skills.rest
a2ajinkya
a2ajinkyaCOMMUNITY
Explore all skills by this author →
GitHub

liteparse-ingest

Convert PDFs, Office files, and images into structured JSON via LiteParse.

1|Updated May 10, 2026
Search Tags:#ocr#pdf#docx#batch-processing#json-output#document-ingestion#liteparse
One-click install
npx skills add https://github.com/a2ajinkya/phone-pi --skill liteparse-ingest
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: liteparse-ingest
Source: https://github.com/a2ajinkya/phone-pi/tree/main/skills/liteparse-ingest
Command: npx skills add https://github.com/a2ajinkya/phone-pi --skill liteparse-ingest

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ingesting documents into an AI workspace is tedious and error-prone when handling PDFs, Office files, and images. LiteParse-ingest provides a fast, local way to convert documents into structured JSON for context-aware AI workflows.

Core Features & Use Cases

  • Fast local parsing of PDFs, DOCX, PPTX, XLSX, and common image formats with preserved layout, text, and bounding boxes.
  • Batch ingestion: process directories of documents to produce consistent JSON outputs for large-scale data preparation.
  • Output versatility: obtain structured JSON, plain text, or ready-to-use data for downstream tasks, references, or citations.

Quick Start

Parse a document with liteparse-ingest to generate a JSON representation of its content.

Frequently Asked Questions about liteparse-ingest

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert PDFs and Office files into structured JSON for AI workflows?▼

Batch ingestion processes entire directories of documents to produce consistent JSON outputs, allowing large-scale data preparation for AI workflows without manual file-by-file parsing.

Can I extract text with bounding boxes from images and PDFs locally?▼

For automated workflows, document ingestion tools often expose CLI scripts that allow you to parse files and generate JSON or plain text outputs directly from the command line.

What is the best way to batch process directories of documents for AI data preparation?▼

Batch ingestion processes entire directories of documents to produce consistent JSON outputs, allowing large-scale data preparation for AI workflows without manual file-by-file parsing.

Does local document ingestion support OCR for scanned images and PDFs?▼

You can parse single files or batch process entire directories of PDFs, DOCX, PPTX, XLSX, and common images, outputting structured JSON, plain text, or ready-to-use data for downstream tasks.

How do I automate document parsing workflows using CLI scripts?▼

Documents like PDFs, DOCX, PPTX, XLSX, and images are converted into structured JSON with preserved layout and bounding boxes, providing ready-to-use data for references, citations, and downstream tasks.

Related Skills

Explore More Data & Analytics Skills→
mxzinkemxzinke
2

document-parse

Parse PDFs, DOCX, PPTX, XLSX, and images into text or structured JSON.

Community
Intermediate
tassiovaletassiovale
13

liteparse

Extract text and bounding boxes from PDFs, Office files, and images.

Community
Intermediate
Aurora-AIAurora-AI
1

Elysian Integrator

Integrate AI agents with Postgres databases and orchestrate workflows via @start and @listen.

Community
Advanced
heysuhasheysuhas
2

ocr-and-documents

Extract text, tables, and images from scanned PDFs and office files.

Community
Intermediate