web-fetch

SKILL.md

Fetch web content as clean markdown using markdown-native endpoints, selector-based HTML extraction, or bundled fallback parsing.

Prioritizes markdown-native responses (content-type: text/markdown) before falling back to HTML extraction

Includes pre-configured selectors for common documentation sites (Anthropic, MDN, GitHub) and a generic fallback for article/main content regions

Provides html2markdown with CSS selector support for fine-grained content isolation, excluding navigation, headers, footers, and scripts

Bundles a Bun-based fallback parser for sites where selector-based extraction fails or produces poor output

Requires curl, html2markdown, and bun; includes troubleshooting guidance for markdown detection, selector testing, and client-rendered content limitations

Web Content Fetching

Fetch web content in this order:

Prefer markdown-native endpoints (content-type: text/markdown)

Use selector-based HTML extraction for known sites

Use the bundled Bun fallback script when selectors fail

Prerequisites

Verify required tools before extracting:

command -v curl >/dev/null || echo "curl is required"
command -v html2markdown >/dev/null || echo "html2markdown is required for HTML extraction"
command -v bun >/dev/null || echo "bun is required for fetch.ts fallback"

Install Bun dependencies for the bundled script: