PA

paddle-ocr-validation

Automates the extraction of invoice and receipt data using OCR with field-level validation.

Install

mkdir -p .claude/skills/paddle-ocr-validation && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/272" && unzip -o skill.zip -d .claude/skills/paddle-ocr-validation && rm skill.zip

Installs to .claude/skills/paddle-ocr-validation

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

PaddleOCR-based receipt and BIR form extraction with validation
63 charsno explicit “when” trigger
Beginner

Key capabilities

  • Extract data from receipts in BIR format
  • Extract data from invoices
  • Validate extracted form fields
  • Assign confidence scores to extractions
  • Verify data at the field level

How it works

The skill uses PaddleOCR to extract specified fields from an image and then applies validation and confidence scoring.

Inputs & outputs

You give it
image_path='receipt.jpg', fields=['merchant', 'tin', 'total', 'vat', 'or_number']
You get back
receipt data with extracted fields

When to use paddle-ocr-validation

  • Extract merchant and VAT data from receipts
  • Validate BIR form 1601-C fields
  • Automate invoice data entry into databases
  • Verify form field accuracy post-extraction

About this skill

PaddleOCR Validation

Extract and validate data from receipts, invoices, and BIR forms.

What This Does

  • Receipt OCR (BIR format)
  • Invoice data extraction
  • Form validation
  • Confidence scoring
  • Field-level verification

Quick Example

receipt = paddle_ocr.extract_bir_form(
    image_path='receipt.jpg',
    fields=['merchant', 'tin', 'total', 'vat', 'or_number']
)

Getting Started

"Scan this restaurant receipt" "Validate BIR form 1601-C"

How it compares

This skill adds validation and confidence scoring to OCR extraction, unlike basic text recognition.

Compared to similar skills

paddle-ocr-validation side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
paddle-ocr-validation (this skill)109moNo flagsBeginner
data-engineering137moReviewAdvanced
crawl4ai218moReviewIntermediate
data-cleaning-pipeline135moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

data-engineering

pluginagentmarketplace

ETL pipelines, Apache Spark, data warehousing, and big data processing. Use for building data pipelines, processing large datasets, or data infrastructure.

13192

crawl4ai

basher83

This skill should be used when users need to scrape websites, extract structured data, handle JavaScript-heavy pages, crawl multiple URLs, or build automated web data pipelines. Includes optimized extraction patterns with schema generation for efficient, LLM-free extraction.

21137

data-cleaning-pipeline

aj-geddes

Build robust processes for data cleaning, missing value imputation, outlier handling, and data transformation for data preprocessing, data quality, and data pipeline automation

13143

ocr

trpc-group

Extract text from images using Tesseract OCR

3562

airflow-dag-patterns

wshobson

Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.

445

instrument-data-to-allotrope

anthropics

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full ASM JSON, flattened CSV for easy import, and exportable Python code for data engineers. Common triggers include converting instrument files, standardizing lab data, preparing data for upload to LIMS/ELN systems, or generating parser code for production pipelines.

346

Search skills

Search the agent skills registry