skills.rest
cdeistopened
cdeistopenedCOMMUNITY
Explore all skills by this author →
GitHub

local-markdown-search

Index and search local Markdown collections with BM25 and vector embeddings.

2|1|Updated Mar 18, 2026
Search Tags:#markdown#search#semantic#privacy#on-device#qmd
One-click install
npx skills add https://github.com/cdeistopened/skill-stack-skills --skill local-markdown-search
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: local-markdown-search
Source: https://github.com/cdeistopened/skill-stack-skills/tree/main/research-scraping/local-markdown-search
Command: npx skills add https://github.com/cdeistopened/skill-stack-skills --skill local-markdown-search

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local Markdown Search enables fast, private indexing and retrieval across your own Markdown collections using on-device tools like QMD. It supports full-text search via BM25, vector semantic search, and LLM-based re-ranking to surface precise passages without sending data to the cloud.

Core Features & Use Cases

  • Index markdown files into searchable collections for quick retrieval
  • Perform keyword, semantic, or combined searches across transcripts, notes, wikis, and documentation
  • Retrieve full documents or relevant snippets with source citations for research or knowledge management
  • Use in private, on-device workflows to protect sensitive information

Quick Start

Index Markdown files into a named collection with qmd collection add /path/to/folder --name my-markdown --mask '**/*.md' and then search with qmd search 'query'.

Frequently Asked Questions about local-markdown-search

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

FAQPage Schema
How do I search local Markdown files privately without sending data to the cloud?▼

On-device Markdown search indexes local files privately using BM25 full-text search, vector embeddings, and LLM-based re-ranking to retrieve precise passages without cloud data transmission.

What is the best way to combine keyword and semantic search across my Markdown notes?▼

Combine keyword and semantic search by indexing Markdown files into QMD collections, then querying with both BM25 full-text matching and vector embeddings to surface relevant snippets with source citations.

Can I use QMD to index and search Markdown documentation collections?▼

Yes, QMD can index Markdown documentation into named collections using a file mask, enabling fast retrieval of relevant snippets or full documents for research and knowledge management workflows.

Do I need the Bun runtime to perform on-device Markdown indexing and retrieval?▼

Yes, on-device Markdown indexing via QMD collections and embedding generation requires the Bun runtime and QMD tooling to execute local full-text and semantic searches.

How do I retrieve exact passages with source citations from local Markdown wikis?▼

Retrieve cited passages by indexing Markdown wikis into a QMD collection, then searching with queries that apply BM25 and vector re-ranking to return precise snippets with source references.

Are there limitations when using on-device full-text search for large Markdown collections?▼

On-device full-text search keeps data local but requires sufficient hardware resources for embedding generation and re-ranking, and depends on the Bun runtime and QMD tooling for indexing operations.

Related Skills

Explore More Data & Analytics Skills→
ninehillsninehills
278

qmd

Locate and retrieve Markdown notes from indexed collections using hybrid search.

Community
Intermediate
lukasdeveloperacclukasdeveloperacc

ai-researcher

Summarizes AI research evidence from provided sources with citations and Markdown output.

Community
Intermediate
softmgsoftmg

AgentDB Vector Search

Implement semantic vector search with HNSW indexing and multiple distance metrics.

Official
Advanced
JuanMS20JuanMS20

qmd

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

Community
Advanced