# What can the pdf skill do that Claude cannot do alone?

Canonical URL: https://bestskillsforclaude.com/en/skills/pdf
Language: en
Skill: pdf
Publisher: Anthropic (https://github.com/anthropics)
Source: https://github.com/anthropics/skills/tree/main/skills/pdf
License as stated by the publisher: Source available, not open source
Runtime: Claude apps and Claude Code
Category: Document work
Last reviewed: 2026-08-05

File operations. Reading a PDF is one thing; rebuilding one is another.

## Short answer
The pdf skill gives Claude real PDF operations: extracting text and tables, merging and splitting files, rotating pages, filling forms, adding watermarks and running OCR on scans. Install it whenever PDFs are an input or an output of the work, rather than something you only need summarised.

Best for: Invoice and report pipelines, scanned archives, and any task that ends with a single assembled PDF.
Skip it if: You only need the gist of one short document, which the model can already read without extra tooling.

## What to remember
- OCR on scans is the capability people most often miss, and the one that unlocks old archives.
- Merging, splitting and rotating are mechanical wins that remove a manual tool from the workflow.
- Table extraction is the highest risk step. Verify a sample before trusting a batch.
- Encrypted files need the password. The skill does not remove protection you do not have rights to.

## What it changes in practice
A PDF is a layout format, not a data format, which is why extraction is the hard part. The skill turns a category of work that usually needs a separate desktop tool into something an agent can do inside the same conversation as the analysis.
The assembly direction matters just as much. Producing one clean PDF from many sources, with pages in the right order and a watermark applied, is a small task that consumes a surprising amount of human time.
- Extract text and tables, including from scanned pages through OCR.
- Combine, split, rotate and watermark existing files.
- Fill forms and handle encrypted documents where you hold the password.

## Where it disappoints
Multi column academic layouts, tables that span pages and low quality scans still produce reading order mistakes. The failure is quiet, because the extracted text looks fine until you compare it with the page.
Treat any extraction that feeds a decision as a draft that needs a sampled check, especially in finance and compliance work.

## Install and first run
1. Install the document skills from anthropics/skills.
2. Start with one real file and one narrow operation, for example extracting the line items from an invoice.
3. Check the extraction against the original page before you build anything on top of it.

## Questions
### Can it read scanned documents?
Yes, through OCR, which is what makes scanned archives searchable rather than just viewable.

### Can it fill in a PDF form?
Yes, form filling is one of the supported operations, along with merging, splitting and watermarking.

### Is table extraction reliable?
It is the least reliable part. Verify a sample against the source pages before trusting a large batch.

## Sources
- anthropics/skills on GitHub: https://github.com/anthropics/skills
- anthropics/skills, pdf skill directory: https://github.com/anthropics/skills/tree/main/skills/pdf

## Other languages
- Spanish: https://bestskillsforclaude.com/es/skills/pdf
- Brazilian Portuguese: https://bestskillsforclaude.com/pt-br/skills/pdf
- Japanese: https://bestskillsforclaude.com/ja/skills/pdf