# ocr-document-processor

Pulls text and structure out of scans, photos and scanned PDFs. Useful when the only copy of a document is an image.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 4800 installs · ★ 122
- Author: dkyazzentwatwa
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/dkyazzentwatwa/chatgpt-skills/tree/HEAD/ocr-document-processor/SKILL.md
- Updated: 2026-04-08
- HTML: https://affpapa.org/en/nevibecode/skills/ocr-document-processor

## What it does

The skill walks the agent through OCR-heavy inputs. First it picks the mode: plain recognition, structured extraction, or parsing built for one document type. Noisy scans with skew, blur or shadows get preprocessed before anything is read.

Two layers of tooling ship with it. Core work goes through `scripts/ocr_processor.py`; narrow cases have their own helpers, `scripts/business_card_scanner.py` and `scripts/receipt_scanner.py`. Output can be text, markdown, JSON or HTML, and tables from scanned pages are covered too, along with searchable PDF export.

Low-quality sources get flagged. Rotated pages, handwriting and mixed languages all come back with confidence caveats, and the skill tells the agent not to present weak fields as exact. Set the language explicitly when accuracy matters. Digital PDFs that were never scanned are routed to `document-converter-suite` by default, since OCR adds nothing there.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add dkyazzentwatwa/chatgpt-skills --skill ocr-document-processor -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/ocr-document-processor/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/ocr-document-processor/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add dkyazzentwatwa/chatgpt-skills --skill ocr-document-processor -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/ocr-document-processor/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add dkyazzentwatwa/chatgpt-skills --skill ocr-document-processor -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/ocr-document-processor/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install dkyazzentwatwa/chatgpt-skills ocr-document-processor
```

2. **Manually: put the files in place**
- File: `.github/skills/ocr-document-processor/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add dkyazzentwatwa/chatgpt-skills --skill ocr-document-processor -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/dkyazzentwatwa/chatgpt-skills --path ocr-document-processor
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/ocr-document-processor/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add dkyazzentwatwa/chatgpt-skills --skill ocr-document-processor -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/dkyazzentwatwa/chatgpt-skills/tree/HEAD/ocr-document-processor/SKILL.md

## When to use it
- recover text from a photo of a document
- turn a scan into a searchable PDF
- extract a table from a scanned page
- parse a receipt into separate fields
- read contact details off a business card

## Example prompts
- OCR `invoice_042.png` and give me the text as markdown
- Pull the table from page 3 of `report_scan.pdf` into JSON
- Parse `receipt.jpg` and list the total, date and vendor

## Similar
- [pptx](https://affpapa.org/en/nevibecode/skills/pptx.md) — skill · 241433 installs
- [pdf](https://affpapa.org/en/nevibecode/skills/pdf.md) — skill · 216041 installs
- [docx](https://affpapa.org/en/nevibecode/skills/docx.md) — skill · 206304 installs
- [xlsx](https://affpapa.org/en/nevibecode/skills/xlsx.md) — skill · 187223 installs
- [brand-guidelines](https://affpapa.org/en/nevibecode/skills/brand-guidelines.md) — skill · 109043 installs
- [theme-factory](https://affpapa.org/en/nevibecode/skills/theme-factory.md) — skill · 94921 installs

From the same set: [dkyazzentwatwa/chatgpt-skills](https://affpapa.org/en/nevibecode/by/dkyazzentwatwa/chatgpt-skills.md) — 2 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md