PDF Processing
Official skill for extracting, splitting, merging, and filling PDFs from an agent.
Use it for
Turning a stack of invoices or reports into text and tables the model can actually read
Skip it if
Scanned documents with heavy handwriting, and anything where layout fidelity is the requirement
What it is
An official document skill that gives an agent reliable PDF operations: text extraction, page splitting and merging, form filling, and table recovery. The reason it exists is that models are bad at guessing a PDF’s structure from raw bytes. It delegates the parsing to real libraries, then hands back structured content.
Install
Clone the repository, then copy the skill folder into your agent's skills directory — ~/.claude/skills/ for Claude Code. Skills are plain files: no build step, no daemon.
npx skills add https://github.com/anthropics/skillsHow to judge it
Read the SKILL.md before you install. A good skill states when it applies, what it must not do, and how to verify the result. A skill that only lists adjectives will change the agent's tone without improving its output — skip those.
Other Productivity skills
- Skill Creator — Official skill for writing a new agent skill with the right structure.
- Claude Code Templates — A large catalogue of ready-made agent components: skills, agents, and commands.
- DOCX Editing — Official skill for reading and editing Word documents without breaking their formatting.