Medium — Data Extraction
CommunityTurn Medium articles into Markdown-ready data.
Authoryangchuansheng
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This skill extracts Medium article bodies and associated metadata from web pages, converting them into structured Markdown-ready content to accelerate research, archiving, and content analysis.
Core Features & Use Cases
- Full article body extraction: Retrieve the article's main text, headings, lists, code blocks, figures, and captions as clean Markdown.
- Metadata retrieval: Pull publication data, author info, word count, claps, reading time, and publication dates from multiple Medium endpoints (format=json, GraphQL, RSS).
- Paywall handling: Distinguish between free and paywalled content and provide fallbacks using non-paywalled sources when possible.
- Use Case: Build an offline archive of essential Medium articles with accurate structure and metrics for analysis.
Quick Start
Fetch the article body and metadata for a given Medium URL using the best available path and return it as Markdown.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: Medium — Data Extraction Download link: https://github.com/yangchuansheng/browser-harness-rust/archive/main.zip#medium-data-extraction Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.