skills.rest
guillempuche
guillempucheCOMMUNITY
Explore all skills by this author →
GitHub

airparser-api

Access Airparser document parsing via REST API with JSON schemas.

Updated Dec 24, 2025
Search Tags:#automation#ocr#api#llm#webhooks#document parsing#airparser
One-click install
npx skills add https://github.com/guillempuche/transports-pau-automatizaciones --skill airparser-api
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: airparser-api
Source: https://github.com/guillempuche/transports-pau-automatizaciones/tree/main/.claude/skills/airparser-api
Command: npx skills add https://github.com/guillempuche/transports-pau-automatizaciones --skill airparser-api

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates the extraction of structured data from various document types like emails, PDFs, and images, eliminating manual data entry and processing bottlenecks.

Core Features & Use Cases

  • API Integration: Seamlessly connect Airparser's powerful OCR and LLM capabilities into your existing workflows via its API.
  • Custom Extraction Schemas: Define precise rules for extracting specific fields using natural language descriptions.
  • Real-time Webhooks: Receive parsed data instantly as documents are processed, enabling immediate downstream actions.
  • Use Case: Automatically extract key details (like invoice number, date, and total amount) from scanned receipts submitted by drivers, and feed this data directly into a Google Sheet for accounting.

Quick Start

Use the airparser-api skill to upload the file 'receipt.pdf' to the inbox with ID 'abc123'.

Frequently Asked Questions about airparser-api

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

FAQPage Schema
How do I automate data extraction from PDFs and emails using an API?▼

Automate data extraction from PDFs and emails by integrating Airparser's REST API to apply OCR and LLM-based parsing into your workflows. You define custom extraction schemas using natural language and receive structured JSON payloads in return.

Can I define custom fields to extract specific data from scanned documents?▼

You can define custom extraction schemas to parse specific fields from scanned documents by providing natural language descriptions. This allows the LLM to identify and extract precise data points like invoice numbers or dates into structured formats.

How do I get parsed document data instantly for downstream automation?▼

Get parsed document data instantly by configuring real-time webhooks within the API integration. Once documents are processed through OCR and LLM extraction, the parsed structured JSON is pushed directly to your specified webhook endpoint.

What do I need to integrate document parsing into my automated workflows?▼

To integrate document parsing into automated workflows, you need an API key for authentication, structured JSON payloads for defining extraction rules, and a target inbox ID for uploading files like PDFs or images.

Does this approach work for extracting structured data from images like receipts?▼

Extracting structured data from images like receipts is fully supported through the API's OCR capabilities. You can upload scanned receipt files to a specific inbox ID and apply custom schemas to capture key details for automated accounting.

Related Skills

Explore More Software Engineering Skills→
UpstageAIUpstageAI
9

upstage-schema-generation

Generate JSON schemas for structured document information extraction.

Official
Advanced
orthogonal-shorthogonal-sh
12

google-sheets

Automate Google Sheets tasks for creating spreadsheets, reading data, and updating cells.

Official
Intermediate
afel6afel6

webhook-subscriptions

Create and manage webhook subscriptions that trigger Hermes agent runs from external POSTed events.

Community
Advanced
LamseyahEliasLamseyahElias

ocr-and-documents

Extract text from PDFs and scanned documents using pymupdf and marker-pdf.

Community
Intermediate