  • On-device hybrid search (BM25 + vector + LLM reranking) across markdown/text collections.
  • MCP integration for native tooling, enabling Hermes Agent to access search tools without loading this skill.
  • No cloud dependency; private search for personal knowledge bases, meeting transcripts, and docs.

Quick Start

Run qmd query 'onboarding plan' to retrieve relevant results from your local collections.

Frequently Asked Questions about qmd

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

FAQPage Schema
How do I search local notes and documents without cloud dependency?▼

On-device hybrid search combines BM25 keyword matching, vector semantic search, and LLM reranking to locate information. This mechanism ensures accurate results across your local markdown and text collections.

How does hybrid search ranking work for personal knowledge bases?▼

On-device hybrid search combines BM25 keyword matching, vector semantic search, and LLM reranking to locate information. This mechanism ensures accurate results across your local markdown and text collections.

Can I use MCP integration to access local search tools natively?▼

Yes, MCP integration exposes search tools via a local API for native tooling. This allows agents to access your local knowledge base and execute queries without explicitly loading the search skill.

What is the best way to find information across meeting transcripts locally?▼

The best way to find information across meeting transcripts is using on-device hybrid search. It indexes your local transcripts and documents, enabling private semantic and keyword queries with accurate reranking.

Do I need cloud services to run semantic queries on my text collections?▼

No, you do not need cloud services to run semantic queries. The skill performs on-device indexing and vector search locally, ensuring your personal knowledge base remains completely private.

Related Skills

Explore More Software Engineering Skills→
AskTinNguyenAskTinNguyen

qmd-search

Index and search Markdown documents with on-device semantic vector search.

Community
Advanced
stevolandstevoland

index-knowledge

Generate hierarchical AGENTS.md knowledge bases from codebases.

Community
Advanced
kingkillerykingkillery

qmd

Search markdown collections with full-text and semantic queries.

Community
Intermediate
JuanMS20JuanMS20

qmd

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

Community
Advanced