DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5

How to extract PDF form fields in Claude Code with Anthropic Skills

Install the document-skills plugin, the same docx, pdf, pptx and xlsx Anthropic Skills behind Claude's document features, and ask Claude Code to work on your files by naming the skill.

Short answer: Run /plugin marketplace add anthropics/skills in Claude Code to register the repo as a plugin marketplace; then run /plugin install document-skills@anthropic-agent-skills to install the xlsx, docx, pptx and pdf Anthropic Skills; Mention the skill in your request, for example: Use the PDF skill to extract the form fields from path/to/some-file.pdf (use your own file path). All steps.

Who it is forSomeone in operations or finance who needs Claude to read and process PDFs, Word, PowerPoint or Excel files from the terminal.

The problemGetting reliable, repeatable document handling out of a general coding agent takes a lot of prompting each time.

The outcomeClaude Code with Anthropic's production document Anthropic Skills installed, so a plain request like using the PDF skill on a file works the same way every time.

What you need first

  • Claude Code to install the plugins (Claude.ai paid plans already include the example skills)
  • The Claude API only if you use pre-built or custom skills through the API
  • Many skills are Apache 2.0; the docx, pdf, pptx and xlsx skills are source-available, not open source

Steps

  1. Run /plugin marketplace add anthropics/skills in Claude Code to register the repo as a plugin marketplace
  2. Run /plugin install document-skills@anthropic-agent-skills to install the xlsx, docx, pptx and pdf Anthropic Skills
  3. Mention the skill in your request, for example: Use the PDF skill to extract the form fields from path/to/some-file.pdf (use your own file path)
  4. Name the docx, pptx or xlsx skill the same way for Word, PowerPoint and Excel files

Prompt for your agent

I installed the document-skills plugin from anthropics/skills. Use the PDF skill to extract the form fields from my PDF and list each field name with its current value. Do not modify the original file; write any output to a new file.

Caveat. The README says the docx, pdf, pptx and xlsx Anthropic Skills are source-available, not open source, so read each skill's LICENSE.txt before reusing the code. It also says these are demonstration Anthropic Skills and behavior may differ from Claude's built-in document features.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for anthropics/skills and "Extract PDF form fields in Claude Code"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer