Extract article content from local HTML files into clean Markdown.
npx skills add https://github.com/beatai-org/beatai --skill extract-article
Please help me install this Agent Skill. Skill: extract-article Source: https://github.com/beatai-org/beatai/tree/main/.claude/skills_bak/extract-article Command: npx skills add https://github.com/beatai-org/beatai --skill extract-article
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.
Ask to extract the article content from your local HTML file path, and then use the skill’s output Markdown directly.
High-intent search queries and answers about installing and using this skill.
To convert saved WeChat or Medium HTML to Markdown, this skill performs platform-aware extraction on your local HTML file. It detects the source and returns clean Markdown by preserving structure, headings, links, lists, and image URLs in their original order.
HTML to Markdown conversion duplicates math formulas due to redundant KaTeX or MathML DOM layers. This skill applies math de-duplication guardrails to skip these redundant layers, ensuring your extracted output contains each formula only once.
The best way to extract article正文 content from a local HTML file is using an extraction tool that removes navigation and boilerplate. This skill targets the correct content region across generic blogs and specific platforms, yielding clean Markdown suitable for reuse.
Structured parsing for Medium articles works by extracting data from the window.__APOLLO_STATE__ object. This skill prioritizes that path for accurate content retrieval and falls back to standard DOM extraction only when the structured data is unavailable.
Yes, you can extract images and links in order when converting HTML to Markdown. The skill preserves block elements, inline emphasis, code fences, and restores images as Markdown URLs sequentially as they appeared in the original article HTML.
yuyuxinliExtract web article content and metadata into Markdown files.
mahg-esGenerate static websites from Markdown into deployable HTML with CI workflows.
yoanbernabeuRender inline and display math in Slidev presentations using KaTeX.
tusososExtract clean article text from URLs and save it as plain text.
