Agent skill · Anthropic

PDF skill for Claude Code, Codex and Cursor

Extracts text and tables, merges, splits, fills forms and creates PDF files.

Officialname: pdf★ 184k (repo)pushed 2026-10-09See repoSKILL.md on GitHubchecked 2026-11-07

What it does, in the publisher's words

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable.

The description field of the SKILL.md. The agent reads only this at startup and decides from it when to load the full skill.

Install PDF

The skills CLI copies the skill into the folder of each agent you pick (Claude Code, Codex, Cursor, Copilot, Gemini CLI, OpenCode, Windsurf...). Add -g for all projects. Needs Node.js 22.20+. docs

npx skills add anthropics/skills --skill pdf

Works with

Claude Code, Claude.ai and Claude Desktop, Codex, GitHub Copilot, Cursor, Gemini CLI, OpenCode, Windsurf and other agents that read the open Agent Skills format.

  • Bundles 8 Python scripts the agent can run, so it needs Python on the machine. In the Claude apps, code execution must be on.

What's in the SKILL.md

17 sections
  • Overview
  • Quick Start
  • Python Libraries
  • pypdf - Basic Operations
  • pdfplumber - Text and Table Extraction
  • reportlab - Create PDFs
  • Command-Line Tools
  • pdftotext (poppler-utils)
  • qpdf
  • pdftk (if available)
  • Common Tasks
  • Extract Text from Scanned PDFs
  • Add Watermark
  • Extract Images
  • Password Protection
  • Quick Reference
  • Next Steps

Bundled files

11
  • LICENSE.txt
  • forms.md
  • reference.md
  • scripts/check_bounding_boxes.py
  • scripts/check_fillable_fields.py
  • scripts/convert_pdf_to_images.py
  • scripts/create_validation_image.py
  • scripts/extract_form_field_info.py
  • scripts/extract_form_structure.py
  • scripts/fill_fillable_fields.py
  • scripts/fill_pdf_form_with_annotations.py

Loaded only when the instructions point to them.

Facts

Skill name
pdf
Publisher
Anthropic (official)
Repo
anthropics/skills
License
Complete terms in LICENSE.txt
SKILL.md size
322 words, 309 lines
Bundled files
11, 8 scripts (Python), 2 docs
Repo stars
184k (as of 2026-10-24)
SKILL.md checked
2026-11-07

More skills from anthropics/skills

  • Canvas Design: Produces posters and static artwork as PNG or PDF files, guided by a written design philosophy.
  • Claude API: Reference for building on the Claude API and Anthropic SDKs: models, tool use, streaming, caching, pricing.
  • Doc Co-authoring: Walks you through drafting specs, proposals and design docs step by step with Claude.
  • Word Documents (DOCX): Creates, reads and edits Word .docx files, including templates, tracked changes and formatting.
  • Frontend Design: Steers UI work toward deliberate visual direction and typography instead of generic template looks.
  • MCP Server Builder: Guide for designing and building Model Context Protocol servers that wrap external APIs as tools.
  • PowerPoint (PPTX): Builds, reads and edits PowerPoint decks and templates, including layouts and speaker notes.
  • Skill Creator: Helps write new skills, refine existing ones and test how well they trigger and perform.
  • Slack GIF Creator: Makes small animated GIFs sized and validated for Slack's emoji and message limits.
  • Web Artifacts Builder: Builds multi-component HTML artifacts with React, Tailwind and shadcn/ui, bundled into one file.
  • Web App Testing: Uses Playwright to drive a local web app, check behavior, read console logs and take screenshots.
  • Excel Spreadsheets (XLSX): Opens, cleans, edits and creates spreadsheets (.xlsx, .csv), including formulas and charts.

FAQ

What does the pdf skill do?+

Extracts text and tables, merges, splits, fills forms and creates PDF files. In its own SKILL.md, Anthropic describes it as: "Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs,..."

How do I install the pdf skill?+

Run npx skills add anthropics/skills --skill pdf and pick your agents, or use the tab for your agent above. In Claude Code the skill ends up in ~/.claude/skills/pdf/SKILL.md; in Codex and Cursor in .agents/skills/pdf/.

Does PDF work in Codex, Cursor and Copilot, or only Claude?+

It's a standard SKILL.md, so any agent that reads the Agent Skills format can use it: Claude Code, the Claude apps, Codex, GitHub Copilot, Cursor, Gemini CLI, OpenCode, Windsurf and more.

Who maintains PDF?+

Anthropic, the company or project behind it, in the anthropics/skills repo on GitHub, last pushed 2026-10-09. License: Complete terms in LICENSE.txt.

Read a skill's SKILL.md and scripts before you install it: skills aren't verified by any agent vendor. Claude skills marketplace · How to install skills · MCP servers