# PDF processing workflows (/automation--pdf-processing)

/automation--pdf-processing is a Claude Code skill in the Code section. Builds a workflow to extract text and tables from PDFs, fill forms, merge or split pages, and run OCR on scanned documents.

- Web version: https://skills.sgomez.dev/en/s/automation--pdf-processing
- Section: [Code](https://skills.sgomez.dev/en/code.md)
- Author: Santiago Gómez de la Torre
- License: MIT
- Source: https://github.com/sgomez-dev/claude-skills/blob/main/skills/automation/pdf-processing.md
- Updated 10 Jul 2026

## How to ask for it

- `/automation--pdf-processing extract the tables from these invoice PDFs`
- `/automation--pdf-processing automatically fill out this PDF form`
- `/automation--pdf-processing merge these scanned PDFs and run OCR on them`

## Install

macOS · Linux:

```
curl -fsSL https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.sh | bash
```

Windows:

```
irm https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.ps1 | iex
```

Claude Code plugin:

```
/plugin marketplace add sgomez-dev/claude-skills
/plugin install automation-skills@claude-skills-collection
```

## Permissions

- Reads: `package.json`, `requirements.txt`, `pyproject.toml`, `*.pdf`, `*.py`, `*.js`, `*.ts`
- Writes: `pdf/**`, `output/**`, `*.py`, `*.js`, `*.ts`, `*.csv`, `*.json`
- Runs: `node`, `npm`, `python`, `pip`, `uv`, `tesseract`, `qpdf`
- Network: No
- Destructive: No

## Author's description

Build PDF workflows — extract text/tables, fill forms, merge/split, OCR fallback

- [How we review this](https://skills.sgomez.dev/en/methodology.md)