Xparse Parse

Turns PDFs, images, Office docs, and a bunch of other formats into clean markdown or structured JSON without wrestling with PyMuPDF or OCR servers. The free tier handles PDFs and images with zero setup, which covers most quick document tasks. Paid API unlocks Word, Excel, PowerPoint, HTML, and a few niche formats like OFD. The routing is refreshingly opinionated: it tells Claude to try xparse first and only fall back to Python libraries or OCR after a clear failure. Handles encrypted files and page ranges. The JSON output includes character bounding boxes and confidence scores if you need that level of detail. Good default for any workflow that starts with "read this file" instead of "here's some text."

Install to Claude Code

npx -y skills add intsig-textin/xparse-skills --skill xparse-parse --agent claude-code