Extract a report’s content
Read selectable text and tables, or use OCR for scanned pages when needed. Compare extracted values and headings with the original pages.
PDF by Anthropic
Use PDF by Anthropic to work with PDF files through an agent: extract text and tables, combine or split pages, prepare forms, or create a document for sharing. Choose the operation from the actual input, then check extracted content and the rendered output before delivery.
Install and get started
Choose your agent to see how to get started. In Floatboat, copy a request that asks the agent to read the original instructions. Other options show the Skill installation command or the publisher’s native setup steps.
Choose an agent
Start in Floatboat
Copy the request into a Floatboat conversation
Read the original PDF instructions at https://github.com/anthropics/skills/blob/main/skills/pdf/SKILL.md. Explain its purpose, required tools, and installation options, then help me use it.Let the agent read the original instructions and check how to use them in your environment.
Download Floatboat ↗Try this request
Extract the tables from this PDF report into a structured file. Check whether the pages are scanned, preserve row labels, and flag uncertain values rather than filling them in.
About PDF
PDF is Anthropic’s document Skill for reading, creating, and modifying PDF files. It routes work to Python libraries and command-line tools according to the operation: extracting content, organizing pages, generating documents, processing scanned pages, or handling forms through separate instructions. A text-based report and a scanned document need different extraction methods, so the input matters as much as the requested output. The Skill provides workflow guidance and references; its required libraries and utilities must be available in the execution environment. Anthropic publishes this document Skill as source-available under its specific license terms. Obtain the Skill package from Anthropic’s official repository and review its license before use.
Use Cases for PDF
Explore PDF tasks where the input format determines the method. Extract a report’s text or tables, organize several files into a correctly ordered document, or prepare a form workflow after checking whether the source contains selectable text, scanned pages, or interactive fields.
Organize a document package
Merge selected PDFs or split a file by page range. Verify the requested order, page count, and orientation before sharing.
Prepare a PDF form
Inspect the form and follow the dedicated field instructions. Check that entered values align with the intended labels and saved output.
How to Use PDF
Provide the PDFs and specify the pages, fields, or content you need. Have the agent inspect the file type and follow the relevant extraction, editing, or form instructions, then compare the output with the source and inspect rendered pages where layout matters.
- 01
Inspect the input PDF
Identify selectable text, scanned pages, and form fields. Specify the pages and output format that the task requires.
- 02
Run the matching workflow
Ask the agent to follow the relevant source instructions with the required tools. Preserve the original and write a clearly named output.
- 03
Verify content and pages
Compare extracted or edited information with the source. Render layout-sensitive outputs and inspect page order, clipping, and form values.
Explore More Agent Skills
Read another Skill guide and check its original source before using it.
PDF FAQ
Can this Skill read scanned PDFs?
The source includes OCR-related processing for scanned documents. OCR accuracy depends on image quality, language, and page structure, so important text and values should be checked against the scan.
Will text extraction preserve the original layout?
Not necessarily. Text extraction and page rendering are different operations. If columns, footnotes, or reading order matter, inspect the pages and choose an extraction method suited to that structure.
How are fillable forms handled?
The source directs form work to its dedicated FORMS.md instructions. Inspect the actual fields and verify saved values in the resulting PDF instead of assuming labels correspond to field names.
Does it require tools beyond an agent?
Yes. Different operations use Python libraries and command-line utilities for extraction, rendering, OCR, or document generation. The host environment must provide the tools needed for the selected operation.
Is this PDF Skill open source?
Anthropic describes its document Skills as source-available, and this folder carries a proprietary LICENSE.txt. Consult that file and the official installation guidance rather than treating public source access as a redistribution permission.
What should I specify when merging or splitting files?
List the source files, required order, page ranges, and output names. Verify the output page count and a few boundary pages where one source or range changes to another.