Give your AI agent PDF superpowers — in one command.
Convert, extract, OCR, redact, sign, and fill documents from any coding agent.

Quickstart • Workflows • Features • 40+ Agents

1. Get a free API key → https://dashboard.nutrient.io/sign_up/?product=processor

2. Install & configure:

# Install the skill (works with 40+ agents)
npx skills add PSPDFKit-labs/nutrient-agent-skill

# Set your API key
export NUTRIENT_API_KEY="pdf_live_..."

3. Ask your agent:

"Extract the text from invoice.pdf"

That's it. Your agent now has full document processing capabilities.

• Python 3.10+
• uv installed: https://docs.astral.sh/uv/
• Nutrient API key

Works out of the box with 40+ AI coding agents:

Any agent that supports the Agent Skills standard works automatically.

You have a scanned PDF — no selectable text. Ask your agent:

"OCR scanned-contract.pdf in English and extract the text to a file"

What happens:

scanned-contract.pdf (image-only)
  → OCR (English) → searchable-contract.pdf (selectable text)
  → Extract text → contract-text.txt

You have an onboarding form to complete. Ask your agent:

"Fill employee-onboarding.pdf with name 'Jane Smith', start date '2026-03-01', and department 'Engineering', then digitally sign it"

What happens:

employee-onboarding.pdf (blank form)
  → Fill fields (name, date, department)
  → Digital signature (CMS)
  → employee-onboarding-signed.pdf ✅

You need to share a document but it contains sensitive data. Ask your agent:

"Redact all social security numbers, email addresses, and credit card numbers from patient-records.pdf"

What happens:

patient-records.pdf (contains PII)
  → Detect SSNs, emails, credit cards
  → Apply black redaction boxes (irreversible)
  → patient-records-redacted.pdf 🔒

Tip: For smarter redaction, try: "Use AI redaction to find and remove all personally identifiable information from contract.pdf" — this uses contextual AI analysis instead of pattern matching.

# Install to all detected agents
npx skills add PSPDFKit-labs/nutrient-agent-skill

# Install to specific agents only
npx skills add PSPDFKit-labs/nutrient-agent-skill -a claude-code -a codex -a cursor

# Install globally (available across all projects)
npx skills add PSPDFKit-labs/nutrient-agent-skill -g

Copy the nutrient-document-processing/ folder to your agent's skills directory:

Example for Claude Code:

git clone https://github.com/PSPDFKit-labs/nutrient-agent-skill.git
cp -r nutrient-agent-skill/nutrient-document-processing ~/.claude/skills/

nutrient-document-processing/
├── SKILL.md                          # Main instructions (loaded by agents)
├── scripts/
│   ├── *.py                          # Single-operation scripts
│   └── lib/common.py                 # Shared utilities
├── assets/
│   └── templates/
│       └── custom-workflow-template.py  # Runtime pipeline template
├── tests/
│   └── testing-guide.md
└── LICENSE                           # Apache-2.0

• scripts/*.py are single-operation scripts only.
• Multi-step workflows are generated at runtime in a temporary script from assets/templates/custom-workflow-template.py.
• Do not commit runtime pipeline scripts.

• SKILL.md — Agent instructions with setup and operation examples
• Testing Guide — Manual test procedures
• Custom Workflow Template — Runtime pipeline starting point
• API Playground — Interactive API testing
• Official API Docs — Nutrient documentation

Built by Nutrient (formerly PSPDFKit) — document SDKs trusted by thousands of companies worldwide.

Apache-2.0