Parse local PDFs, DOCX, PPTX, XLSX, and images into structured JSON.
npx skills add https://github.com/kendreaditya/.config --skill liteparse
Please help me install this Agent Skill. Skill: liteparse Source: https://github.com/kendreaditya/.config/tree/main/claude/skills/liteparse Command: npx skills add https://github.com/kendreaditya/.config --skill liteparse
LiteParse enables fast, local parsing and text extraction of diverse document formats without relying on cloud services or LLMs.
Install LiteParse globally with npm i -g @llamaindex/liteparse and run the lit CLI to start parsing your documents.
High-intent search queries and answers about installing and using this skill.
You can parse local PDFs without cloud dependencies by using a CLI tool to process documents entirely offline. This approach extracts text and outputs structured JSON with bounding boxes for precise text location.
Yes, local document parsing supports scanned PDFs and image files using built-in OCR. This recovers text content from images while outputting structured JSON with coordinate data.
Yes, you can batch process multiple Word documents, spreadsheets, and slides locally by running the parser on whole directories. This enables scalable workflows for diverse formats without cloud services.
The best way to get structured JSON with bounding boxes from local documents is using a local CLI parser. It handles various formats and provides precise text location coordinates in the output.
Yes, you need Node 18 or higher and a global installation of the parsing package to run the local CLI. This environment setup is required for processing documents without cloud dependencies.
enowdevSearch registry metadata to discover and install modular agent skills.
a2ajinkyaConvert PDFs, Office files, and images into structured JSON via LiteParse.
juanreExtract structured data from LLM responses with JSON Schema validation.
juliuss1907Extract text from PDFs, scanned documents, and images using OCR.
