Fetch URLs and PDFs and return concise source-grounded summaries.
npx skills add https://github.com/tw93/Waza --skill read-tw93
Please help me install this Agent Skill. Skill: read Source: https://github.com/tw93/Waza/tree/main/plugins/waza/skills/read Command: npx skills add https://github.com/tw93/Waza --skill read-tw93
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask 看这个链接/读一下/read this/check this URL. Not for local text files already in the repo.
Fetch the URL or PDF and return a concise, source-grounded summary.
High-intent search queries and answers about installing and using this skill.
To summarize web content from a URL or PDF, the extractor fetches the source content and returns a concise, source-grounded summary by default. It handles plain read requests for online pages and documents automatically.
Yes, you can convert web pages and PDFs to clean Markdown. When you ask to quote, cite, or save the content, the tool extracts the source text and formats it into Markdown for downstream use.
The URL reader handles paywalled articles and dynamic pages by falling back from local extraction to proxy-based rendering or alternative parsers. This ensures content extraction succeeds even when standard fetching fails.
Extracting content from URLs and PDFs relies on requests, readability, html2text, playwright, beautifulsoup4, and lxml. These dependencies enable fetching, parsing, and rendering web content or documents.
You should not use this URL reading and summarization approach for local text files already in your repository. It is designed specifically for fetching and extracting content from external URLs and PDFs.
The best way to extract web content for downstream workflows is to request a conversion to Markdown. This produces clean, formatted output ready for quoting, citing, or feeding into subsequent processing tasks.
AbilityaiExtract EPUB chapters into separate markdown documents.
u9401066Extract text, figures, and citations from PDFs into Markdown.
Marcu-LoretoConvert HTML presentations to editable .pptx files using Python libraries.
olostepScrape up to 10,000 URLs in parallel with configurable output formats.
