open_webpage

What problem does it solve?

It removes the manual effort of copying, reading, and reformatting content by automatically fetching a URL and extracting the complete readable text from both HTML pages and PDFs.

Core Features & Use Cases

• Webpage HTML parsing: Downloads an HTML document, strips non-content elements (like scripts/styles), and converts the page into cleaned, readable text.
• PDF text extraction: Detects PDFs by content-type and file/headers heuristics, then extracts full text from the PDF bytes.
• No truncation and clean output: Returns the entire parsed page text, with basic whitespace and formatting cleanup.
• Use Case: You need the full content of a documentation page (or a linked PDF spec) for summarization or analysis, but you want it reliably converted into plain text.

Quick Start

Use the open_webpage skill to fetch and parse the URL https://example.com and return the full parsed text.