Agent skill · Anthropic Agent Skills
/pdf Work with PDF files: extract, merge, fill and create
The pdf skill gives Claude a working playbook for PDF tasks: pulling text and tables, merging and splitting files, rotating pages, filling forms, handling encryption and generating new PDFs. It relies on Python libraries such as pypdf, pdfplumber and reportlab plus command-line tools like pdftotext and qpdf, with separate reference files for forms and advanced cases.
Works with
- Claude Code
Used forDocuments and files
When to use it
- You need text or tables extracted from a PDF into another format
- Several PDFs must be combined, split by page range, or rotated
- A PDF form has to be filled in, or a new PDF report generated from data
How it works
- 1Identify the task
Claude matches the request to a reading, editing, form-filling or creation path.
- 2Pick the tool
It chooses a Python library or CLI tool suited to that operation.
- 3Load extra guidance
For forms or advanced features it reads the bundled FORMS.md or REFERENCE.md first.
- 4Write the output
It runs the code and saves the resulting PDF or extracted data to disk.
What it steers the agent away from
- Losing table structure when extracting content
- Broken text from Unicode sub- and superscripts in generated PDFs
- Guessing at form field handling instead of following a tested procedure
Install this skill
It installs with the Anthropic Agent Skills pack.
Claude CodeAdds the repo as a plugin marketplace, then installs the document set and the example set separately.
/plugin marketplace add anthropics/skills
/plugin install document-skills@anthropic-agent-skills
/plugin install example-skills@anthropic-agent-skillsCommands come from the author’s README; check it for changes before you run them.
Questions
Can it handle scanned PDFs?
Its description lists OCR on scanned PDFs among supported tasks, which depends on the OCR tooling available in your environment.
What license is the pdf skill under?
The README states the document skills, including pdf, are open source under Apache 2.0, and the folder ships its own LICENSE.txt with that license.
More guides from Anthropic Agent Skills
/mcp-builderBuild MCP servers that connect agents to external APIsPlans, builds and evaluates MCP servers in TypeScript or Python that wrap external APIs.Read the guide →/skill-creatorCreate, test and tune your own agent skillsDrafts new skills, tests them on sample prompts and tunes their trigger descriptions.Read the guide →
Also in this pack
/academy-guideSuggests a matching Claude Academy course or tutorial after answering how-to questions about Claude.↗/algorithmic-artCreates original generative art in p5.js with seeded randomness and adjustable parameters.↗/brand-guidelinesApplies Anthropic's brand colors and typography to documents, slides and other artifacts.↗/canvas-designProduces original static visual designs such as posters as PNG or PDF files.↗/claude-apiGuides building applications on the Claude API and official Anthropic SDKs across languages.↗/discernment-nudgeAdds two or three follow-up questions that help users check facts and assumptions.↗/doc-coauthoringLeads a staged workflow for drafting specs, proposals and other structured documents with the user.↗/frontend-designSteers new or reworked user interfaces toward deliberate, non-templated visual design choices.↗/internal-commsDrafts internal communications such as status reports, leadership updates and incident reports.↗/slack-gif-creatorMakes small animated GIFs sized and validated for use in Slack.↗/theme-factoryApplies one of ten preset color and font themes, or a new one, to an artifact.↗/web-artifacts-builderBuilds multi-component claude.ai HTML artifacts with React, Tailwind CSS and shadcn/ui, bundled into one file.↗
Summary by trendhub. The skill itself lives in anthropics/skills/skills/pdf by Anthropic (Apache-2.0); read the full, current text there.