本文へスキップ
TakoAPI
スキル一覧に戻る

greek-document-ocr

satoshistackalotto 作

DevOps & Cloud
—まだ評価がありません
あなたの評価

概要

Greek-language OCR using Tesseract.

説明

このスキルでできること

Greek-language OCR using Tesseract for scanned invoices, receipts, contracts, and government forms. Extracts structured data including VAT numbers, amounts, and dates from Greek business documents. All processing runs locally with no cloud APIs.

Local processing keeps sensitive Greek financial documents off cloud services while still automating structured data extraction from printed and handwritten sources.

使いどころ

  • Digitizing stacks of Greek supplier invoices for monthly accounting
  • Extracting VAT amounts and rates from Greek POS receipts
  • Processing AADE and EFKA government forms into structured data
  • Converting handwritten Greek notes and signatures to searchable text
  • Exporting OCR results to QuickBooks or Xero accounting software

ワークフロー例

入力

User asks: Process today's batch of scanned Greek invoices

エージェント
  1. 1

    Assess image quality and detect Greek text layout

  2. 2

    Enhance images for Greek character recognition

  3. 3

    Run Tesseract OCR with Greek language model

  4. 4

    Extract and validate VAT numbers, amounts, and dates against Greek business rules

  5. 5

    Export structured invoice data to CSV or accounting software format

出力

Structured invoice records with supplier names, VAT numbers, line items, and totals ready for accounting import

要件

  • Tesseract OCR with Greek language pack (tesseract-ocr-ell)
  • Xero API key (XERO_API_KEY) for direct Xero integration (optional)

インストール

clawhub install satoshistackalotto/greek-document-ocr

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク