skills.rest
andrewyng
andrewyngCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill

Automate document parsing, structured data extraction, and classification via the LandingAI ADE API.

13.9k|1.2k|Updated Oct 30, 2025
Search Tags:#ocr#pdf parsing#document extraction#data classification#landingai#ade
One-click install
npx skills add https://github.com/andrewyng/context-hub --skill skill-andrewyng
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill
Source: https://github.com/andrewyng/context-hub/tree/main/content/landingai-ade/skills
Command: npx skills add https://github.com/andrewyng/context-hub --skill skill-andrewyng

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the extraction of structured data, classification, and splitting of documents, transforming unstructured content into usable information.

Core Features & Use Cases

  • Document Parsing: Converts PDFs, images, and spreadsheets into markdown.
  • Structured Data Extraction: Extracts specific fields based on a defined schema.
  • Document Classification & Splitting: Identifies and separates different document types within a single file.
  • Use Case: Automatically extract invoice details (number, date, amount) from a batch of scanned PDF invoices, or classify a multi-page PDF into separate documents like bank statements and pay stubs.

Quick Start

Use the LandingAI ADE skill to parse the document located at '/path/to/your/document.pdf'.

Frequently Asked Questions about skill

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

FAQPage Schema
How do I extract structured data from scanned PDF invoices?▼

To extract structured data from scanned PDF invoices, you can use this Skill to automate document parsing and pull specific fields like invoice number, date, and amount based on a user-defined schema via the LandingAI ADE API.

What is the best way to convert PDFs and images into markdown?▼

The best way to convert PDFs and images into markdown is by using document parsing features that transform unstructured content into usable text, handling various file types like spreadsheets and scanned documents automatically.

Can I classify and split a multi-page PDF containing different document types?▼

Yes, you can classify and split a multi-page PDF. This Skill identifies and separates different document types within a single file, such as distinguishing bank statements from pay stubs for organized processing.

Does asynchronous job processing support large document extraction?▼

Asynchronous job processing does support large document extraction. This Skill utilizes the LandingAI ADE API to handle asynchronous jobs, ensuring large documents are parsed and extracted without timing out.

What file formats are supported for document parsing and data classification?▼

Supported file formats for document parsing and data classification include PDFs, images, and spreadsheets. The Skill processes these unstructured files to extract specific fields or convert them into markdown.

Related Skills

Explore More Product & Management Skills→
AgentientAgentient
2

mcp-pydantic-tool-definition

Define MCP tool schemas with Pydantic models and strict validation.

Official
Advanced
glebisglebis
345

health-data

Query Apple Health SQLite data to generate Markdown, JSON, and FHIR R4 reports.

Community
Advanced
caobingshengcaobingsheng
1

pdf

Process PDFs by extracting text, merging, splitting, rotating, watermarking, and filling forms.

Community
Advanced
NeoLabs-SystemsNeoLabs-Systems
23

ocr-and-documents

Extract text from PDFs and scanned documents using OCR.

Official
Intermediate