extract-article
OfficialConvert saved HTML articles into clean Markdown.
Content & Communication#html#article extraction#wechat#markdown conversion#medium#math de-duplication
Authorbeatai-org
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Converts locally saved article HTML into clean, readable Markdown by extracting only the main article content while preserving structure, headings, links, lists, code blocks, and images.
Core Features & Use Cases
- Platform-aware extraction: Detects common sources like WeChat, Zhihu, Medium, or generic blogs from the HTML and targets the correct content region.
- Markdown-preserving output: Keeps title hierarchy, block elements, inline emphasis, code fences, links, tables, and image URLs in the right order.
- Medium-safe structured parsing: For Medium, prefers the structured parsing path via window.APOLLO_STATE and falls back to DOM extraction only when needed.
- Math de-duplication guardrails: Avoids duplicate extraction for KaTeX/MathJax/MathML-rendered formulas by skipping redundant math DOM layers.
Quick Start
Ask to extract the article content from your local HTML file path, and then use the skill’s output Markdown directly.
Dependency Matrix
Required Modules
None requiredComponents
scripts
💻 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: extract-article Download link: https://github.com/beatai-org/beatai/archive/main.zip#extract-article 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.