skills.rest
johncarpenter
johncarpenterCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

kb-search

Search, retrieve, and index local Markdown files using the QMD CLI.

Updated Feb 7, 2026
Search Tags:#markdown#indexing#embeddings#search#local-docs#knowledgebase#QMD
One-click install
npx skills add https://github.com/johncarpenter/knowledge-base --skill kb-search-johncarpenter
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: kb-search
Source: https://github.com/johncarpenter/knowledge-base/tree/main/.claude/skills/kb-search
Command: npx skills add https://github.com/johncarpenter/knowledge-base --skill kb-search-johncarpenter

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill enables users to search, retrieve, and index local Markdown knowledgebase files using the QMD CLI, reducing time spent locating relevant information across large doc collections.

Core Features & Use Cases

  • Search modes include keyword, semantic, and hybrid queries to quickly locate passages in local docs.
  • Indexing and embedding: register directories as QMD collections and generate embeddings for fast, accurate retrieval.
  • Retrieval and export: fetch full documents or passages and support structured outputs for programmatic consumption.
  • Use Case: A developer can quickly answer a teammate's question by locating API docs scattered across a local knowledgebase and summarizing the relevant section.

Quick Start

  • Install the QMD CLI and ensure it is on your PATH.
  • Add a collection from a directory of Markdown files: qmd collection add /path/to/docs --name myDocs
  • Build embeddings: qmd embed
  • Perform a search: qmd query "how to authenticate" or qmd vsearch "authentication flow"

Frequently Asked Questions about kb-search

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

FAQPage Schema
How do I search local markdown files for specific information?▼

You can search local markdown knowledgebases by registering directories as collections and running keyword, semantic, or hybrid queries to retrieve relevant passages or full documents.

How does semantic search work on a local knowledgebase?▼

Semantic search works by generating embeddings for your local markdown files, allowing you to retrieve contextually relevant passages rather than just matching exact keywords.

What's the best way to index a directory of markdown documentation?▼

The best way to index markdown documentation is adding the directory as a collection and generating embeddings, which enables fast multi-mode retrieval across all files.

Do I need to install any CLI tools to index and search local markdown docs?▼

Yes, you need the QMD CLI installed and available on your PATH to index directories, generate embeddings, and perform multi-mode searches on local markdown knowledgebases.

Can I export search results from a local markdown knowledgebase as structured data?▼

Yes, you can export retrieved passages and documents from your markdown knowledgebase using structured output formats like --json and --md for programmatic consumption.

What is the difference between keyword and hybrid search for local docs?▼

Keyword search matches exact terms, while hybrid search combines keyword matching with semantic embeddings to return more contextually relevant passages from local markdown files.

Related Skills

Explore More Content & Communication Skills→
steipetesteipete
385.7k

qmd

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

Community
Advanced
BekaChkhiroBekaChkhiro
1

planExportJson

Export PROJECT_PLAN.md into structured JSON with phases and tasks.

Community
Basic
miko06miko06

document-release

Update project documentation files after shipping using Git and Bash.

Community
Advanced
bobvarkeybobvarkey
1

clawhub-searing

Search document content by meaning and summarize relevant passages.

Community
Basic