Turn web links and PDFs into clean Markdown.
What it does
Extracts readable Markdown from web links and PDFs for direct reading or further writing and analysis.
When to use it
Use first when asked to read or extract a URL, including before summarizing, rewriting, translating, or analyzing its content; exclude pasted full text, ordinary searches, YouTube extraction, and local non-PDF files.
How to use it
Give it a URL or local PDF path; it extracts Markdown, saves extraction-only results in Downloads unless preview-only is requested, and continues any requested downstream task.
What you provide
- a URL or local PDF path
Uses
Good to know
- cannot be undone: /tmp/input.pdf
What you need · 3
Python is needed for the Feishu and arXiv extraction routes.
The Feishu extractor imports requests, so that route needs the package available to Python.
Access · 8
This skill
/tmp/input.pdf
Downloads PDFs to a fixed path (irreversible)
r.jina.ai
Sends URLs to r.jina.ai