docs-to-md

Convert official documentation sites into local Markdown files with frontmatter metadata.

1|Updated Feb 12, 2026
One-click install
npx skills add https://github.com/dev-goraebap/grimoire --skill docs-to-md
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: docs-to-md
Source: https://github.com/dev-goraebap/grimoire/tree/main/misc/skills/docs-to-md
Command: npx skills add https://github.com/dev-goraebap/grimoire --skill docs-to-md

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill converts official documentation sites into local Markdown files, enabling offline access and easy reference for knowledge retention and onboarding.

Core Features & Use Cases

  • Automated discovery: retrieves pages via llms-full.txt, llms.txt, sitemap.xml, or navigational links and saves them as Markdown with frontmatter metadata.
  • Configurable output: stores results under a local path like ./docs or a user-specified directory; handles single-page and multi-page crawls; preserves source URLs for traceability.
  • Reference archival: supports metadata such as source_url and fetched_at to help determine staleness and provenance.

Quick Start

Transform a given official docs URL into local Markdown by invoking the /docs-to-md command with the target URL and optional output path.

Frequently Asked Questions about docs-to-md

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

FAQPage Schema
How do I convert official documentation sites to local Markdown files?

To convert official documentation sites to local Markdown files, this skill crawls pages discovered via llms-full.txt, llms.txt, sitemap.xml, or site navigation and saves them under ./docs or a specified path.

How does automated web crawling discover documentation pages for offline use?

Automated web crawling discovers documentation pages by fetching and normalizing URLs from llms-full.txt, llms.txt, sitemap.xml, or navigational links using a deterministic script workflow.

Can I save multi-page documentation crawls to a specific output directory?

Yes, you can save multi-page documentation crawls to a specific output directory by invoking the command with your target URL and an optional output path, defaulting to ./docs.

Does the converted Markdown include source URL and fetched metadata?

Yes, the converted Markdown includes source URL and fetched metadata by generating frontmatter with source_url and fetched_at fields for traceability and staleness determination.

What is the best way to archive reference docs offline with frontmatter metadata?

The best way to archive reference docs offline with frontmatter metadata is using this skill to fetch documentation sites and save them as Markdown files with provenance and timestamp metadata.

Do I need network access to crawl and convert documentation sites to Markdown?

Yes, you need network access to crawl and convert documentation sites to Markdown because the discovery script must fetch live pages from the target URL to generate local files.