Skill

convert-to-markdown

Extracts clean Markdown from any URL using ezycopy CLI. Handles JS-rendered pages with headless Chrome, retries on failure, and auto-installs tool if needed.

Bash

Markdown

cli-tools

documentation

npx claudepluginhub gupsammy/claudest --plugin claude-utilities

Tool Access

This skill is limited to using the following tools:

Bash(ezycopy:*)Bash(curl:*)AskUserQuestion

Preview

Extract clean markdown from any URL using the `ezycopy` CLI.

SKILL.md

Similar Skills

web-to-markdown

667

Converts web URLs to cleaned Markdown with site-specific routing: r.jina.ai for general/X/Twitter pages, defuddle.md for YouTube, browser-impersonated extraction for WeChat/Zhihu/Feishu using Mozilla Readability and Turndown.

8 files

writing-workflows

baoyu-url-to-markdown

16.5k

Fetches any URL and converts to markdown using baoyu-fetch CLI (Chrome CDP with adapters for X/Twitter, YouTube transcripts, Hacker News, Defuddle). Handles login/CAPTCHA waits for saving webpages.

20 files

jimliu-baoyu-skills-9

fetch-url-as-markdown

Fetches web pages as clean Markdown using local trafilatura, with Exa MCP fallback for JS-rendered or anti-bot sites. Use for reading, scraping, summarizing, or quoting URLs.

3 files

ai-driven-development

Stats

Parent Repo Stars129

Parent Repo Forks10

Last CommitFeb 23, 2026

Used By2 plugins

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Web-to-Markdown via EzyCopy

Extract clean markdown from any URL using the ezycopy CLI.

Phase 1: Determine Extraction Mode

Default mode uses fast HTTP fetch. Add --browser when the page relies on client-side JavaScript to render its content or when authentication cookies are required — the default fetcher only sees the raw HTML response, not the JS-rendered DOM.

Common --browser cases: Twitter/X, single-page applications, paywalled content.

Flags

-c — copy output to clipboard

-o <path> — save to file or directory

--browser — use headless Chrome for JS-rendered or authenticated pages

--no-images — strip image links

-t <duration> — timeout (default: 30s)

Phase 2: Execute

Run ezycopy <URL> [flags] with the chosen mode.

In --browser mode: run as a foreground process and do not redirect stderr with 2>&1. Chrome outputs diagnostic messages to stderr that should flow naturally rather than polluting stdout capture.

Phase 3: Handle Failure

If the output is empty or suspiciously short and --browser was not used, retry with --browser — the site likely requires JS rendering.

If ezycopy is not found, ask the user before installing:

curl -sSL https://raw.githubusercontent.com/gupsammy/EzyCopy/main/install.sh | sh

Phase 4: Deliver

Present the extracted markdown to the user. If the user requested a file save, use -o. If they requested clipboard, use -c. When no explicit destination was given, display the content directly.