scraping-documentation

Scrape documentation websites and convert pages into organized Markdown files.

8|1|Updated Aug 12, 2025

Search Tags:#documentation #markdown #offline #conversion #knowledge-base #scrape

Ready to run

npx skills add https://github.com/memyselfandm/cconami --skill scraping-documentation

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: scraping-documentation
Source: https://github.com/memyselfandm/cconami/tree/main/apps/dot-claude/skills/scraping-documentation
Command: npx skills add https://github.com/memyselfandm/cconami --skill scraping-documentation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Scrapes documentation websites and converts content to organized Markdown files for offline reference and local knowledge bases.

Core Features & Use Cases

Web-site discovery and selective crawling to gather relevant documentation.
Conversion of fetched pages into clean Markdown with preserved headings, code blocks, and images.
Use case: Build an offline library of API references or project docs for quick offline lookup.

Quick Start

Run /scraping-documentation <url> to generate offline Markdown from a documentation site.

Frequently Asked Questions about scraping-documentation

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

FAQPage Schema

How do I convert website documentation to Markdown for offline reference?▼

To convert website documentation to offline Markdown, this Skill scrapes documentation pages and structures the content into organized Markdown files. It preserves headings, code blocks, and images while generating an index for local knowledge bases.

Can I build an offline knowledge base from API references and developer guides?▼

Yes, you can build an offline knowledge base from API references and developer guides by crawling the target URLs. The Skill selectively fetches documentation pages and converts them into clean Markdown for quick local lookup.

What is the best way to scrape a documentation site and generate an index?▼

The best way to scrape a documentation site and generate an index is to run the Skill's URL discovery process. It crawls the site, converts HTML to Markdown, and outputs structured files complete with an index for navigation.

Does the HTML-to-Markdown conversion preserve code blocks and images?▼

Yes, the HTML-to-Markdown conversion preserves code blocks and images. The Skill ensures that fetched documentation pages retain their structural formatting and visual elements during the offline Markdown generation process.

Are there limitations when scraping large documentation websites for local curation?▼

When scraping large documentation websites for local curation, the Skill applies selective crawling to gather relevant pages. However, extremely large or dynamically rendered sites may require specific URL inputs to ensure accurate offline Markdown conversion.

How do I start scraping documentation pages for my offline library?▼

To start scraping documentation pages for your offline library, simply provide the target URL to the Skill. It will handle the website discovery, HTML conversion, and Markdown structuring to create your local reference files.