Fetch web pages and PDFs and convert them to Markdown.
npx skills add https://github.com/einargudnig/dotfiles --skill read-einargudnig
Please help me install this Agent Skill. Skill: read Source: https://github.com/einargudnig/dotfiles/tree/main/claude/skills/read Command: npx skills add https://github.com/einargudnig/dotfiles --skill read-einargudnig
Convert web pages, platform-specific documents, and PDFs into clean, readable Markdown automatically, eliminating manual copying, format cleanup, and tool chaining so users can quickly read, archive, or process content.
Use the read skill to fetch a URL or PDF and save the cleaned Markdown to your Downloads folder.
High-intent search queries and answers about installing and using this skill.
To convert a web page or PDF into clean Markdown, this Skill fetches the content using a proxy cascade and saves the extracted text with YAML frontmatter directly to your Downloads folder for easy reading and archival.
Yes, you can extract content from Feishu documents and WeChat articles using built-in platform-specific handlers, which utilize the Feishu API and a Playwright scraper to reliably retrieve and convert the text into Markdown.
The proxy cascade fetching mechanism uses defuddle.md and r.jina.ai before falling back to local tools, maximizing content coverage and preserving images and metadata even when standard direct web scraping fails.
To get raw file content from GitHub URLs into Markdown format, the Skill applies specific GitHub file page handlers with gh and raw fallback strategies to reliably retrieve and convert the source code or documentation.
The best way to extract text from local and remote PDFs is using multiple extraction strategies with built-in retries and fallback logic, ensuring you get a summarized header and a cleanly saved Markdown file.
Yes, you need Playwright and BeautifulSoup installed as dependencies, because the Skill relies on Playwright to drive the browser scraper and BeautifulSoup with lxml for parsing the fetched WeChat article HTML into Markdown.
tw93Fetch URLs and PDFs and return concise source-grounded summaries.
revfactoryRead, parse, and convert HWP/HWPX documents to Markdown or other formats.
HouseGarofaloAutomate browser interactions and web scraping with Playwright, Puppeteer, Selenium, and Scrapy.
Khang5687Convert PDF, Office, HTML, and media files to Markdown using command-line tools.
