pdf — Claude Code skill: what it does, how to install
This skill lets an agent read, create, and edit PDF files, including forms and scanned documents. Use it when PDF work is part of the task.
- Author anthropics
- License LicenseRef-Proprietary
- GitHub ★ 183,434
- Installs 216,041
- Updated 2026-10-09
- Source on GitHub
What pdf does
The skill handles common PDF tasks: extracting text, tables, and images; merging or splitting files; rotating pages; adding watermarks; creating documents; and filling forms. It also covers encryption and decryption. For scanned PDFs, it can run OCR so the document becomes searchable.
The guide includes Python examples with pypdf, pdfplumber, and reportlab, plus command-line workflows for pdftotext, qpdf, pdftk, and pdfimages. OCR requires pytesseract and pdf2image, installed with pip install pytesseract pdf2image.
Install it when Claude Code needs to inspect or produce PDF files. It is unnecessary for tasks that do not involve PDFs.
What it helps with
- extract text and tables from a PDF
- merge several documents into one file
- split a PDF into separate pages
- run OCR on scanned documents
- fill a PDF form or add a watermark
How to install pdf
Command from the source
/plugin marketplace add anthropics/skillsCommand from the source
/plugin install document-skills@anthropic-agent-skillsCommand from the source
npx skills add anthropics/skills --skill pdf -a claude-codeWith the Skills CLI (Vercel)
npx skills add anthropics/skills --skill pdf -a claude-codeManually
~/.claude/skills/pdf/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/pdf/
Manually
.agents/skills/pdf/SKILL.mdFor all projects use ~/.agents/skills/
Manually
.cursor/skills/pdf/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
GitHub CLI (gh ≥ 2.90)
gh skill install anthropics/skills pdfManually
.github/skills/pdf/SKILL.mdGemini CLI
gemini skills install https://github.com/anthropics/skills --path skills/pdfManually
.devin/skills/pdf/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
How to use it: example prompts
- Extract text and tables from `document.pdf` and save the results to separate files.
- Merge `doc1.pdf`, `doc2.pdf`, and `doc3.pdf` into `merged.pdf`.
- Run OCR on `scanned.pdf` and make it searchable.
Questions about pdf
How do I install pdf in Claude Code?
Add the marketplace with /plugin marketplace add anthropics/skills, then install it with /plugin install document-skills@anthropic-agent-skills. You can also use npx skills add anthropics/skills --skill pdf -a claude-code.
What does the pdf skill do?
It helps the agent read, create, and edit PDF files. Its workflows cover text and table extraction, merging, splitting, forms, images, watermarks, encryption, and OCR.
What is required for OCR with pdf?
OCR requires the Python packages pytesseract and pdf2image. Install them with pip install pytesseract pdf2image.
