SkillWriting

liteparse

Extract document text with layout information.

Apache-2.0 licence

What it does

Parses local PDFs, Office files and images into text with spatial coordinates. It can run OCR, produce Markdown or JSON and render pages for later review or search ingestion.

Installation

This command adds the whole Scientific Agent Skills collection, which includes liteparse.

npx skills add K-Dense-AI/scientific-agent-skills

  • The installer offers the upstream collection, including specialist science skills not listed here. Select only the skills you need; installing instructions does not install their runtime dependencies.
  • Individual skills have their own licence metadata, which can differ from the repository MIT licence.

Installation options in the README

Using this skill

  • Python 3.10+ with liteparse 2.15.0. LibreOffice required for Office formats; images convert natively. Tesseract is bundled but missing language data downloads on first use. Optional HTTP OCR requires network access and server-specific authentication.

Part of a collection