skills.rest
beatai-org
beatai-orgOFFICIAL
Explore all skills by this author →
GitHub

medium-fetch

Downloads Medium articles as Markdown with images into a local directory.

4.7k|260|Updated Dec 29, 2021
Search Tags:#web scraping#markdown conversion#medium#image localization#article download#member-only access#chrome session
One-click install
npx skills add https://github.com/beatai-org/beatai --skill medium-fetch
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: medium-fetch
Source: https://github.com/beatai-org/beatai/tree/main/.claude/skills/medium-fetch
Command: npx skills add https://github.com/beatai-org/beatai --skill medium-fetch

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, @mozilla/readability, jsdom, turndown, yaml, and includes scripts (resource) components.

What problem does it solve?

It eliminates the manual effort of downloading Medium articles by URL, including member-only stories, and converting them into offline-ready content for downstream processing.

Core Features & Use Cases

  • Authenticated, real-Chrome fetching: Uses a persistent real Chrome profile to access content behind Cloudflare and Medium membership gates.
  • Cross-domain SSO handling: Automatically routes publication custom-domain URLs through Medium’s SSO bridge to ensure the right cookies are applied.
  • Readability + Turndown cleanup: Extracts the main article body and outputs Readability-cleaned Markdown with images downloaded locally.
  • Leaf executor output contract: Writes results to a caller-provided RAW_DIR as markdown + assets without translating, summarizing, or choosing storage destinations.

Quick Start

Ask the assistant to download the Medium article at the given URL and store the resulting Markdown and local image assets in your provided RAW_DIR.

Frequently Asked Questions about medium-fetch

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

FAQPage Schema
How do I download Medium articles as Markdown for offline ingestion?▼

Downloading member-only Medium articles requires headful real Chrome with a persistent authenticated profile. This setup bypasses Cloudflare and membership gates, applying the correct cookies to access and convert restricted content into Markdown.

Can I scrape Medium publication articles hosted on custom domains?▼

Yes, Medium article images are localized during the download process. The skill downloads referenced images into a local assets folder within your provided directory, ensuring the Readability-cleaned Markdown links to local files for offline access.

Do I need a real Chrome profile to convert member-only Medium stories to Markdown?▼

The best way to handle Medium SSO bridging is using a persistent real Chrome profile. The skill automatically routes publication custom-domain URLs through Medium’s SSO bridge, ensuring the correct cookies are applied for authenticated access.

What are the limitations of using Readability and Turndown for Medium article conversion?▼

You should not use this approach if you lack a pre-authenticated Chrome profile. Cloudflare and Medium membership gates require headful real Chrome with persistent authentication, meaning unauthenticated headless scraping will fail to access restricted content.

Related Skills

Explore More Content & Communication Skills→
beatai-orgbeatai-org
4.7k

x-fetch

Converts X posts and long-form articles to Markdown with local image assets.

Official
Advanced
William2333ZZWilliam2333ZZ
5

knowledge

Search and organize Markdown knowledge bases using FTS5 indexing and vector embeddings.

Community
Intermediate
sdyckjq-labsdyckjq-lab
2.3k

baoyu-url-to-markdown

Convert web pages to markdown using the Chrome DevTools Protocol.

Community
Advanced
richardnguyen0715richardnguyen0715

scrapling

Scrape static and JavaScript-rendered web content with stealth and Cloudflare bypass.

Community
Advanced