# Ocr Reader

> Extract text from images and PDFs using OCR. Use when the user uploads or references a scanned document, receipt, invoice, or image with text.

- Skill: `jigarjani-dev/ocr-reader` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add jigarjani-dev/ocr-reader`
- Raw SKILL.md: https://api.skillmd.com/api/skills/jigarjani-dev/ocr-reader/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Finance & Business
- License: Apache-2.0
- Author: jigarjani-dev (https://skillmd.com/u/jigarjani-dev)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/jigarjani-dev/ocr-reader

---


# OCR Reader

Extract text from images and PDF documents.

## When to use
- "read this receipt", "what does this invoice say", "extract text from this scan"

## Scripts
- `scripts/extract.py` — OCR a file. Args: `file_path`, `image_description` (optional fallback text).

## Procedure
1. Run `scripts/extract.py` with `file_path`.
2. Return the extracted text to the user.