mdbase

Initialize, create, query, and validate mdbase collections from Markdown files.

3|1|Updated Feb 10, 2026
One-click install
npx skills add https://github.com/callumalpass/mdbase-skill --skill mdbase
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mdbase
Source: https://github.com/callumalpass/mdbase-skill/tree/main
Command: npx skills add https://github.com/callumalpass/mdbase-skill --skill mdbase

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

mdbase helps AI coding assistants transform folders of Markdown files with YAML frontmatter into typed, queryable data stores, enabling robust data-driven prompts and validations.

Core Features & Use Cases

  • Turn a directory of Markdown records into a typed database using mdbase.yaml and _types definitions.
  • Validate, query, and refactor records across large collections with type safety.
  • Use in projects to initialize, create, query, and validate mdbase collections in AI-assisted workflows.

Quick Start

Initialize an mdbase collection in your project by enabling mdbase.yaml and typing files in _types, then begin creating records and running queries.

Frequently Asked Questions about mdbase

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

FAQPage Schema
How do I turn a directory of Markdown files with YAML frontmatter into a typed database?

To create a typed Markdown database, initialize a collection by setting up an mdbase.yaml file and defining types in the _types directory. This allows AI assistants to validate and query your records with type safety.

Can I validate and query Markdown records across large collections using AI coding assistants?

Yes, you can validate, query, and refactor typed Markdown records across large collections. The Skill guides AI assistants to perform type matching and validation using the definitions configured in your project.

What is the best way to manage typed Markdown collections in AI-assisted workflows?

The best way to manage typed Markdown collections is using an mdbase.yaml configuration file. This approach transforms folders of Markdown files into typed, queryable data stores, enabling robust data-driven prompts.

How do I initialize a typed Markdown collection for my project?

To initialize a typed Markdown collection, create an mdbase.yaml file and set up typing files in an _types directory. Once initialized, you can begin creating records and running queries against the collection.

Does this approach require any specific dependencies to manage typed Markdown data stores?

No specific dependencies are required to manage typed Markdown data stores. The Skill operates by guiding AI to read the mdbase.yaml file and type definitions directly within your existing project environment.

When do I need a typed Markdown collection instead of standard Markdown files?

You need a typed Markdown collection when you want to transform standard files with YAML frontmatter into a queryable data store. This is necessary for robust data-driven prompts, type matching, and validation in AI-assisted workflows.