Convert web pages to markdown and download embedded images.
npx skills add https://github.com/mikker/dotfiles --skill visit-webpage-mikker
Please help me install this Agent Skill. Skill: visit-webpage Source: https://github.com/mikker/dotfiles/tree/main/agents.symlink/skills/visit-webpage Command: npx skills add https://github.com/mikker/dotfiles --skill visit-webpage-mikker
Converting diverse web content into clean, portable Markdown and saving embedded images for offline use, reducing manual copy-paste time and ensuring readability.
Fetch a URL and return its readable content as markdown.
High-intent search queries and answers about installing and using this skill.
To convert a web page to markdown for offline reading, the Skill extracts readable text from the URL and transforms it into clean Markdown. It also detects and downloads embedded images to a local temp file.
Yes, you can extract content from JavaScript-rendered pages. The Skill uses Jina Reader to retrieve dynamic content, handling common site structures and errors gracefully during the web scraping process.
No, a Jina API key is not strictly required to convert web pages to text. The Skill uses an optional Jina API key to achieve higher rate limits when fetching and processing web content.
The size limits are 5MB for downloading embedded images and 100KB for extracting text. The Skill enforces these limits and performs HEAD content-type checks during web content extraction.
The best way to save embedded images from an article locally is to use this Skill's image download feature. It detects image URLs, enforces a 5MB size limit, and saves the files to a local temp file for offline viewing.
Web content extraction might fail if sites block automated retrieval or if the content exceeds the 100KB text limit. The Skill includes retry logic to handle transient errors and improve extraction robustness.
ArcanexisFetch web pages and convert them into Markdown-formatted text.
zinohomeConvert PDFs, office files, images, audio, and web content into Markdown.
HieubkavConvert base64 images to stored files and clean up unused media in Lexical Editor.
xberg-ioScrape webpages and convert HTML content to Markdown.
