skill

pdf-processing-pro — Claude Code skill: what it does, how to install

Q: How do I install pdf-processing-pro in Claude Code?

Run `npx claude-code-templates@latest --skill document-processing/pdf-processing-pro`. Alternatively, run `npx skills add davila7/claude-code-templates --skill pdf-processing-pro -a claude-code`.

Q: What system dependencies are needed for OCR?

You need the system package `tesseract-ocr`. Install it via `brew install tesseract` on macOS or `apt-get install tesseract-ocr` on Ubuntu.

Python scripts for form filling, table extraction, and PDF manipulation in Claude Code. Built for automated document workflows.

Install into Claude Code · claude-code-templates All methods and platforms ↓

npx claude-code-templates@latest --skill document-processing/pdf-processing-pro

Open on GitHub

What pdf-processing-pro does

This skill supplies Claude Code with Python scripts for document handling. The package includes analyze_form.py to inspect form inputs and fill_form.py for filling forms. Helper scripts handle merging and splitting files, while tabular data exports directly to CSV or Excel.

All scripts emit exit codes from 0 to 4. That simplifies debugging. Without the system binary tesseract-ocr, text recognition scripts will crash because the pytesseract module requires it.

Python packages pdfplumber, pypdf, pillow, pytesseract, and pandas must be installed first. For documents larger than 50MB, process pages one by one to avoid out-of-memory errors.

What it helps with

extract structured tables from PDF files into CSV or Excel
fill interactive PDF forms from JSON schemas
run OCR on scanned documents using Tesseract
split and merge multi-page PDF documents

Example prompts for the agent

Inspect form fields inside input.pdf using scripts/analyze_form.py
Export tables from report.pdf into tables.csv with scripts/extract_tables.py
Fill template.pdf with data.json and write the result to completed.pdf

How to install pdf-processing-pro

1claude-code-templates

npx claude-code-templates@latest --skill document-processing/pdf-processing-pro

2Skills CLI (Vercel)

npx skills add davila7/claude-code-templates --skill pdf-processing-pro -a claude-code

3Manually: put the files in place

~/.claude/skills/pdf-processing-pro/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/pdf-processing-pro/

Manually: put the files in place

.agents/skills/pdf-processing-pro/SKILL.md

For all projects use ~/.agents/skills/

Manually: put the files in place

.cursor/skills/pdf-processing-pro/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install davila7/claude-code-templates pdf-processing-pro

2Manually: put the files in place

.github/skills/pdf-processing-pro/SKILL.md

Platform CLI

gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/document-processing/pdf-processing-pro

Manually: put the files in place

.devin/skills/pdf-processing-pro/SKILL.md

The legacy .windsurf/skills/ path still works

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about pdf-processing-pro

How do I install pdf-processing-pro in Claude Code?

Run npx claude-code-templates@latest --skill document-processing/pdf-processing-pro. Alternatively, run npx skills add davila7/claude-code-templates --skill pdf-processing-pro -a claude-code.

What does pdf-processing-pro do?

It gives Claude Code pre-built Python CLI scripts for form processing, data validation, table extraction, and OCR.

What system dependencies are needed for OCR?

You need the system package tesseract-ocr. Install it via brew install tesseract on macOS or apt-get install tesseract-ocr on Ubuntu.

Similar skills

All skills for Office documents →

pptx official anthropics This skill helps create, read, and edit .pptx files and .potx templates. Use it when building a deck or extracting slide text. 241,433installs pdf official anthropics 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. 216,041installs docx official anthropics This skill creates, reads, and edits Word documents and templates. Use it for reports, letters, and files that need headings, tables, or page numbers. 206,304installs xlsx official anthropics Creates, reads, edits, and converts spreadsheet files. Use it when the requested deliverable is an Excel workbook or another tabular file. 187,223installs brand-guidelines official anthropics Applies Anthropic's official brand colors and fonts to documents, slides and other artifacts. Useful whenever something needs to match the company look. 109,043installs theme-factory official anthropics Applies preset color palettes and font pairs to slides, documents, and HTML pages. Use it when an artifact needs one consistent visual style. 94,921installs

From the same set238

The whole set →

documentation-expert This subagent creates, updates, and maintains project documentation, from README files to API references. Use it when docs need structure or a refresh. 6,992installs task-decomposition-expert Breaks down complex multi-step goals into a structured work breakdown structure with dependency graphs, effort estimates, and handoff plans. 6,870installs create-architecture-documentation A Claude slash command that turns your repo into architecture documentation: diagrams, ADRs and component descriptions. 6,136installs mcp-expert Designs and configures Model Context Protocol servers for Claude Code. It prepares ready-to-use JSON manifests for databases, APIs, and file access. 6,052installs nextjs-architecture-expert A Claude subagent for Next.js architecture: App Router, Server Components, Pages Router migration and performance work. 4,935installs refactor-code A slash command that walks Claude through 17 refactoring steps, from analysis and tests to performance checks and review prep. 4,890installs seo-analyzer A subagent for technical SEO audits, meta tag review and Core Web Vitals. Useful when you need a prioritized list of fixes for a site. 4,060installs react-performance-optimization A subagent that tracks down React performance problems: wasted re-renders, bloated bundles, memory leaks. Useful when a page drags or Core Web Vitals slip. 3,935installs