Web To Markdown

A straightforward wrapper around the web2md CLI that spins up Puppeteer to handle JavaScript-heavy pages and convert them to clean Markdown. You get Readability extraction plus Turndown conversion, which works well for docs, articles, and SPAs that don't render without a real browser. The interactive mode is practical for login walls: it pauses Chrome so you can click through a captcha or sign in, then continues the scrape. One quirk: it enforces an explicit trigger phrase, so you have to say "use the skill web-to-markdown" instead of just asking for a URL conversion. Useful if you're already scraping content locally and need something heavier than curl or basic HTTP clients.

skills.sh installs: 780
GitHub stars: 2.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add softaworks/agent-toolkit --skill web-to-markdown --agent claude-code

Installs into .claude/skills of the current project.

Files

web-to-markdown

Convert web pages to clean Markdown by driving a locally installed browser (via web2md).

Hard trigger gate (must enforce)

This skill MUST NOT be used unless the user explicitly wrote exactly a phrase like:

use the skill web-to-markdown ...
use a skill web-to-markdown ...

If the user did not explicitly request this skill by name, stop and ask them to re-issue the request including: use the skill web-to-markdown.

What this skill does

Handles JS-rendered pages (Puppeteer → user Chrome).
Works best with Chromium-family browsers (Chrome/Chromium/Brave/Edge) via puppeteer-core.
Extracts main content (Readability).
Converts to Markdown (Turndown) with cleaned links and optional YAML frontmatter.