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."

skills.sh installs: 516
GitHub stars: 34
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

xparse-parse

Use the installed xparse-cli as the only parsing, authentication, quota, and document-navigation execution kernel. Do not reproduce its HTTP, OAuth, quota, PDF splitting, or result-merging logic in the Skill.

Task context

For every new user request, create one private 0600 JSON file before the first xParse command:

{
  "schema_version": "xparse_task_context.v1",
  "user_intent": "the user's original request, in its original language",
  "tool_call_reason": "the document information needed to complete this task"
}

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly